Article

Combining night time lights in prediction of poverty incidence at the county level

Authors:
To read the full-text of this research, you can request a copy directly from the authors.

Abstract

Long-term poverty data can support accurate decision-making. This study demonstrates an accurate and reliable method for identifying poverty areas and predicting poverty incidence based on night time light remote-sensing data and machine learning methods. Using data of poverty counties and poverty incidence in Guizhou Province of China as the training dataset, we show how to use machine learning to identify poverty counties and predict poverty incidence in the Yunnan-Guangxi-Guizhou Rocky desertification area. The identification accuracy of poverty-stricken counties was 76.5%. The root mean squared error, mean absolute error, and R² values of the poverty incidence rates were 5.01, 4.04, and 0.60, respectively. Using data from 2015 to verify the trained model, the R² value of the predicted and actual values of poverty incidence reached 0.95. With the progress in machine learning and night light remote sensing, poverty mapping combined with night time lights and machine learning can compensate for the data gap in deprived areas and provide a decision-making basis for sustainable development in poverty-stricken areas.

No full-text available

Request Full-text Paper PDF

To read the full-text of this research,
you can request a copy directly from the authors.

... Given the strong correlation of most human activities to the regional electricity demand, mapping the NTL intensity variations could potentially capture the regional economic activities. Such an approach could render two major benefits particularly in developing countries: lower survey cost and lower time in acquiring data when using it as a proxy for economic activities [2], [3], [4] and [5]. Moreover, another reason for using an indirect technique like satellite images to estimate the electricity demand is due to inconsistency and unreliable nature of the electricity data available in Sri Lanka. ...
... The results in columns (5)-(8) also show the same contrast between the two outcomes: there is no impact on first difference of the Mean NTL intensity even after allowing for differential effects for the Western province. However, when considering NTL intensity, while column (5) shows that average NTL intensity increased significantly (at 10% significance) across the country during lockdowns with no differential effect for the Western Province, column (7) shows that when considering the monthly change in NTL intensity, the Western Province had a negative significant effect in NTL intensity than the rest of the country. ...
... Several studies have employed (non-spatial) regression models in the prediction of poverty using satellite imagery (e.g., Pan & Hu, 2018;Xu et al., 2021;Yong et al., 2022). However, they ignored misspecifications that might occur due to induced spatial autocorrelation observed in data aggregated at a spatial unit, for example, county, ward, or municipality. ...
... (ii) Highlighting existing shortcomings of current studies (e.g., Pan & Hu, 2018;Xu et al., 2021;Yong et al., 2022) that have employed regression models that ignore spatial dependence in their respective formulation when | 5 KATUMBA et al. ...
Article
Full-text available
To realize the first sustainable development goal of ending “poverty in all its forms everywhere,” local governments in South Africa need to implement informed targeted policy interventions based on up‐to‐date data and sound analytics. Statistics South Africa (Stats SA) Censuses reveal the socioeconomic circumstances of people living in South Africa but are only conducted every 10 years. As a result, most analytical studies done in‐between Censuses rely on outdated socioeconomic data. This study demonstrates how poverty levels in one of the provinces of South Africa, Gauteng, can be predicted when up‐to‐date Census datasets are not available. The spatial lag model is used to explain the relationship between the South African Multidimensional Poverty Index (SAMPI) and statistically significant variables extracted from land use datasets (i.e., land areas classified as built‐up, informal, residential, township, and non‐urban), and to ultimately predict the levels of poverty. Out‐of‐sample predicted poverty levels obtained based on the spatial lag model correlate with the actual levels of poverty thereby reflecting known spatial patterns of the levels of poverty in Gauteng province.
... The diversification of multi-dimensional feature data played a crucial role in achieving high-precision regression results for the model in this study. Previous studies on poverty prediction relied mainly on NL data as the only data source to map the MPI [20,21]. While the nighttime light intensity effectively reflects economic activities, its exclusive use falls short in accurately estimating a county-level MPI due to the intricate interplay of economic, social, and natural factors. ...
... In machine learning models, these point-based pieces of information provide a comprehensive view of a re-gion's infrastructure and social welfare status, becoming significant predictors in poverty predictions. The layout of educational and healthcare resources is also frequently a focal point of policy decisions, reflecting the government's emphasis on poverty alleviation and regional development strategies, further highlighting their importance in predictive models [1,20,21]. Therefore, in analyzing and predicting multi-dimensional indicators of poverty, the feature data of education and healthcare points are indispensable key variables. ...
Article
Full-text available
The accurate and timely acquisition of poverty information within a specific region is crucial for formulating effective development policies. Nighttime light (NL) remote sensing data and geospatial information provide the means for conducting precise and timely evaluations of poverty levels. However, current assessment methods predominantly rely on NL data, and the potential of combining multi-source geospatial data for poverty identification remains underexplored. Therefore, we propose an approach that assesses poverty based on both NL and geospatial data using machine learning models. This study uses the multidimensional poverty index (MPI), derived from county-level statistical data with social, economic, and environmental dimensions, as an indicator to assess poverty levels. We extracted a total of 17 independent variables from NL and geospatial data. Machine learning models (random forest (RF), support vector machine (SVM), adaptive boosting (AdaBoost), extreme gradient boosting (XGBoost), and light gradient boosting machine (LightGBM)) and traditional linear regression (LR) were used to model the relationship between the MPI and independent variables. The results indicate that the RF model achieved significantly higher accuracy, with a coefficient of determination (R2) of 0.928, a mean absolute error (MAE) of 0.030, and a root mean square error (RMSE) of 0.037. The top five most important variables comprise two (NL_MAX and NL_MIN) from the NL data and three (POI_Ed, POI_Me, and POI_Ca) from the geographical spatial data, highlighting the significant roles of NL data and geographical data in MPI modeling. The MPI map that was generated by the RF model depicted the detailed spatial distribution of poverty in Fujian province. This study presents an approach to county-level poverty evaluation that integrates NL and geospatial data using a machine learning model, which can contribute to a more reliable and efficient estimate of poverty.
... hem, Random Forest (RF) is becoming increasingly popular in nonlinear regression studies (Breiman, 2001). It can manage high-dimensional data and explore multilevel interactions and nonlinear associations. Consequently, experts in the field of socioeconomic development predictions are paying increasing attention to the RF method G. Li et al., 2019;J. Xu et al., 2021). ...
... ability and computation efficiency as compared to many other modern algorithms in a number of international studies (Breiman, 2001). It can handle the complex relationships between predictors and is robust to noise (Arpaci et al., 2014;Delgado-Baquerizo et al., 2017;Song & Zhu, 2020b). Based on a combination of related research(G. Li et al., 2019;J. Xu et al., 2021), we selected eight NTL statistical characteristics for each administrative unit regarding nighttime lighting data as the training features for the training process. Each unit's training features and descriptions used by Random Forest model are listed in Table 4. The measured-IHDI samples are separated into two parts, the training datase ...
Article
China shares its board with one developed and thirteen developing countries. A timely, precise, and efficient socioeconomic study of border regions is vital for evaluating political problems and identifying potential economic prospects. Usually, conventional socioeconomic statistical data suffer from significant time lags and unequal statistical scales. This study utilized the random forest model to establish a connection between satellite-derived nighttime light data and the improved human development index (IHDI). The relationship was then applied to predict the IHDI, and differences in its strength, trend, and change pattern by bordering statistical units from 2000 to 2020 were evaluated. Our findings indicate that China's administrative units (AUCs) are more developed and have a greater development trend than their neighbors (AUNs). Except for the Tibet Autonomous Region, all AUCs are spatially more developed than AUNs, with the discrepancy widening between 2000 and 2020. Socioeconomic changes in AUCs predominantly exhibit a forward-leaping development pattern, which may be represented by a logarithmic (53%) or sigmoid (22.6%) function, whereas AUNs' socioeconomic changes exhibit either a late-leaping exponential (34.2%) or static development (18.6%) trend. The IHDI values in AUCs exhibit greater disparity as measured by the Theil index, than the AUNs, primarily due to the natural environment, resource availability, and development policies. In less developed regions, harsh natural surroundings, temperatures, and scarce natural resources hinder socioeconomic growth.
... Census data is the most reliable source of data for poverty mapping, but it has the problems of high cost, long cycle, and low efficiency (Minot and Baulch 2005;Niu et al. 2020). With the advancement of technology, multi-source big data have been used to assist poverty mapping, such as night lights (Jean et al. 2016;Andreano et al. 2021;Xu et al. 2021), remote sensing images (Elvidge et al. 2009), mobile phones (Pokhriyal and Jacques 2017), and livelihood assets (Erenstein et al. 2010). Poverty mapping based on multi-source data has been widely used in anti-poverty practices in regions such as Africa (Jean et al. 2016), Southeast Asia (Erenstein et al. 2010;Olivia et al. 2011;Xu et al. 2021), and Latin American and Caribbean (Andreano et al. 2021). ...
... With the advancement of technology, multi-source big data have been used to assist poverty mapping, such as night lights (Jean et al. 2016;Andreano et al. 2021;Xu et al. 2021), remote sensing images (Elvidge et al. 2009), mobile phones (Pokhriyal and Jacques 2017), and livelihood assets (Erenstein et al. 2010). Poverty mapping based on multi-source data has been widely used in anti-poverty practices in regions such as Africa (Jean et al. 2016), Southeast Asia (Erenstein et al. 2010;Olivia et al. 2011;Xu et al. 2021), and Latin American and Caribbean (Andreano et al. 2021). Focus on the spatial scale of this theme has gone from global (Elvidge et al. 2009;Zhou and Liu 2022) and national (Okwi et al. 2007; Wang and Alkire, 2009) to sub-national (Alejandro et al. 2015), county (Liu et al. 2017;Wang and Qi 2021), district (Minot and Baulch 2005;Erenstein et al. 2010), village (Wang et al., 2018), and even household level (Blumenstock et al. 2015). ...
Article
Full-text available
According to the stratified poverty theory, poverty includes individual (people) and regional (place) poverty. Understanding the interaction mechanism between individual poverty and regional poverty is crucial to achieving the UN goal of poverty eradication by 2030. However, at present, the relevant empirical research is still limited by the availability of data. To fill this important gap, based on the multi-source data of poverty census, geo-environmental and socio-economic data of China’s 1587 counties in 2013, we used exploratory spatial data analysis (ESDA) and spatial econometric models (spatial-lag and spatial-error model) to identify determinants of individual poverty and regional poverty in this county. Results show that the spatial distribution of the rural poor in China had strong spatial dependence (Global Moran’s I = 0.574). There was a high degree of spatial overlap between individual poverty and regional poverty. The poverty-causing factors were complex and varied across regions and individuals. Disease of family members was the leading factor driving rural areas in Northeast, Central, and Southwest China. Northeast China was mainly affected by the illness and lack of labor skills of family members. The complex terrain conditions were the determinants driving rural poverty in most areas of China. Improved transportation can greatly reduce rural poverty. Geographical isolation or lack of geographical capital caused by complex terrain conditions, backward transportation, and regional closure promoted regional poverty. In turn, regional poverty-causing factors further restricted the improvement of rural residents’ self-development ability and aggravated individual poverty. Our findings indicate that individual poverty and regional poverty have different poverty-causing mechanisms and poverty reduction priorities. Effective poverty reduction strategies require the coordinated promotion of individual and regional poverty reduction. The reduction of individual poverty should focus on enhancing the livelihood capital of the poor through differentiated policy intervention, while regional poverty alleviation should focus on creating a favorable development environment by increasing infrastructure investment and public service supply.
... At the same time, the rapid development of machine learning and data mining technology has greatly promoted the accuracy of the NTL inversion of other socio-economic factors. [29,31]. Inspired by these studies, we used machine learning methods to explore the inversion of NTL to the improved HDI. ...
Article
Full-text available
Uneven regional development has long been a focal issue for both academia and policymakers, with numerous studies over the past decades actively engaging in discussions on measuring regional development disparities. Generally, most existing studies measure the Human Development Index (HDI) using relatively simple indicators, with a focus on national and provincial scales. As a crucial component of regional development, counties can directly reflect the regional characteristics of socio-economic progress. This study employs a multi-dimensional approach to develop an improved Human Development Index (improved HDI) system, using machine learning techniques to establish the relationship between nighttime light (NTL) data and the improved HDI. Subsequently, NTL data are utilized to infer the spatial distribution characteristics of the improved HDI across China’s county-level regions. The improved HDI for county-level areas in the Ningxia Hui Autonomous Region was validated using a machine learning model, resulting in a Pearson correlation coefficient of 0.93. The adjusted R-squared value for the linear fit was 0.86, and the residuals were relatively balanced, ensuring the accuracy of the simulations. This study reveals that 1439 county-level units, representing 50% of all county-level units in China, have development levels at or above the medium level. At the provincial and national levels, the improved HDI shows significant clustering, characterized by a multi-center pattern with declining diffusion. The spatial distribution of the improved Human Development Index remains closely associated with the natural geographic background and socio-economic development levels of the county regions. Lower HDI values are predominantly found in the inland areas of central and western China, often in ecologically sensitive areas, inter-provincial border zones, and mountainous regions of mainland China, sometimes forming contiguous distribution patterns. This underscores the need for the government and society to focus more on these specific geographic development areas, promoting continuous improvements in health, education, and living standards to achieve coordinated regional development.
... In contrast, Chinese statistic yearbook is updated more frequently, encompassing multiple dimensions such as education, healthcare, and living resources. Nonetheless, it is worth mentioning that the Chinese statistics yearbook contains about 10% missing data, with even more gaps in older years (Xu et al. 2021). Additionally, inconsistencies in statistical caliber hinder the continuous dynamic analysis in a large-scale area. ...
Article
Full-text available
Assessing the socioeconomic development of rural areas is important for the targeted implementation of rural revitalization in China, especially after three years of COVID-19 pandemic restrictions. However, the influence of COVID-19 on socioeconomic development in rural areas remains unclear. Therefore, this paper constructed a comprehensive socioeconomic development index (SEDI) by considering county-level statistics on natural environment, social resources, and economy as proxies for assessing local socioeconomic development, and analyzed the influence of COVID-19 from the changing pattern of SEDI before and after COVID-19, with Wumeng Mountain (WM) area as the study case. In response to the absence and untimeliness of statistics, we employed both nighttime light (NTL) and land use/land cover (LULC) features to fill in these missing SEDIs from 2013 to 2022, using random forest regression. With the assistance of LULC, the overall R² increased from 0.7763 to 0.9056, and the estimation accuracy improved in 36 out of 38 counties. All counties in WM experienced an increase in SEDI, and the growth rate did not slow down, proving the effective implementation of rural revitalization strategy. Also, the spatial clustering pattern remained relatively stable. These findings provide scientific foundations for the local government to assess comprehensive development and formulate policies.
... Subsequently, NTL data were used as proxies for income and wealth. The related studies can be divided into the following categories: First, NTL and survey data were used to estimate poverty on a small scale, mainly in settlements, counties, and cities (Ni et al. 2020;Noor et al. 2008;Xu et al. 2021;Yu et al. 2015). Second, NTL and high-resolution image data, such as Google images and land-use data, were used to obtain nationaland continental-scale poverty projections for a short period or a single year using an estimation model (e.g. ...
Article
Full-text available
Poverty continues to pose significant global challenges. Analyzing poverty distribution is pivotal for identifying spatial and demographic disparities, informing targeted policy interventions, and fostering inclusive and equitable development. The absence of a worldwide pixel-scale time-series poverty dataset has hampered effective policy formulation. To address this gap, we employ the international wealth index (IWI) derived from household survey data to represent poverty levels. Subsequently, a random forest regression model was constructed, with IWI serving as the dependent variable and representative features extracted from nighttime lights, land cover, digital elevation model, and World Bank statistical data serving as independent variables. This yielded a global map of the IWI for low- and middle-income nations at a 10-km resolution spanning 2005 to 2020. The model demonstrated robust performance with an R² value of 0.74. Over the studied period, areas and populations with IWI ≤ 50 decreased by 8.85% and 16.17%, indicating a steady decrease in global poverty regions. Changes in the IWI at the pixel scale indicate that areas closer to cities have faster growth rates. Furthermore, our poverty estimation models present a novel method for real-time pixel-scale poverty assessments. This study provides valuable insights into the dynamics of poverty, both globally and nationally.
... Consequently, NTL data has been extensively employed in studies on measuring regional asset wealth and poverty identification. Some studies have explored the relationship between NTL and regional wealth levels, using machine learning models to estimate economic well-being and poverty at the grid level (Lin et al. 2022;McCallum et al. 2022) or different administrative levels (Jean et al. 2016;Xu et al. 2021). Furthermore, some studies have integrated multi-source data to compensate for the lack of luminous information in unlit areas (Lee and Braithwaite 2022;Niu, Chen, and Yuan 2020;Shao and Li 2023;Yeh et al. 2020). ...
Article
Full-text available
Due to the difficulty of obtaining survey data, nighttime light (NTL) imagery has emerged as valuable alternative data for asset wealth estimation. However, the nighttime light values do not differentiate between levels of asset wealth in various unlit areas, as the nighttime light values in unlit areas are all 0. Here, NTL data and World Settlement Footprint (WSF) data were combined to extract multidimensional luminous features that are also differential in unlit areas to estimate asset wealth in nighttime light-poor areas at 500 m × 500 m spatial units. A random forest model was used to estimate asset wealth, based on the shortest distance of settlements to three categories of lighted areas, along with the brightness values derived from the nearest lighted area and the settlements themselves. This model achieved an explanation of 71% for the variation in settlement asset wealth and demonstrated effectiveness in estimating the asset wealth of unlit areas. The MAE and RMSE of asset wealth estimation in the unlit clusters were 4.03 and 5.28, respectively. Asset wealth is generally low across most African settlements, with clear two-tier differentiation in Africa. In summary, the proposed method can extensively explore the luminous information in unlit areas.
... These models can handle non-linear relationships and capture interactions among multiple predictors, resulting in more accurate predictions. A study by (Xu et al., 2021) combined different machine learning methods with nighttime light RS data to identify poverty areas and predict poverty incidence. Machine learning approaches can also incorporate diverse data sources, including satellite imagery (Puttanapong et al., 2022), household surveys, and socioeconomic indicators, to enhance the predictive power. ...
Article
Full-text available
Energy poverty affects billions worldwide, including people in developed and developing countries. Identifying those living in energy poverty and implementing successful solutions require timely and detailed survey data, which can be costly, time-consuming, and difficult to obtain, particularly in rural areas. Through machine learning, this study investigates the possibility of identifying vulnerable households by combining satellite remote sensing with socioeconomic survey data in the UK. In doing so, this research develops a machine learning-based approach to predicting energy poverty in the UK using the low income low energy efficiency (LILEE) indicator derived from a combination of remote sensing and socioeconomic data. Data on energy consumption, building characteristics, household income, and other relevant variables at the local authority level are fused with geospatial satellite imagery. The findings indicate that a machine learning algorithm incorporating geographical and environmental information can predict approximately 83% of districts with significant energy poverty. This study contributes to the expanding body of research on energy poverty prediction and can help shape policy and decision-making for energy efficiency and social fairness in the UK and worldwide.
... Could nightlights serve as a proxy for living standards as well as economic activity in cities in LMICs? Previous research has confirmed a strong correlation between NTL emissions and GDP at various spatial scales [27][28][29][30] and has used NTL emissions to produce subnational estimates of the incidence of poverty [31][32][33]. However, the accuracy of NTL predictions is highly dependent on both the context and scale of application [28,34]. ...
Article
Full-text available
Urban data deficits in developing countries impede evidence-based planning and policy. Could energy data be used to overcome this challenge by serving as a local proxy for living standards or economic activity in large urban areas? To answer this question, we examine the potential of georeferenced residential electricity meter data and night-time lights (NTL) data in the megacity of Karachi, Pakistan. First, we use nationally representative survey data to establish a strong association between electricity consumption and household living standards. Second, we compare gridded radiance values from NTL data with a unique dataset containing georeferenced median monthly electricity consumption values for over 2 million individual households in the city. Finally, we develop a model to explain intra-urban variation in radiance values using proxy measures of economic activity from Open Street Map. Overall, we find that NTL data are a poor proxy for living standards but do capture spatial variation in population density and economic activity. By contrast, electricity data are an excellent proxy for living standards and could be used more widely to inform policy and support poverty research in cities in low- and middle-income countries.
... Lin et al. [60] found that POI data can reflect urban poverty to a certain extent, and thus, a combined use of POI and nighttime light data can improve the accuracy of poverty assessment. Although spatial big data have been increasingly used in poverty assessments, previous studies have relied greatly on the coarse-resolution DMSP-OLS and NPP-VIIRS data, and most of them have focused on regions with absolute poverty [61][62][63][64][65][66]. More importantly, few studies have provided poverty assessment results at a grid scale. ...
Article
Full-text available
Poverty is a social issue of global concern. Although socioeconomic indicators can easily reflect poverty status, the coarse statistical scales and poor timeliness have limited their applications. While spatial big data with reasonable timeliness, easy access, and wide coverage can overcome such limitations, the integration of high-resolution nighttime light and spatial big data for assessing relative poverty is still limited. More importantly, few studies have provided poverty assessment results at a grid scale. Therefore, this study takes the Pearl River Delta, where there is a large disparity between the rich and the poor, as an example. We integrated Luojia 1-01, points of interest, and housing prices to construct a big data poverty index (BDPI). To evaluate the performance of the BDPI, we compared this new index with the traditional multidimensional poverty index (MPI), which builds upon socioeconomic indicators. The results show that the impoverished counties identified by the BDPI are highly similar to those identified by the MPI. In addition, both the BDPI and MPI gradually decrease from the center to the fringe of the study area. These two methods indicate that impoverished counties were mainly distributed in ZhaoQing, JiangMen and HuiZhou Cities, while there were also several impoverished parts in rapidly developing cities, such as CongHua and HuaDu Counties in GuangZhou City. The difference between the two poverty assessment results suggests that the MPI can effectively reveal the poverty status in old urban areas with convenient but obsolete infrastructures, whereas the BDPI is suitable for emerging-development areas that are rapidly developing but still lagging behind. Although BDPI and MPI share similar calculation procedures, there are substantial differences in the meaning and suitability of the methodology. Therefore, in areas lacking accurate socioeconomic statistics, the BDPI can effectively replace the MPI to achieve timely and fine-scale poverty assessment. Our proposed method could provide a reliable reference for formulating targeted poverty-alleviation policies.
... Poverty has many significant impacts on the lives of the world's communities, including hunger (Sharma 2019), health problems (Billings et al. 2021), an increase in crime cases (Imran et al. 2018), and the worst part will have an impact on the death of the population. This makes the poverty problem widely discussed by researchers around the world, both broadly and specifically , Xu et al. 2021Nanhthavong et al. 2020;Eva et al. 2022). Poverty is a state of inability to meet basic needs such as food, clothing, shelter, education, and health (Statistics Indonesia, 2017). ...
Article
Full-text available
Accurate and comprehensive urban poverty monitoring is undoubtedly essential to support the urban poverty alleviation targets in many developing countries. The currently available urban poverty monitoring in Indonesia is, however, primarily depends on the expensive and resource-demanding Indonesia National Socio-Economic Survey (SUSENAS). Despite its high-quality poverty statistics, such national-scale survey collection methods are indispensably labor and cost expensive to scale. Alternative data is essentially required to be explored for supporting government poverty data in order to increase the data granularity. In this study, we aim to develop the spatially granular poverty index (SGPI) consisting of multisource remote sensing satellite imageries and big data sources. With 1 km resolution, the SGPI is composed of nighttime light (NTL), normalized difference built-up index (NDBI), carbon monoxide (CO) and nitrogen dioxide (NO2) pollution levels, education and healthcare Point of Interest (POI) data, as alternative economic activity and poverty proxy indicators. Three different approaches of the equal-weighted sum method, the Pearson correlation coefficient method weighted method, and PCA weighted method are compared and evaluated to combine different indicators. Our result shows that the SGPI built in the scope of Jakarta Metropolitan Area (JMA) by using the equal weighted sum with Yeo-Johnson transformation (EWS-YJ) has the highest correlation with official poverty data which is 0.954. Based on visual identifications through high-resolution satellite imagery, the areas with a relatively high SGPI value are densely populated, and vice versa. Our findings suggest that multi-source remote sensing and geospatial big data integration are promising alternative approaches for granular urban poverty mapping based on spatial characteristics.
... mosquito vectors [9]. However, other factors that are proxies for poverty such as a lack of electricity (light in the night) [10], and nutritional status (e.g., malnutrition may affect ability of immunity to fight diseases) may also play a role [11][12][13]. ...
Article
Full-text available
Background Lymphatic filariasis (LF) is a vector-borne parasitic disease which affects 70 million people worldwide and causes life-long disabilities. In Bangladesh, there are an estimated 44,000 people suffering from clinical conditions such as lymphoedema and hydrocoele, with the greatest burden in the northern Rangpur division. To better understand the factors associated with this distribution, this study examined socio-economic and environmental factors at division, district, and sub-district levels. Methodology A retrospective ecological study was conducted using key socio-economic (nutrition, poverty, employment, education, house infrastructure) and environmental (temperature, precipitation, elevation, waterway) factors. Characteristics at division level were summarised. Bivariate analysis using Spearman’s rank correlation coefficient was conducted at district and sub-district levels, and negative binomial regression analyses were conducted across high endemic sub-districts (n = 132). Maps were produced of high endemic sub-districts to visually illustrate the socio-economic and environmental factors found to be significant. Results The highest proportion of rural population (86.8%), poverty (42.0%), tube well water (85.4%), and primary employment in agriculture (67.7%) was found in Rangpur division. Spearman’s rank correlation coefficient at district and sub-district level show that LF morbidity prevalence was significantly (p<0.05) positively correlated with households without electricity (district rs = 0.818; sub-district rs = 0.559), households with tube well water (sub-district rs = 0.291), households without toilet (district rs = 0.504; sub-district rs = 0.40), mean annual precipitation (district rs = 0.695; sub-district rs = 0.503), mean precipitation of wettest quarter (district rs = 0.707; sub-district rs = 0.528), and significantly negatively correlated with severely stunted children (district rs = -0.723; sub-district rs = -0.370), mean annual temperature (district rs = -0.633.; sub-district rs = 0.353) and mean temperature (wettest quarter) ((district rs = -0.598; sub-district rs = 0.316) Negative binomial regression analyses at sub-district level found severely stunted children (p = <0.001), rural population (p = 0.002), poverty headcount (p = 0.001), primary employment in agriculture (p = 0.018), households without toilet (p = <0.001), households without electricity (p = 0.002) and mean temperature (wettest quarter) (p = 0.045) to be significant. Conclusions This study highlights the value of using available data to identify key drivers associated with high LF morbidity prevalence, which may help national LF programmes better identify populations at risk and implement timely and targeted public health messages and intervention strategies.
... To eliminate the gap between the actual carbon emission data and the simulated carbon emission data, we used the carbon emission zero error method (Gu et al., 2017b) to correct the simulated carbon emission values on the unit image element, which reduced the error between the simulated and statistical values. Some scholars have also corrected nighttime light images based on machine learning and achieved good fitting results (Xu et al., 2021). In the next step, the integration of nighttime light data with other correction methods should be enhanced to obtain more accurate regional land use carbon emission simulation values. ...
Article
Carbon emissions from land-use and land-cover change (together referred to as ‘land-use emissions’) are an important way to influence the regional carbon balance. However, due to the limitations and complexity of obtaining carbon emissions data at spatial scales, previous studies rarely reveal the long-term evolution characteristics of regional land-use emissions. Therefore, we propose a method to integrate DMSP/OLS and NPP/VIIRS nighttime light images to calculate land-use emissions over a long time series. The accuracy validation results show that the integrated nighttime light images and land-use emissions have a good fit and can accurately assess the long-term evolution of regional carbon emissions. In addition, by combining the Exploratory Spatial Analysis (ESTDA) model and the Vector Autoregressive Regression (VAR) model, we found significant spatial variation in carbon emissions in the Guangdong-Hong Kong-Macao Greater Bay Area (GBA), with the two regional emission centres spreading outwards between 1995 and 2020, with an increase in construction land area of 3445 km2, resulting in 257 million tons (Mt) of carbon emissions over the same period. The rapid increase in emissions from carbon sources is not offset by a correspondingly large amount of carbon sinks, resulting in a serious imbalance. Controlling the intensity of land use, optimizing the structure of land use and promoting the transformation of the industrial structure are now the keys to achieving carbon reduction in the GBA. Our study demonstrates the enormous potential of long-time-series nighttime light data in regional carbon emission research.
... For example, researchers have used satellite imagery to examine the relationship between nighttime lights and economic growth, finding that the percentage of nighttime light-covered areas strongly correlates with economic growth. Bickenbach et al., 2016;Bluhm & Krause, 2022;Cauwels et al., 2014;Chanda & Cook, 2022;Chen et al., 2022;Elvidge et al., 2012;Henderson et al., 2012;Hu & Yao, 2022;Liu et al., 2021;McCallum et al., 2022;McCord & Rodriguez-Heredia, 2022;Pérez-Sindín et al., 2021;Weidmann & Schutte, 2017;Xu et al., 2021;Yeh et al., 2020 used Overall, nighttime lights and satellite imagery provide valuable data for studying economic growth and development, as well as their impacts on the environment and society (Deng et al., 2008). By analysing patterns and trends in satellite imagery, researchers can gain insights into the complex relationships among economic activity, urbanisation and environmental change (Sutton & Costanza, 2002). ...
Article
Full-text available
Street views, satellite imageries and remote sensing data have been integrated into a wide spectrum of topics in the social sciences. Computer vision methods not only help analysts and policymakers make better decisions and produce more effective solutions but they also enable models to achieve more precise predictions and greater interpretability. In this paper, we review the growing literature applying such methods to economic issues and the social sciences, in which social scientists employ deep learning approaches to utilise image data to retrieve additional information. Typically, image data produce better results than traditional approaches and can provide detailed results and helpful insights to improve society and people’s well-being.
... For example, socio-economic disadvantaged neighborhoods in developing countries are usually more crowded, inaccessible and badly-maintained, which means traditional data (e.g., remote sensing) may not be able to reflect built environment characteristics there and more micro-level data are needed (Zhanjun et al., 2022). Although recent studies have tried to use multi-source data and include the built environment characteristics to assess urban poverty in developing countries Xu et al., 2021;Zhao et al., 2019), scant attention has been paid to the characteristics of micro built environments at the street level, which prevents researchers from further understanding urban poverty at a finer scale. ...
Article
Understanding and ending poverty has become one of the most important SDG (Sustainable Development Goals) all over the world. The street-level built environment is an important indicator to reflect urban poverty. However , traditional data such as satellite imagery may not provide fine-grained information of built environment at the street level. In recent years, street view image has become promising data for assessing an urban micro environment. This study aimed to use street view data and deep learning technique to examine the association between street-level built environment and urban poverty in Guangzhou, China, from a geographical hetero-geneity perspective. First, we measured urban poverty in Guangzhou based on the Index of Multiple Deprivation. Second, we used the Pyramid Scene Parsing Network model for image segmentation and then performed principal component analysis to extract five major street view factors (i.e., vegetation enclosure sense, color complexity sense, road openness sense, sky openness sense, and building enclosure sense) from the street view data. Third, we conducted the geographical detector analysis to examine how street view factors is associated with urban poverty. Results suggested that vegetation enclosure sense, color complexity sense, and road openness sense are significantly related to the spatial heterogeneity of urban poverty. Among all factors, vegetation enclosure sense played a leading role. The results also confirmed the coexistence of different street view factors have association with the spatial heterogeneity of urban poverty. In conclusion, street-level built environment is generally associated with urban poverty, and therefore our proposed method can be considered as an efficiently method for identifying urban poor communities.
... Next, a linear regression analysis is conducted according to Eq. xi is the average housing price in cell i, zi is the proportion of low-and high-412 income groups in cell i, α0 and α1 are the coefficients, and εi is the regression error of 413 the proportion of low-and high-income groups in cell i. If the regression error is below 414 5% for 65% of the cells, the linear validation is considered credible(Xu et al., 2021).415 The regression errors for the proportion of low-and high-income individuals in 416 different cells appear in Fig. 5 (a) and (b). ...
Article
Full-text available
The travel mobility gap is among the indicators that can be used to evaluate the level of social and transport inequity. To achieve a large and representative sample for this investigation of the different impacts of the built environment on travel mobility of various income and migrant groups, we have utilized big data from mobile phones for over 10 million users in Shenzhen, China. Travel mobility was measured by non-commute travel frequency and activity space. Our descriptive analysis demonstrates lower-income groups and migrant workers have lower levels of travel mobility than higher-income groups and non-migrant workers. The results produced by our linear regression models also reveal a significant travel mobility gap between different income and migration groups. That gap appears to be positively impacted by job density and bus stop distance and negatively impacted by residential density and metro station distance. Our modeling results also demonstrate that the travel mobility gap is larger in the outer suburbs than in the city center and inner suburbs. Our research findings reveal that the built environment influences the travel mobility gap, which implies that marginalized groups experience some degree of social inequality and exclusion. Based on these findings, we provide policy recommendations that aim to reduce the travel mobility gap between the marginalized and reference groups.
... Poverty level (y) is the explanatory variable of this paper. Scholars usually use poverty incidence [50], poverty income level [4,38], the Engel coefficient [51,52], the poverty FGT index [53], and other indicators to measure poverty level. Since the research area of this paper is 15 underdeveloped counties in Anhui Province, and the poverty population has been accounted for according to the unified national filing and card establishment. ...
Article
Full-text available
Based on the characteristics of underdeveloped areas, this paper selects the panel data of 15 underdeveloped counties in Anhui Province from 2013 to 2019 and uses the panel threshold model to empirically analyze the sustainability of rural tourism development. The results show that: (1) Rural tourism development has a non-linear positive impact on poverty alleviation in underdeveloped areas and has a double threshold effect. (2) When the poverty rate is used to express the poverty level, it can be found that the development of rural tourism at a high level can significantly promote poverty alleviation. (3) When the number of poor people is used to express the poverty level, it can be found that the poverty reduction effect shows a marginal decreasing trend with the phased improvement of the development level of rural tourism. (4) The degree of government intervention, industrial structure, economic development, and fixed asset investment play a more significant role in poverty alleviation. Therefore, we believe that we need to actively promote rural tourism in underdeveloped areas, establish a mechanism for the distribution and sharing of rural tourism benefits, and form a long-term mechanism for rural tourism poverty reduction.
... In recent years, combining geospatial information and machine learning technology has become ever increasing interest for research on poverty area identification [6,8,13]. Geospatial information, such as nighttime lights, day-time satellite imagery, and crowd-sourced map data, can assist in capturing poverty and socioeconomic conditions on a coarse scale [1,3,30]. Machine learning technology allows researchers to effectively and efficiently utilize geospatial information [9,10,14]. ...
Preprint
Poverty status identification is the first obstacle to eradicating poverty. Village-level poverty identification is very challenging due to the arduous field investigation and insufficient information. The development of the Web infrastructure and its modeling tools provides fresh approaches to identifying poor villages. Upon those techniques, we build a village graph for village poverty status identification. By modeling the village connections as a graph through the geographic distance, we show the correlation between village poverty status and its graph topological position and identify two key factors (Centrality, Homophily Decaying effect) for identifying villages. We further propose the first graph-based method to identify poor villages. It includes a global Centrality2Vec module to embed village centrality into the dense vector and a local graph distance convolution module that captures the decaying effect. In this paper, we make the first attempt to interpret and identify village-level poverty from a graph perspective.
... The application of remote sensing technology to do urbanization research has greater advantages and convenience, making up for the disadvantage that statistical data are not conducive to dynamic monitoring. Nighttime light remote sensing can create a unique view centered on human activities and find potential patterns of human activities from it and has a wide range of applications in monitoring urbanization, mapping poverty, assessing light pollution, etc. [3][4][5]. In 1978, Croft [6] first used DMSP/OLS data to extract urban built-up areas and conducted a series of related studies, in which the NTL data needed to be corrected for processing. ...
Article
Full-text available
It is of great significance to grasp the spatio-temporal characteristics and expansion mechanism of urban built-up areas for formulating urban development strategy. This paper takes the built-up area of Fuzhou as the study area, uses multi-temporal Landsat images and remote sensing data of nighttime light (NTL) as the main data sources, and extracts the built-up area of NTL images with a higher spatial resolution comparison method. It discusses the development trends of the Fuzhou built-up area from 2000 to 2021 from the perspectives of temporal and spatial evolution characteristics and spatial morphology evolution and analyzes the relationship between population factors, economic factors, natural conditions, policy factors, and urban expansion. The results show that the urbanization level of Fuzhou is gradually improving, and the compounded nighttime light index (CNLI) increases from 0.0105 in 2000 to 0.0635 in 2021. The trend of expansion speed and expansion intensity is consistent, showing the changing trend of first fast and then slow, then accelerating and then slowing down. The expansion direction presents the trend of “expanding eastward, advancing southward and expanding westward”, the spatial form tends to be irregular, and the migration range of the center of gravity is not significant. Population factors, economic factors, and expansion are positively correlated and closely related, and natural conditions and policy guidance affect the direction and mode of the expansion of the built-up area. The above results indicate that the overall urban development of Fuzhou shows an upward trend, which is consistent with the planned urbanization development trend of Fuzhou.
... Based on field research data, scholars used the Alkire-Foster method [22], multi-dimensional poverty index [23], sustainable livelihood model [24], and other methods to investigate multi-dimensional relative poverty and accurately identify the poor. Scholars used GIS technology to identify relatively poor areas based on nighttime lighting data, population income data, and empirical research on the spatial and temporal distribution, evolution law, and driving mechanism of relative poverty to support national and regional poverty reduction decision-making [25,26]. Most current regional studies on relative poverty identification, however, are based on income; scholars defined the relative poverty line by the median proportion of population income, which focused on the economic dimensions and could not reflect the multi-dimensional characteristics of relative poverty [7,27]. ...
Article
Full-text available
Absolute poverty has historically been solved in China, and the focus on poor areas has shifted to addressing relative poverty. To realize the organic combination of the rural revitalization strategy and relative poverty governance, multi-dimensional relative poverty identification and governance path research at the village scale in an alpine-gorge region is required. For this study, the Nujiang Lisu Autonomous Prefecture’s research area in a typical alpine-gorge was chosen. This paper constructed an evaluation index system for the rural regional system based on location conditions, ecological environment, productive resources, economic base, and public service, based on the theory of multi-dimensional regional poverty and the human–land relationship. The level of poverty, types of poverty, and spatial distribution characteristics of 255 administrative villages were systematically analyzed, and poverty governance paths were proposed. The results show that: (1) There were 215 multi-dimensional relative poverty villages in Nujiang Prefecture, accounting for 84.31% of the total. The relatively poor villages with poverty grades I and II, which are classified as mild poverty, account for 77.21% of all poor villages; this demonstrated that the relatively poor villages in Nujiang Prefecture had a high potential for poverty alleviation. (2) There are 19 different types of constraints in poor villages. Grades III and IV poor villages were mostly found in high-altitude areas. The economic foundation was very weak, the infrastructure was imperfect, the land use type was relatively single, and traffic conditions were relatively backward. (3) The priority model accounted for 16.67% of relative poverty governance, the steady improvement accounted for 28.79%, and key support accounted for 54.54%. Relative poverty governance paths for various counties have been proposed, including rural revitalization priority demonstration, ecological environment governance, eco-tourism, modern agriculture + mountain agroforestry, and improved people’s livelihood and well-being. The findings provided scientific support and direction for future research on the mode and course of relative poverty governance in poor villages in the alpine-gorge area, as well as the rural revitalization strategy’s implementation.
... Chen et al. (2021) proposed the use of remote sensing data, meteorological data, geological lithology maps, and other data to construct a multidimensional poverty and ecological vulnerability coupled indicator system. Xu et al. (2021b) used DMSP/OLS and NPP/VIIRS night-time light images and combined them with machine learning and statistical data to identify and predict the long time series of poverty characteristics in mountainous areas. Thus, effectively coupling these multisource spatial data into a multidimensional system of poverty has become an important issue in the construction of multidimensional poverty indices. ...
Article
Poverty is a severe barrier to sustainable human development and a pressing worldwide issue. Understanding how to accurately assess the spatial distribution of poverty in mountain areas has become crucial for ensuring that governments at all levels take suitable poverty reduction strategies. In this study, the mountain poverty spatial index (MPSI) was created by combining the digital elevation model (DEM), Luojia-1 night-time light imagery, point of interest (POI) data, and vegetation index products. The MPSI was then used to identify the spatial characteristics of poverty at different scales in the hilly area of Ganzhou city, Jiangxi Province, China. Socioeconomic statistics and Google satellite images were used to verify the reliability of MPSI by constructing a multidimensional poverty index (MPI) at the county scale. The results showed that MPSI and MPI have a positive correlation with a correlation coefficient of 0.8934 (P<0.001), which indicates that MPSI could be used to identify the spatial distribution of poverty well. Specifically, the smallest distribution of both MPSI and MPI was in Zhanggong District (1.4555 and 0.1894), which indicates that most of the affluent counties were concentrated in the central region of Ganzhou, and the poor areas were scattered in the surrounding areas of Ganzhou. In addition, MPSI accurately identified poverty in mountainous areas with complex terrain in small administrative units, which can provide a more accurate way to monitor the poverty situation in the mountainous areas of China. This study will be useful for providing scientific references for the Chinese government to implement targeted strategies for eradicating poverty with differentiated policies.
... The aim of the paper is to show that machine learning can be applied in identifying and predicting poverty at the county level [103]. In measuring poverty levels, a poverty incidence indicator was applied [104]. ...
Article
Full-text available
Artificial Intelligence (AI) is generating new horizons in one of the biggest challenges in the world’s society—poverty. Our goal is to investigate utilities of AI in poverty prediction via finding answers to the following research questions: (1) How many papers on utilities of AI in poverty prediction were published up until March, 2022? (2) Which approach to poverty was applied when AI was used for poverty prediction? (3) Which AI methods were applied for predicting poverty? (4) What data were used for poverty prediction via AI? (5) What are the advantages and disadvantages of the created AI models for poverty prediction? In order to answer these questions, we selected twenty-two papers using appropriate keywords and the exclusion criteria and analyzed their content. The selection process identified that, since 2016, publications on AI applications in poverty prediction began. Results of our research illustrate that, during this relatively short period, the application of AI in predicting poverty experienced a significant progress. Overall, fifty-seven AI methods were applied during the analyzed span, among which the most popular one was random forest. It was revealed that with the adoption of AI tools, the process of poverty prediction has become, from one side, quicker and more accurate and, from another side, more advanced due to the creation and possibility of using different datasets. The originality of this work is that this is the first sophisticated survey of AI applications in poverty prediction.
... Existing prediction work about poverty in rural China is limited to how nighttime lights from a surveyed area can predict county-level poverty in a non-surveyed area (Xu et al., 2021), how geo-spatial information can make poverty predictions for Guizhou Province (Yin et al., 2021), urban poverty or county-level poverty (Li et al., 2019). Importantly, human well-being is not limited to income poverty, but is rather related to a sense of deprivation that can be better captured by measures of subjective poverty, multidimensional poverty or inequalities. ...
Article
Purpose Despite rising incomes and reduction of extreme poverty, the feeling of being poor remains widespread. Support programs can improve well-being, but they first require identifying who are the households that judge their income is insufficient to meet their basic needs, and what factors are associated with subjective poverty. Design/methodology/approach Households report the income level they judge is sufficient to make ends meet. Then, they are classified as being subjectively poor if their own monetary income is inferior to the level they indicated. Second, the study compares the performance of three machine learning algorithms, the random forest, support vector machines and least absolute shrinkage and selection operator (LASSO) regression, applied to a set of socioeconomic variables to predict subjective poverty status. Findings The random forest generates 85.29% of correct predictions using a range of income and non-income predictors, closely followed by the other two techniques. For the middle-income group, the LASSO regression outperforms random forest. Subjective poverty is mostly associated with monetary income for low-income households. However, a combination of low income, low endowment (land, consumption assets) and unusual large expenditure (medical, gifts) constitutes the key predictors of feeling poor for the middle-income households. Practical implications To reduce the feeling of poverty, policy intervention should continue to focus on increasing incomes. However, improvements in nonincome domains such as health expenditure, education and family demographics can also relieve the feeling of income inadequacy. Methodologically, better performance of either algorithm depends on the data at hand. Originality/value For the first time, the authors show that prediction techniques are reliable to identify subjective poverty prevalence, with example from rural China. The analysis offers specific attention to the modest-income households, who may feel poor but not be identified as such by objective poverty lines, and is relevant when policy-makers seek to address the “next step” after ending extreme poverty. Prediction performance and mechanisms for three machine learning algorithms are compared.
... Selecting important variables to obtain good prediction results is an integral part of the study. Based on night-time light remotesensing data and machine learning methods, the study in [13] demonstrates an accurate and reliable approach to determine poverty areas and predicting poverty incidence. The study outlines how to utilize machine learning to identify poverty counties and predict poverty incidence in the Yunnan-Guangxi-Guizhou Rocky desertification area using data from poverty counties and poverty incidence in Guizhou Province, China as the training dataset. ...
Article
Full-text available
This paper improves on a recently proposed machine learning approach to assess and monitor the poverty status of Jordanian households. Without a doubt, accurate identification, tracking, and targeting households in poverty is a key to poverty alleviation. This work presents a nontraditional approach to the accurate prediction of poverty for Jordanian households using feature selection and machine learning. This approach can be seen as a support in the decision making process in the government and non-governmental organizations in an ever-shifting socio-economic environment. Using the Jordanian household expenditure and income surveys collected by the Department of Statistics (DoS), LightGBM predictive performance is improved to reach 83% F1-Score using only 41 features in contrast to 81% F1-score and 96 features in our previous work. At the heart of this work is determining which variables of household expenditure and income surveys are most predictive and how they can be most effectively combined. National surveys can now be run with fewer, more targeted questions that can greatly help in assessing the effectiveness of new policies and intervention programs rapidly and cheaply.
... Could nightlights serve as a proxy for living standards as well as economic activity in cities in LMICs? Previous research has confirmed a strong correlation between NTL emissions and GDP at various spatial scales [27][28][29][30] and has used NTL emissions to produce subnational estimates of the incidence of poverty [31][32][33]. However, the accuracy of NTL predictions is highly dependent on both the context and scale of application [28,34]. ...
Preprint
Data deficits in developing countries impede evidence-based urban planning and policy, as well as fundamental research. We show that residential electricity consumption data can be used to partially address this challenge by serving as a proxy for relative living standards at the block or neighbourhood scale. We illustrate this potential by combining infrastructure and land use data from Open Street Map with georeferenced data from ~2 million residential electricity meters in the megacity of Karachi, Pakistan to map median electricity consumption at block level. Equivalent areal estimates of economic activity derived from high-resolution night lights data (VIIRS) are shown to be a poor predictor of intraurban variation in living standards by comparison. We argue that electricity data are an underutilised source of information that could be used to address empirical questions related to urban poverty and development at relatively high spatial and temporal resolution. Given near universal access to electricity in urban areas globally, this potential is significant
Article
Full-text available
Accurate, inexpensive and granular human poverty assessments are critical for data-driven policy decision-making. This research proposes a novel approach to computing poverty scores utilizing multispectral satellite images and indices calculated from census reference values. We show how this approach can leverage standard and sparse survey-based multidimensional poverty assessments at the municipal level to develop a deep learning architecture to obtain poverty scores at the residential block level. This method has the distinctive feature that the obtained inference corresponds to Multidimensional Measurement of Poverty generated by CONEVAL, the Mexican agency responsible for measuring poverty. We provide a reliable alternative to survey-based approaches with an R2R^2 of 0.802±0.0220.802\pm 0.022 for the lack of housing quality and spaces dimension. A convolutional neural network trained on multispectral satellite images and the lack of housing quality and spaces dimension, which is regressed from census reference variables corresponding to lack of water, electricity, sewage, concrete floor, toilet and occupancy level obtains an R2R^2 of 0.753. These results represent a significant step forward in including machine learning techniques to provide reliable information at reduced costs and a higher spatiotemporal frequency than traditional person-to-person surveys.
Article
Despite the rapid development in very recent years of Artificial Intelligence models to predict poverty risk, this problem still remains an unsolved open challenge, especially from a multidimensional perspective. One of the main challenges is related to the scarcity of labelled and high-quality data for training models coupled with the lack of a general reference model to build good predictors. This results in the proposal of a variety of approaches tailored to specific contexts. This paper presents our proposal to address multidimensional poverty prediction, starting from an unlabelled dataset. We focus on the case of a fragile population, the older adults; our approach is highly flexible and can be easily adapted to various scenarios. Firstly, starting from expert knowledge, we apply a stochastic method for estimating the probability of an individual being poor, and we use this probability to identify three levels of risk. Then, we train an XGBoost classification model and exploit its tree structure to define a ranking of feature relevance. This information is used to create a new set of aggregated features representative of different poverty dimensions. An explainable novel Naive Bayes model is then trained for predicting individuals’ deprivation level in our particular domain. The capacity to identify which variables are predominantly associated with poverty among older adults offers valuable insights for policymakers and decision-makers to address poverty effectively.
Article
Investigating the spatial distribution and correlation characteristics of carbon emissions would be conducive to the policy formulation for precise carbon emission spatial reduction. Firstly, a new carbon emission spatial inversion model was developed, incorporating nighttime light data and land use data. After verifying the validity and accuracy of the inversion results, the continuous carbon emission spatial data in the Beijing-Tianjin-Hebei Urban Agglomeration (BTHUA) were acquired from 2000 to 2019. Then, the spatial distribution and correlation characteristics were further analyzed in the BTHUA. Finally, policy recommendations were proposed for carbon emission reduction and urban sustainable development. The results showed that the built model can improve the accuracy of the carbon emission spatial inversion data. The carbon emissions were low in the northwest and high in the southeast of the BTHUA, with a noticeable expansion of the high carbon emission contiguous areas around Beijing, Tianjin, Shijiazhuang, and other prefecture-level cities, which was consistent with the socioeconomic development pattern. The center of gravity of carbon emissions moved to the southeast, showing a relatively stable distribution. The spatial correlation degree of carbon emissions among cities gradually increased, with Beijing and Tianjin playing a prominent role. As a scientific tool, the spatial inversion model helps to produce more accurate spatial data. The results and conclusions can provide useful and scientific references for spatial analysis and regulation strategies of regional carbon emission reduction.
Article
The coronavirus disease 2019 (COVID-19) has caused significant changes in urban networks due to epidemic prevention policies (e.g., social distancing strategies) and personal concerns. Previous measurements of urban networks were mainly based on flow data or were simulated from statistical data using models (e.g., Gravity model). However, these measurements are not directly applicable to the mapping of directional urban networks during unexpected events, such as COVID-19. Since nighttime light (NTL) data offer a unique opportunity to track near real-time human activities, the radiation model, traditionally used for routine situations only, was modified to measure directional urban networks using NTL data under three scenarios: the routine scenario (before the Shanghai lockdown), the COVID-19 scenario (during the Shanghai lockdown), and the extreme scenario (without Shanghai's participation). When compared with the Baidu migration index, the modified radiation model achieved an acceptable accuracy of 0.74 under the routine scenario and 0.44 under the COVID-19 scenario. Our mapping of each scenario's urban networks in the Yangtze River Delta Region (YRDR) shows that the Shanghai lockdown reduced the urban interaction index between Shanghai and its surrounding cities. However, it led to an increase in the urban interaction index centered on the periphery cities of YRDR. Our findings suggest that urban interactions within YRDR are resilient, even under extreme scenarios. Considering the long time series and global coverage of NTL data, the proposed NTL-based urban network model can be readily updated and applied to other regions.
Article
The urban-rural difference in economy is a key indicator of urban sustainability and socio-economic development, especially when the rapid urbanization has taken place in China. Scientific understanding of the urban-rural economy difference will help the future urbanization process and policy decisions. Different from the traditional analysis based on statistical data, we have conceptualized the novel nighttime light landscape metrics, by analogy to traditional landscape metrics, to reveal the rural and urban economic development, as well as their differences from multi-perspectives (e.g., economic volume and economic expansion). Taking all towns in Fujian province as examples, we found from 2000 to 2020 the urban economic development presents a decoupling between the economic volume and economic space, which satisfies the criteria of high-quality urbanization. The rural economy has a rapid development mainly via the rural construction and structural transformation, which furthermore caused the differences between the coastal and inland urban-rural economic differentiation. Our empirical results indicate the novel nighttime light landscape metrics are valuable indicators to facilitate the analysis of economy distribution and evolution. Also, owing to the conceptualization of traditional landscape metrics, the nighttime light landscape metrics can be further enriched to reveal more information of economic development, even of other fields.
Article
Poverty is a severe barrier to sustainable human development and a pressing worldwide issue. Understanding how to accurately assess the spatial distribution of poverty in mountain areas has become crucial for ensuring that governments at all levels take suitable poverty reduction strategies. In this study, the mountain poverty spatial index (MPSI) was created by combining the digital elevation model (DEM), Luojia-1 night-time light imagery, point of interest (POI) data, and vegetation index products. The MPSI was then used to identify the spatial characteristics of poverty at different scales in the hilly area of Ganzhou city, Jiangxi Province, China. Socioeconomic statistics and Google satellite images were used to verify the reliability of MPSI by constructing a multidimensional poverty index (MPI) at the county scale. The results showed that MPSI and MPI have a positive correlation with a correlation coefficient of 0.8934 (P<0.001), which indicates that MPSI could be used to identify the spatial distribution of poverty well. Specifically, the smallest distribution of both MPSI and MPI was in Zhanggong District (1.4555 and 0.1894), which indicates that most of the affluent counties were concentrated in the central region of Ganzhou, and the poor areas were scattered in the surrounding areas of Ganzhou. In addition, MPSI accurately identified poverty in mountainous areas with complex terrain in small administrative units, which can provide a more accurate way to monitor the poverty situation in the mountainous areas of China. This study will be useful for providing scientific references for the Chinese government to implement targeted strategies for eradicating poverty with differentiated policies.
Article
Under the double pressure of ecological vulnerability and economic development, natural resources and ecological environment have become the key constraints to the development of the Yellow River Basin (YRB). This paper proposed a theoretical framework for the relationship between water-energy-food (WEF) and poverty. An improved coupling coordination degree model and the geographical detector were used to evaluate the spatio-temporal coupling between WEF and poverty and its influencing factors in YRB. The results suggest that the levels of coupling coordination increase to different degrees in YRB and its provinces from 2000 to 2019, and the coupling types are characterized by pyramidal-shaped distribution. The regions of YRB are divided into four development types: water-driven type, energy-driven type, food-driven type, and economy-driven type. Spatially, a dominant factor zone is formed with a multi-polar core. Furthermore, some practical suggestions are put forward to promote the effective utilization of water resources and high-quality development according to specific regional situations in YRB. This study will promote coupling coordination and high-quality development in YRB, providing a reference for the coordination of the human-land relationship and regional sustainable development.
Article
Government consumption is an important factor affecting corporate performance. By exploiting a unique data set that reveals the Three Public Consumptions (TPCs) of China’s prefecture-level city governments, this paper investigates the impact of actual local government consumption on corporate performance and identifies the potential impact mechanism. We show that increases in local government consumption did lead to declines in firm productivity. TPC expenditures on official cars and official receptions had the most obvious impact on corporate performance. After considering endogenous measurement errors and substitution variables, the conclusion remained stable. Moreover, we show that the increase of local government TPC expenditures caused an increase in corporate tax burden, a decline in government efficiency, and excessive administrative intervention, which in turn caused a decline in firm performance. Our findings are particularly pronounced in non-state-owned enterprises, in firms with tight financing constraints, and in regions with weak marketization and low budget transparency. This study expands the theory that government behavior affects corporate performance, and also provides policy implications regarding restraints on government consumption.
Article
As one of the new and crucial fields of economic development, the digital economy refers to the economic activities associated with digital technologies and information. The traditional measurement mainly relies on the statistical data, which are regionally specific and labour cost. As an appropriate proxy for socio-economic activities, nighttime light (NTL) remote sensing data was used in this study to explore its potential in estimating the digital economy. Then, the Zipf's law was used to evaluate the growth of the digital economy at the city level. The results show that the total NTL intensity has a logarithmic relationship with the digital economy index and can be estimated for each cities' digital economy growth in China from 2017 to 2020 (R² ≈ 0.7). An unbalanced distribution and a decentralized polycentric structure of digital economy are found among all cities in China. But the top 100 cities have a relative harmonious development with a better goodness of Zipf's law. Finally, four main incentives behind the digital economy growth were concluded for three stages of the digital economy growth. This study could enrich the understanding of digital economy and have valuable implications for its future growth in China.
Article
Full-text available
Accurate and comprehensive measurements of economic well-being are fundamental inputs into both research and policy, but such measures are unavailable at a local level in many parts of the world. Here we train deep learning models to predict survey-based estimates of asset wealth across ~ 20,000 African villages from publicly-available multispectral satellite imagery. Models can explain 70% of the variation in ground-measured village wealth in countries where the model was not trained, outperforming previous benchmarks from high-resolution imagery, and comparison with independent wealth measurements from censuses suggests that errors in satellite estimates are comparable to errors in existing ground data. Satellite-based estimates can also explain up to 50% of the variation in district-aggregated changes in wealth over time, with daytime imagery particularly useful in this task. We demonstrate the utility of satellite-based estimates for research and policy, and demonstrate their scalability by creating a wealth map for Africa’s most populous country.
Article
Full-text available
The impact of settlements isolation and land-use changes on poverty is often overlooked. This study explored the spatial pattern and impact of settlements isolation and land use changes on poverty in Guizhou, a mountainous province of China, based on a Pearson correlation analysis and geographically weighted regression (GWR). The results showed that the incidence of high poverty levels in the counties of Guizhou tended to move from the southwest to the southeast over the period of 2005–2015. Both settlements isolation and land use changes had an impact on poverty, and this effect displayed spatial heterogeneity. With other factors unchanged, a 1 m increase in settlements isolation was associated with a statistically significant 0.58% increase in poverty incidence. Changes in the area of crop land, water, and forest land had a significant impact on poverty. The authors suggest that in the process of resettlement, the distance between settlements should be kept less than 5000 m if possible. The government needs to further improve and implement preferential land use policies, with appropriate increases in the area of built-up land.
Article
Full-text available
The goal of the present study is to demonstrate that high-poverty counties and robust classification features can be identified by machine learning approaches using only DMSP/OLS night-time light imagery. To accomplish this goal, a total of 96 high-poverty and 96 non-poverty counties were classified using 15 statistical and spatial features extracted from night-time light imagery in China in 2010 formed a training set for identifying high-poverty counties. Seven machine learning approaches were adopted to classify high-poverty counties, and five feature importance measures were used to select robust features. The resulting metrics, including the user’s (>63%), producer’s (>66%) and overall (>82%) accuracies of the poor county identification (probability of poverty greater than 0.6), show that the seven machine learning approaches used in this paper exhibit good performance, although some differences exist among the approaches. The order of feature importance reveals that the relative importance of each feature differs among the models; however, the important features remain consistent. The nine most important features ranked in each approach are relatively robust for poverty identification at the county level. Both spatial feature and statistical features calculated in part from the central tendency, degree of dispersion, and the distribution of the night-time light data were identified as indispensable robust features in all the approaches, indicating that the complex social phenomenon of poverty requires analysis from different aspects. Previous studies that utilized primarily night-time light imagery applied single features related to the central tendency or the distribution features of the imagery; this study provides a new method and can act as a reference for feature selection and identification of high-poverty counties using night-time light imagery and has potential applications across several scientific domains.
Article
Full-text available
Luojia1-01 satellite is the first scientific experimental satellite applied for night-time light remote sensing data acquisition, and the payload is an optical camera with high sensitivity, high radiation measurement accuracy and stable elements of interior orientation. At the same time, a special shaped hood is designed, which significantly improved the ability of the camera to suppress stray light. Camera electronics adopts the integrated design of focal plane and imaging processing, which greatly reduces the volume and weight of the system. In this paper, the design of the optical camera is summarized, and the results of in-orbit imaging performance tests are analyzed. The results show that the dynamic modulation transfer function (MTF) of the camera is better than 0.17, and the SNR is better than 35 dB under the condition of 10 lx illuminance and 0.3 reflectivity and all indicators meet the design requirements. The data obtained have been widely applied in many fields such as the process of urbanization, light pollution analysis, marine fisheries detection and military.
Article
Full-text available
Increased availability of satellite imageries and rapid development in algorithms to process imagery data has spurred interest amongst economist to use high-frequency imagery data for meaningful economic interpretations. One such application is to use satellite night light data as an indicator of poverty. As poverty statistics in India is released once in five years, high-frequency night lights data can be used to predict poverty in the years where official poverty statistics are not available. In this paper, we explored the use of satellite night light data and machine learning algorithms (Artificial Neural Network) to predict rural poverty at sub-national level, i.e. state. We compared night light data with per capita domestic product as a predictor for the model. We find night light data as a better predictor of poverty than per capita domestic product. Such predictions using satellite data can be used as a complement to the existing data-sets. This will facilitate economist for modeling the economic relationships in understanding poverty and provide more frequent and local estimates for policymakers.
Article
Full-text available
The LuoJia1-01 satellite can acquire high-resolution, high-sensitivity nighttime light data for night remote sensing applications. LuoJia1-01 is equipped with a 4-megapixel CMOS sensor composed of 2048 × 2048 unique detectors that record weak nighttime light on Earth. Owing to minute variations in manufacturing and temporal degradation, each detector’s behavior varies when exposed to uniform radiance, resulting in noticeable detector-level errors in the acquired imagery. Radiometric calibration helps to eliminate these detector-level errors. For the nighttime sensor of LuoJia1-01, it is difficult to directly use the nighttime light data to calibrate the detector-level errors, because at night there is no large-area uniform light source. This paper reports an on-orbit radiometric calibration method that uses daytime data to estimate the relative calibration coefficients for each detector in the LuoJia1-01 nighttime sensor, and uses the calibrated data to correct nighttime data. The image sensor has a high dynamic range (HDR) mode, which is optimized for day/night imaging applications. An HDR image can be constructed using low- and high-gain HDR images captured in HDR mode. Hence, a day-to-night radiometric reference transfer model, which uses daytime uniform calibration to calibrate the detector non-uniformity of the nighttime sensor, is herein built for LuoJia1-01. Owing to the lack of calibration equipment on-board LuoJia1-01, the dark current of the nighttime sensor is calibrated by collecting no-light desert images at new moon. The results show that in HDR mode (1) the root mean square of mean for each detector in low-gain (high-gain) images is better than 0.04 (0.07) in digital number (DN) after dark current correction; (2) the DN relationship between low- and high-gain images conforms to the quadratic polynomial mode; (3) streaking metrics are better than 0.2% after relative calibration; and (4) the nighttime sensor has the same relative correction parameters at different exposure times for the same gain parameters.
Article
Full-text available
Purpose Poverty alleviation is a global challenge. Human society has never ceased to fight against poverty. China was once the developing country with the largest rural poor population in the world. Remarkable achievements have been made in China’s anti-poverty program over the past decades, shaping a unique poverty reduction strategy with Chinese characteristics. This paper first reviewed the history of China’s rural reform and anti-poverty, and then analyzed the related policy systems, mechanism innovations and future challenges in poverty alleviation and development. At last, some specific policy implications were provided. Design/methodology/approach Literature on China’s antipoverty history was reviewed and mechanism innovations on targeted poverty alleviation strategy was investigated. Findings Along with the deepening of the rural reform, the poverty alleviation and development in new China has undergone six stages, and experienced a transformation from relief-oriented to development-oriented poverty alleviation. The object of poverty alleviation has gradually targeted with a transformation from poor counties/areas to villages/households, and the effectiveness of poverty alleviation is also gradually improved. However, the increasing in the difficulty of antipoverty, fragile ecological environment, rapid population aging and rural decline pose challenges to the construction of a well-off society in an all-round way in China. Specific antipoverty measures were put forward based on the investigation. Finally, we emphasize the importance of strengthening the study of poverty geography. Originality/value This study investigates the history of China’s antipoverty policy and analyzes the future challenges for implementing targeted poverty alleviation policy. These findings will lay a foundation for the formulation of China’s antipoverty policies after 2020, and provide experience for poverty alleviation in other developing countries around the world.
Article
Full-text available
The Visible Infrared Imaging Radiometer Suite (VIIRS) Day/Night Band (DNB) collects global low-light imaging data that have significant improvements over comparable data collected for 40 years by the DMSP Operational Linescan System. One of the prominent features of DNB data is the detection of electric lighting present on the Earth’s surface. Most of these lights are from human settlements. VIIRS collects source data that could be used to generate monthly and annual science grade global radiance maps of human settlements with electric lighting. There are a substantial number of steps involved in producing a product that has been cleaned to exclude background noise, solar and lunar contamination, data degraded by cloud cover, and features unrelated to electric lighting (e.g. fires, flares, volcanoes). This article describes the algorithms developed for the production of high-quality global VIIRS night-time lights. There is a broad base of science users for VIIRS night-time lights products, ranging from land-use scientists, urban geographers, ecologists, carbon modellers, astronomers, demographers, economists, and social scientists.
Article
Full-text available
In this paper, we have made a comprehensive assessment of the extent and various socio-economic implications of energy poverty in India. Amartya Sens's capability approach to development underpins the analysis of household-level data taken from the India Human Development Survey-II (IHDS-II), 2011-12 using the Multidimensional Energy Poverty Index (MEPI). The overall results show that energy poverty is widespread in India and the existence of energy poverty also coincides with the other forms of deprivations such as income poverty and social backwardness. For example, Dalits (Lower Caste) and Adivasis (Tribal) are found to be extremely energy poor compared to the other social groups in India. The results also reveal that it is the responsibility of women to manage the domestic chores such as collection of firewood and making of dung cake in traditional Indian households. Inefficient use of such biomass fuels is found to cause health hazards.
Article
Full-text available
Small area estimation techniques are now routinely used to generate local-level poverty estimates for aid allocation and poverty monitoring in developing countries. However, the widely implemented World Bank (WB) or Elbers, Lanjouw and Lanjouw [Econometrica 71 (2003) 355–364] (ELL) method can only be used when a survey and census are conducted at approximately the same time. The empirical best prediction (EBP) method of Molina and Rao [Canad. J. Statist. 38 (2010) 369–385] also requires a new census for updating. Hence, if small area estimation methods that use both survey and census unit record data are required, and the survey is rerun some years after the census, how to update small area estimates becomes an important issue. In this paper, we propose an intercensal updating method for local-level poverty estimates with estimated standard errors which we call Extended Structure PREserving Estimation (ESPREE). This method is a new extension of classical Structure PREserving Estimation (SPREE). We test our approach by applying it to inter-censal municipal-level poverty estimation and carrying out a validation exercise in the Philippines, comparing the estimates generated with an alternative ELL or EBP updating method due to Lanjouw and van der Wiede [Determining changes in welfare distributions at the microlevel: Updating poverty maps. (2006) Powerpoint presentation at the NSCB Workshop for the NSCB/World Bank Intercensal Updating Project] which uses time-invariant variables. The results show that the ESPREE estimates are preferable, generally being unbiased and concurring well with local experts’ opinion on poverty levels at the time of the updated survey.
Article
Full-text available
Background: Atheoretical large-scale data mining techniques using machine learning algorithms have promise in the analysis of large epidemiological datasets. This study illustrates the use of a hybrid methodology for variable selection that took account of missing data and complex survey design to identify key biomarkers associated with depression from a large epidemiological study. Methods: The study used a three-step methodology amalgamating multiple imputation, a machine learning boosted regression algorithm and logistic regression, to identify key biomarkers associated with depression in the National Health and Nutrition Examination Study (2009-2010). Depression was measured using the Patient Health Questionnaire-9 and 67 biomarkers were analysed. Covariates in this study included gender, age, race, smoking, food security, Poverty Income Ratio, Body Mass Index, physical activity, alcohol use, medical conditions and medications. The final imputed weighted multiple logistic regression model included possible confounders and moderators. Results: After the creation of 20 imputation data sets from multiple chained regression sequences, machine learning boosted regression initially identified 21 biomarkers associated with depression. Using traditional logistic regression methods, including controlling for possible confounders and moderators, a final set of three biomarkers were selected. The final three biomarkers from the novel hybrid variable selection methodology were red cell distribution width (OR 1.15; 95% CI 1.01, 1.30), serum glucose (OR 1.01; 95% CI 1.00, 1.01) and total bilirubin (OR 0.12; 95% CI 0.05, 0.28). Significant interactions were found between total bilirubin with Mexican American/Hispanic group (p = 0.016), and current smokers (p<0.001). Conclusion: The systematic use of a hybrid methodology for variable selection, fusing data mining techniques using a machine learning algorithm with traditional statistical modelling, accounted for missing data and complex survey sampling methodology and was demonstrated to be a useful tool for detecting three biomarkers associated with depression for future hypothesis generation: red cell distribution width, serum glucose and total bilirubin.
Article
Full-text available
Several investigators 'have demonstrated that the built-up area and equivalent radius of settlements can be estimated with considerable accuracy from a knowledge of the number of inhabitants. A recent circumstance, somewhat fortuitous, has led to an interesting, independent confirmation of this result. Specifically, on the basis of theoretical and empirical deductions it has been concluded that the built-up area of a settlement should be proportional to the population raised to some exponent (<1). From this it follows that the radius of a circle of the same area should be given by a formula of the form. r = aP b where P is the population. The population density is also readily deduced from this formula. For the United States empirical estimates yield the values a = 0.035, b = 0.44, when the radius is measured in kilometres. In general the built-up area differs from the area of the legal jurisdiction, and from the physical area used for enumerations. Using these coefficients, with census data plus latitude and longitude coordinates, it is possible to use a digital plotter to produce population maps, as illustrated in Fig. 1 for a portion of Michigan. Comparable maps prepared for sections of southern Germany, central Spain, and central Turkey yielded similarly reasonable results, but for a portion of the Nile Delta they suggested village overlapping to an outrageously absurd degree. There is no evidence that the Egyptian census data are seriously in error. A somewhat casual comparison of the Egyptian map plot with a Gemini photograph 2 of the same area suggested that dividing the radii of the villages by four would yield estimates of the correct order of magnitude (Fig. 2). The implication is that Egyptian towns are 16 times more compact than United States towns. This suggested a re-examination of the previous studies 1 , even though the actual project for which the maps were being prepared is relatively unrelated in objectives to these works. Table 1 summarizes the relevant observations. The phenomenon discussed for the Nile Delta is clearly consistent with Nordbeck's data for Japan. On this basis it is suggested that the coefficient a, (or a 2 /π, provides a useful characterization of settlement packing, with clear value in distinguishing between various strategies employed by society for the organization of spatial activity. Stewart and Warntz suggest that it is related to their notion of population potential. Extrapolation of the formulae to one individual yields a reasonable measure of space consumption, in principle capable of independent estimation. World-wide samples of actual measurements on the built-up area of settlements would appear to be possible if high resolution satellite photographs were available. The analysis can, of course, also be inverted, e.g., using the Apollo VI photograph (AS6-2-1462) of Dallas (Fig. 3). With 1/10 th inch coordinate paper to measure the built-up area and inferred consequences of the Public Land Survey System as a surrogate for an actual scale, fifteen minutes suffice to estimate the population at 668,000 people, which is within 2% of the 1960 census figure. To sharpen the efficacy of such estimates requires theoretical studies of the concept of built-up area, especially along the lines suggested by Nystuen 3 . The general utility and applicability of the settlement size relations, however, seems well established. Area, Vol 1, No 3 (1969); 30-34. (Also see 'Visual Evidence.rtf' under Movement on this CD) Acknowledgement B. Collins generously provided a translation of Egyptian census materials. Processing of the data and photographs was performed by G. Aspbury. NSF Grant GS-1082, Spectral Analysis of Spatial Series, supports the main inquiry.
Article
Full-text available
Much research has suggested that night-time light (NTL) can be used as a proxy for a number of variables, including urbanization, density, and economic growth. As governments around the world either collect census data infrequently or are scaling back the amount of detail collected, alternate sources of population and economic information like NTL are being considered. But, just how close is the statistical relationship between NTL and economic activity at a fine-grained geographical level? This paper uses a combination of correlation analysis and geographically weighted regressions in order to examine if light can function as a proxy for economic activities at a finer level. We use a fine-grained geo-coded residential and industrial full sample micro-data set for Sweden, and match it with both radiance and saturated light emissions. We find that the correlation between NTL and economic activity is strong enough to make it a relatively good proxy for population and establishment density, but the correlation is weaker in relation to wages. In general, we find a stronger relation between light and density values, than with light and total values. We also find a closer connection between radiance light and economic activity, than with saturated light. Further, we find the link between light and economic activity, especially estimated by wages, to be slightly overestimated in large urban areas and underestimated in rural areas.
Article
Full-text available
Bovine viral diarrhea virus (BVDV) causes one of the most economically important diseases in cattle, and the virus is found worldwide. A better understanding of the disease associated factors is a crucial step towards the definition of strategies for control and eradication. In this study we trained a random forest (RF) prediction model and performed variable importance analysis to identify factors associated with BVDV occurrence. In addition, we assessed the influence of features selection on RF performance and evaluated its predictive power relative to other popular classifiers and to logistic regression. We found that RF classification model resulted in an average error rate of 32.03% for the negative class (negative for BVDV) and 36.78% for the positive class (positive for BVDV).The RF model presented area under the ROC curve equal to 0.702. Variable importance analysis revealed that important predictors of BVDV occurrence were: a) who inseminates the animals, b) number of neighboring farms that have cattle and c) rectal palpation performed routinely. Our results suggest that the use of machine learning algorithms, especially RF, is a promising methodology for the analysis of cross-sectional studies, presenting a satisfactory predictive power and the ability to identify predictors that represent potential risk factors for BVDV investigation. We examined classical predictors and found some new and hard to control practices that may lead to the spread of this disease within and among farms, mainly regarding poor or neglected reproduction management, which should be considered for disease control and eradication. Electronic supplementary material The online version of this article (doi:10.1186/s13567-015-0219-7) contains supplementary material, which is available to authorized users.
Article
Full-text available
Historically, the Defense Meteorological Satellite Program's Operational Linescan System (DMSP-OLS) was the unique satellite sensor used to collect the nighttime light, which is an efficient means to map the global economic activities. Since it was launched in October 2011, the Visible Infrared Imaging Radiometer Suite (VIIRS) sensor on the Suomi National Polar-orbiting Partnership (NPP) Satellite has become a new satellite used to monitor nighttime light. This study performed the first evaluation on the NPP-VIIRS nighttime light imagery in modeling economy, analyzing 31 provincial regions and 393 county regions in China. For each region, the total nighttime light (TNL) and gross regional product (GRP) around the year of 2010 were derived, and a linear regression model was applied on the data. Through the regression, the TNL from NPP-VIIRS were found to exhibit R-2 values of 0.8699 and 0.8544 with the provincial GRP and county GRP, respectively, which are significantly stronger than the relationship between the TNL from DMSP-OLS (F16 and F18 satellites) and GRP. Using the regression models, the GRP was predicted from the TNL for each region, and we found that the NPP-VIIRS data is more predictable for the GRP than those of the DMSP-OLS data. This study demonstrates that the recently released NPP-VIIRS nighttime light imagery has a stronger capacity in modeling regional economy than those of the DMSP-OLS data. These findings provide a foundation to model the global and regional economy with the recently availability of the NPP-VIIRS data, especially in the regions where economic census data is difficult to access.
Article
Full-text available
The first global night-time light composite data from the Visible Infrared Imaging Radiometer Suite (VIIRS) day-night band carried by the Suomi National Polar-orbiting Partnership (NPP) satellite were released recently. So far, few studies have been conducted to assess the ability of NPP-VIIRS night-time light composite data to extract built-up urban areas. This letter aims to evaluate the potential of this new-generation night-time light data for extracting urban areas and compares the results with Defense Meteorological Satellite Program-Operational Linescan System (DMSP-OLS) data through a case study of 12 cities in China. The built-up urban areas of 12 cities are extracted from NPP-VIIRS and DMSP-OLS data by using statistical data from government as reference. The urban areas classified from Landsat 8 data are used as ground truth to evaluate the spatial accuracy. The results show the built-up urban areas extracted from NPP-VIIRS data have higher spatial accuracies than those from DMSP-OLS data for all the 12 cities. These improvements are due to the relatively high spatial resolution and wide radiometric detection range of NPP-VIIRS data. This study reveals that NPP-VIIRS night-time light composite data would provide a powerful tool for urban built-up area extraction at national or regional scale.
Article
Full-text available
This paper describes an initial assessment of human-induced nighttime lights acquired by the Defence Meteorological Satellite Program (DMSP) Operational Linescan System (OLS) with respect to its applicability in monitoring settlement patterns, population, electricity consumption, gross domestic product (GDP), and carbon dioxide emissions at different spatial levels in the Republic of Kazakhstan. The results revealed the suitability of DMSP-OLS data to detect both urban expansion and contraction over last two decades caused by the new economic situation following the independence of Kazakhstan in 1991. Relationships between DMSP-OLS urban lit area and the socioeconomic parameters were quantified. The DMSP-OLS data proved to be an effective tool in the monitoring of both the spatial and temporal variability of the examined socioeconomic parameters.
Article
Full-text available
The nighttime light data records artificial light on the Earth's surface and can be used to estimate the spatial distribution of the gross domestic product (GDP) and the electric power consumption (EPC). In early 2013, the first global NPP-VIIRS nighttime light data were released by the Earth Observation Group of National Oceanic and Atmospheric Administration's National Geophysical Data Center (NOAA/NGDC). As new-generation data, NPP-VIIRS data have a higher spatial resolution and a wider radiometric detection range than the traditional DMSP-OLS nighttime light data. This study aims to investigate the potential of NPP-VIIRS data in modeling GDP and EPC at multiple scales through a case study of China. A series of preprocessing procedures are proposed to reduce the background noise of original data and to generate corrected NPP-VIIRS nighttime light images. Subsequently, linear regression is used to fit the correlation between the total nighttime light (TNL) (which is extracted from corrected NPP-VIIRS data and DMSP-OLS data) and the GDP and EPC (which is from the country's statistical data) at provincial-and prefectural-level divisions of mainland China. The result of the linear regression shows that R-2 values of TNL from NPP-VIIRS with GDP and EPC at multiple scales are all higher than those from DMSP-OLS data. This study reveals that the NPP-VIIRS data can be a powerful tool for modeling socioeconomic indicators; such as GDP and EPC.
Article
Full-text available
Numerous studies have examined the correlation between socioeconomic statistics and night light (NL) imagery. Previous studies have shown that the NL data correlates well with gross domestic product (GDP) statistics. This study calls for a focus on process over correlation between the variables so as to better inform scaled models of the relationship. A focus on process is addressed in this study by examining the relationship between the variables at two scales and two time periods. The two scales examined are: States and Metropolitan Statistical Areas (MSA). The MSA scale exhibits a stronger relationship with the NLs over the State scale, and the results at either scale are consistent through time. However, the models examined here are miss-specified at all scales. Examination of outliers and residuals informs for future well-described models of the relationship.
Article
Full-text available
All countries around the world and many international bodies, including the United Nations Development Program (UNDP), United Nations Food and Agricultural Organization (FAO), the International Fund for Agricultural Development (IFAD) and the International Labor Organization (ILO), have to eliminate rural poverty. Estimation of regional poverty level is a key issue for making strategies to eradicate poverty. Most of previous studies on regional poverty evaluations are based on statistics collected typically in administrative units. This paper has discussed the deficiencies of traditional studies, and attempted to research regional poverty evaluation issues using 3-year DMSP/OLS night-time light satellite imagery. In this study, we adopted 17 socio-economic indexes to establish an integrated poverty index (IPI) using principal component analysis (PCA), which was proven to provide a good descriptor of poverty levels in 31 regions at a provincial scale in China. We also explored the relationship between DMSP/OLS night-time average light index and the poverty index using regression analysis in SPSS and a good positive linear correlation was modelled, with R2 equal to 0.854. We then looked at provincial poverty problems in China based on this correlation. The research results indicated that the DMSP/OLS night-time light data can assist analysing provincial poverty evaluation issues.
Article
Full-text available
Timely and accurate information about the dynamics of urban expansion is vital to reveal the relationships between urban expansion and the ecosystem, to optimize land use patterns, and to promote the effective development of cities in China. Nighttime stable light data from the Defense Meteorological Satellite Program's Operational Line-scan System (DMSP-OLS) Nighttime Lights Time Series dataset provide a new source of information that can quickly reveal the dynamics of urban expansion. However, the DMSP-OLS sensor has no on-board calibration, which makes it difficult to directly compare time series data from multiple satellites. This study developed a new method for systematically correcting multi-year multi-satellite nighttime stable lights data and rapidly extracting the dynamics of urban expansion based on this corrected data for China from 1992 to 2008. The results revealed that the proposed method effectively reduced abnormal discrepancy within the nighttime stable light data and improved continu
Article
Full-text available
A global poverty map has been produced at 30 arcsec resolution using a poverty index calculated by dividing population count (LandScan 2004) by the brightness of satellite observed lighting (DMSP nighttime lights). Inputs to the LandScan product include satellite-derived land cover and topography, plus human settlement outlines derived from high-resolution imagery. The poverty estimates have been calibrated using national level poverty data from the World Development Indicators (WDI) 2006 edition. The total estimate of the numbers of individuals living in poverty is 2.2 billion, slightly under the WDI estimate of 2.6 billion. We have demonstrated a new class of poverty map that should improve over time through the inclusion of new reference data for calibration of poverty estimates and as improvements are made in the satellite observation of human activities related to economic activity and technology access.
Article
Full-text available
Population health is linked closely to poverty. To assess the effectiveness of health interventions it is critical to monitor the spatial and temporal changes in the health indicators of populations and outcomes across varying levels of poverty. Existing measures of poverty based on income, consumption or assets are difficult to compare across geographic settings and are expensive to construct. Remotely sensed data on artificial night time lights (NTL) have been shown to correlate with gross domestic product in developed countries. Using national household survey data, principal component analysis was used to compute asset-based poverty indices from aggregated household asset variables at the Administrative 1 level (n = 338) in 37 countries in Africa. Using geographical information systems, mean brightness of and distance to NTL pixels and proportion of area covered by NTL were computed for each Administrative1 polygon. Correlations and agreement of asset-based indices and the three NTL metrics were then examined in both continuous and ordinal forms. At the Administrative 1 level all the NTL metrics distinguished between the most poor and least poor quintiles with greater precision compared to intermediate quintiles. The mean brightness of NTL, however, had the highest correlation coefficient with the asset-based wealth index in continuous (Pearson correlation = 0.64, p < 0.01) and ordinal (Spearman correlation = 0.79, p < 0.01; Kappa = 0.64) forms. Metrics of the brightness of NTL data offer a robust and inexpensive alternative to asset-based poverty indices derived from survey data at the Administrative 1 level in Africa. These could be used to explore economic inequity in health outcomes and access to health interventions at sub-national levels where household assets data are not available at the required resolution.
Article
Full-text available
Background Sub-national figures providing information about the wealth of the population are useful in defining the spatial distribution of both economic activity and poverty within any given country. Furthermore, since several health indicators such as life expectancy are highly correlated with household welfare, sub-national figures allow for the estimation of the distribution of these health indicators within countries when direct measurement is difficult. We have developed methods that utilize spatially distributed information, including night-time light imagery and population to model the distribution of income per capita, as a proxy for wealth, at the country and sub-national level to support the estimation of the distribution of correlated health indicators. Results A first set of analysis are performed in order to propose a new global model for the prediction of income per capita at the country level. A second set of analysis is then confirming the possibility to transfer the country level approach to the sub-national level on a country by country basis before underlining the difficulties to create a global or regional models for the extrapolation of sub-national figures when no country data set exists. Conclusions The methods described provide promising results for the extrapolation of national and sub-national income per capita figures. These results are then discussed in order to evaluate if the proposed methods could not represent an alternative approach for the generation of consistent country specific and/or global poverty maps disaggregated to some sub-national level.
Article
In 2014, China initiated a nationwide poverty reduction campaign through deploying photovoltaic (PV) systems in its vast rural areas, which aims to support over 2 million households. Despite the significant socioeconomic benefits anticipated by policy-makers, it remains unclear regarding the challenges of implementing such an ambitious program in remote rural areas and its effect on poverty reduction. Focusing on Qinghai, a province that serves as the testbed for solar energy development in China but suffers chronic poverty, we aim to assess implementation status of the program, and examine whether and how solar energy-based development affects rural household well-being and generates socioeconomic spillovers. Using data from multiple sources, including household survey, interviews, policy documents, and large-scale socioeconomic covariates, as well as advanced statistical and spatial analyses, we find there have been substantial adjustments to the plan of building small-scale PV stations across poor villages throughout Qinghai. While total installation capacity was met, the 97 planned PV stations in 39 counties were aggregated into 24 medium- to large-scale PV farms in 27 counties. We also find substantial challenges to precisely target the poor, improve their income, facilitate a transition in household use of energy, and enhance local capacity for economic development. Future PV-based intervention programs need to sufficiently consider local contexts and demands, and promote local engagement to achieve the twin goals of sustainable energy transition and poverty reduction.
Article
After nearly seventy years of poverty alleviation, China has basically solved the problem of providing food and clothing to the rural poor. However, the islanding effect of the distribution of the poor and the marginal diminishing effect of the antipoverty resources, which restrict the effects of poverty-eliminating strategies, are increasingly obvious. In this context, targeted poverty alleviation is designed by the Chinese central government. Therefore, it is necessary to systematically analyse targeted poverty alleviation and explore the mechanism of its practices. In addition to reviewing the process of antipoverty in rural China, this study investigated the connotation of targeted poverty alleviation and considered the case of Fuping in Hebei Province to explore targeted antipoverty practices. Results showed that poverty alleviation in rural China could be divided into six stages, and the essence of targeted poverty alleviation lied in helping those who truly needed help and achieving genuine outcomes by accurately identifying and assisting poverty-stricken households, accurately managing objects and measures and accurately assessing antipoverty effectiveness. The practices of targeted poverty alleviation in Fuping county mainly involved industrial development, resettlement assistance, financial and educational development, together with medical security and land consolidation, all of which built an endogenous and sustainable mechanism enabling regional development. This study suggests that targeted poverty alleviation is an innovative strategy which is suitable for overcoming the islanding effect of poverty distribution and helping policymakers formulate detailed and targeted measures to eliminate poverty.
Article
Geography of poverty (GOP) or poverty geography is a branch of human geography, which studies the geographical patterns, distribution characteristics, areal types and evolution mechanism of poverty and the relationship with geographical environment as well as antipoverty measures. Based on the systematical analysis on the significance of GOP research, this study firstly put forward the impoverished areal system (IAS), and then elaborated the main contents, research progresses and existing problems in GOP research, and finally proposed the possible key areas in the future. Results show that the IAS is an open system with structure and function and has its life-cycle law, which is composed of natural endowments, location conditions, human capital and geographical capital within a certain geographical area. The subsystem of human, land and industry is the core of the IAS. Poverty geography studies both regional (place) poverty and individual (people) poverty. Regional poverty is an external manifestation of the coupling maladjustment of human, land and industry elements in a particular area. There are 5W + H (What, Where, Why, When, Who and How) models in GOP research. Key areas of future GOP research include: 1) IAS's life cycle evolution law; 2) regional multidimensional poverty measurement; 3) geographical identification of poverty and its areal type; 4) dynamic simulation of impoverished and its mechanism; 5) poverty mapping; 6) antipoverty measure; and 7) poverty reduction effectiveness evaluation. Facing the UN's goal of eradicating poverty by 2030, poverty geography research in the new period should focus on the complexity, spatial heterogeneity and mechanism of poverty, and designs anti-poverty paths and models suitable for different countries. To adapt to the trend of globalization and informationization, poverty geographers should make use of modern technologies such as data platform, cloud computing, remote sensing and artificial intelligence to focus on the spatio-temporal pattern of poverty and its driving mechanism as well as antipoverty path, and to solve the global poverty problem and promote the internationalization, basification and engineering of geography.
Article
Poverty has become one of the long-term predicaments affecting the development of human society during the 2 1 s t century. Eliminating poverty in rural areas in 2020 under the current standards and addressing the regional overall poverty are the most difficult challenges to build a sustainable society across China. Since traditional statistical data on the socioeconomic conditions have been limited by the lack of information regarding the area being studied and the time-consuming nature of data collection, and because objectivity has been difficult to be guaranteed, this method cannot meet the demand for large-scale, long-term, and dynamic research for addressing the problem of poverty. Developing methods for measuring multi-dimensional poverty and improving the accuracy of poverty identification are the key issues for improving the quality and effectiveness of rural poverty reduction programs in China. In light of the academic thoughts of the vulnerability and sustainability of livelihood analysis framework, this study established an index system and combined 30 variables into a sustainable livelihoods index (SLI), including 22 counties of Ningxia H u i Autonomous Region as a sample, to reflect the multiple factors that affect the livelihood of farmers. Regression models have been used to verify the correlation between nighttime light index and S L I . In 2002 and 2 0 1 3, the model was tested in 43 counties of Qinghai Province, and the estimates had an average relative error of only 10.84% and 1 2 . 1 9 %, respectively. This efficient method has good practical applicability and relatively high measurement precision for multi-dimensional spatial poverty identification. Spatial clustering effect of ecological poverty was analyzed using the explore spatial data analysis (E S D A) method. A significant spatial auto-correlation was noted for sustainable livelihood, since M o r a n ' s I index in 2002 and 2013 was 0 . 6 3 6 and 0 . 5 7 9, respectively, which indicates that poverty of neighboring counties has a positive effect on the poverty of a specific county. Both H i g h - H i g h and Low-Low areas are distributed intensively, whereas both High-Low and Low-High areas are distributed discretely. Some counties with a Low-Low SLI pattern fall into the spatial trap of poverty based on the results of Local Moran's I index. These counties are located in the western parts of the Zaerdong—Bose Line. Geographical identification of multi-dimensional spatial poverty in rural China was performed at the grid and county levels. In China, 642 and 612 multi¬ dimensional poverty counties were recorded in 2002 and 2 0 1 3, respectively. During 2 0 0 2 — 2 0 1 3, the contiguous and concentrated distribution of poverty-stricken areas has not changed significantly. In 2 0 1 3, the multi-dimensional poverty counties showed 3 spatial areal patterns: island distribution in eastern China, massive distribution in central China, and contiguous distribution in western China. The multi-dimensional poverty counties need to develop different policies to overcome poverty based on regional sustainable livelihood capacity and development potential. This method can improve the accuracy of targeting and identifying multi-dimensional poverty areas and could surpass the current Poverty-Targeting-Alleviation (j i n g zhun fu p i n) initiatives dominating the poverty-reduction policy of China's government. To reduce multi¬ dimensional poverty, China needs to have a clear regional development strategy that favors disadvantaged areas. The core implication is to combine region-based strategy and people-based policy.
Article
The economic development difference index and spatial autocorrelation model is used to analyze the different patterns of economic development in China's provincial border counties. And the spatial heterogeneity of regional economic development and its driving factors were studied by using Ordinary Least Square (OLS) and geo-weighted regression model (GWR). The results show that the counties' economic development of the provincial border areas in China has significant spatial agglomeration, and the areas with large differences in border economic development are concentrated in the border areas such as Inner Mongolia-Gansu, Inner Mongolia-Ningxia, Shaanxi-Inner Mongolia and other border areas. There is a negative correlation between the macroeconomic regulation and the economic development of the western region. The influence of educational development level on county economic disparity shows the regional differentiation of poverty and developed counties. There is a positive correlation between the compactness of the boundary, the terrain fluctuation degree and the provincial economic development at the provincial boundary. Traffic dominance and industrial structure factor show a positive correlation trend in terms of the difference of county economic development. This paper analyzes the differences between the influencing factors and the direction of the impact of different factors on the development index of county economic development in different counties. It provides scientific basis for rationally regulating the elements of development in different regions, narrowing the economic development differences in the border areas and setting up different provincial border development strategies.
Article
Monthly composites of night-time light acquired from the Meteorological Satellite Program’s Operational Linescan System (DMSP/OLS) had been used to evaluate socio-economic dynamics and human rights during the Syrian Civil War, which started in March 2011. However, DMSP/OLS monthly composites are not available subsequent to February 2014, and the only available night-time light composites for that period were acquired from the Suomi National Polar-orbiting Partnership satellite’s Visible Infrared Imaging Radiometer Suite (Suomi NPP/VIIRS). This article proposes an intercalibration model to simulate DMSP/OLS composites from the VIIRS day-and-night band (DNB) composites, by using a power function for radiometric degradation and a Gaussian low pass filter for spatial degradation. The DMSP/OLS data and the simulated DMSP/OLS data were combined to estimate the city light dynamics in Syria’s major human settlement between March 2011 and January 2017. Our analysis shows that Syria’s major human settlement lost about 79% of its city light by January 2017, with Aleppo, Daraa, Deir ez-Zor, and Idlib provinces losing 89%, 90%, 96%, and 99% of their light, respectively, indicating that these four provinces were most affected by the war. We also found that the city light in Syria and 12 provinces rebounded from early 2016 to January 2017, possibly as a result of the peace negotiation signed in Geneva.
Article
Poverty is a challenge facing all countries and the international community as a whole. Promoting development, narrowing the rural-urban gap, eliminating poverty and achieving common prosperity are all ideals that humanity constantly pursues. Despite the great achievements have been made in poverty alleviation over the past three decades, the extent of poverty in rural China is still high. It is both necessary and urgent to fully understand the root and status quo of China's poverty and establish a scientific poverty relief system. Based on high resolution poverty data, this study systematically examined the status quo and spatial distribution characteristics of poverty in rural China and its driving mechanism. The results showed that the distribution of the Chinese rural poor exhibits a distinct spatial agglomeration feature. Poverty is mainly concentrated in the remote deep rocky mountainous areas, border areas and minority areas of central and western China and gradually gathers towards the southwestern region. The “islanding effect” may well appear in China's poverty-stricken regions in the future. The proportion of poor people in the northwestern and southeastern regions of the Hu Huanyong line was 16.4% and 83.6%, respectively, indicating the uneven distribution of the rural poor. Furthermore, further investigations indicated that suffering from illness is the greatest contributor to current individual or transient poverty in rural China. The lack of natural endowments, poor geographic conditions and fragile ecological environment are the main driving forces behind persistent poverty. Ultimately, we proposed that China implement a scientific, differentiated, sustainable, targeted and problem-oriented poverty alleviation strategy that can lift the country's rural poor population out of poverty by 2020 as scheduled.
Article
The rapid development of global industrialization and urbanization has resulted in a great deal of electric power consumption (EPC), which is closely related to economic growth, carbon emissions, and the long-term stability of global climate. This study attempts to detect spatiotemporal dynamics of global EPC using the Defense Meteorological Satellite Program’s Operational Linescan System (DMSP-OLS) nighttime stable light (NSL) data. The global NSL data from 1992 to 2013 were intercalibrated via a modified invariant region (MIR) method. The global EPC at 1 km resolution was then modeled using the intercalibrated NSL data to assess spatiotemporal dynamics of EPC from a global scale down to continental and national scales. The results showed that the MIR method not only reduced the saturated lighted pixels, but also improved the continuity and comparability of the NSL data. An accuracy assessment was undertaken and confined that the intercalibrated NSL data were relatively suitable and accurate for estimating EPC in the world. Spatiotemporal variations of EPC were mainly identified in Europe, North America, and Asia. Special attention should be paid to China where the high grade and high-growth type of EPC covered 0.409% and 1.041% of the total country area during the study period, respectively. The results of this study greatly enhance the understanding of spatiotemporal dynamics of global EPC at the multiple scales. They will provide a scientific evidence base for tracking spatiotemporal dynamics of global EPC.
Article
Measuring consumption and wealth remotely Nighttime lighting is a rough proxy for economic wealth, and nighttime maps of the world show that many developing countries are sparsely illuminated. Jean et al. combined nighttime maps with high-resolution daytime satellite images (see the Perspective by Blumenstock). With a bit of machine-learning wizardry, the combined images can be converted into accurate estimates of household consumption and assets, both of which are hard to measure in poorer countries. Furthermore, the night- and day-time data are publicly available and nonproprietary. Science , this issue p. 790 ; see also p. 753
Article
Policy-makers in the world's poorest countries are often forced to make decisions based on limited data. Consider Angola, which recently conducted its first postcolonial census. In the 44 years that elapsed between the prior census and the recent one, the country's population grew from 5.6 million to 24.3 million, and the country experienced a protracted civil war that displaced millions of citizens. In situations where reliable survey data are missing or out of date, a novel line of research offers promising alternatives. On page 790 of this issue, Jean et al. ( 1 ) apply recent advances in machine learning to high-resolution satellite imagery to accurately measure regional poverty in Africa.
Article
The long time series of nighttime light (NTL) data collected by DMSP/OLS sensors provide a unique and valuable resource to study changes in human activities. However, its full time series potential has not been fully explored, mainly due to inconsistencies in the temporal signal. Previous studies have tried to resolve this issue in order to generate a consistent NTL time series. However, due to geographic limitations with the algorithms, these approaches cannot generate a coherent NTL time series globally. The purpose of this study is to develop a methodology to create a consistent NTL time series that can be applied globally. Our method is based on a novel sampling strategy to identify pseudo-invariant features. We select data points along a ridgeline – the densest part of a density plot generated between the reference image and the target image-- and then use those data points to derive calibration models to minimize inconsistencies in the NTL time series. Results show that the algorithm successfully calibrates DMSP/OLS annual composites and generates a consistent NTL time series. Evaluation of the results show that the calibrated NTL time series significantly reduces the differences between two images within the same year and increases the correlations between NTL time series and GDP as well as with energy consumption, and outperforms the Elvidge et al. (2014) method. The methodology is simple, robust, and easy to implement. The quality-enhanced NTL time series can be used in myriad applications that require a consistent data set over time.
Article
Poverty has appeared as one of the long-term predicaments facing development of human society during the 21st century. Estimation of regional poverty level is a key issue for making strategies to eliminate poverty. This paper aims to evaluate the ability of the nighttime light composite data from the Visible Infrared Imaging Radiometer Suite (VIIRS) Day–Night Band (DNB) carried by the Suomi National Polar-orbiting Partnership (NPP) Satellite in estimating poverty at the county level in China. Two major experiments are involved in this study, which include 1) 38 counties of Chongqing city and 2) 2856 counties of China. The first experiment takes Chongqing as an example and combines 10 socioeconomic variables into an integrated poverty index (IPI). IPI is then used as a reference to validate the accuracy of poverty evaluation using the average light index (ALI) derived from NPP-VIIRS data. Linear regression and comparison of the class ranks have been employed to verify the correlation between ALI and IPI. The results show a good correlation between IPI and ALI, with a coefficient of determination (R2R^2) of 0.8554, and the class ranks of IPI and API show relative closeness at the county level. The second experiment examines all counties in China and makes a comparison between ALI values and national poor counties (NPC). The comparison result shows a general agreement between the NPC and the counties with low ALI values. This study reveals that the NPP-VIIRS data can be a useful tool for evaluating poverty at the county level in China.
Article
DMSP-OLS (Defense Meteorological Satellite Program Operational Linescan System) night-time light data can accurately reflect the scope and intensity of human activities. However, the raw data cannot be used directly for temporal analyses due to the lack of inflight calibration. There are three problems that should be addressed in intercalibration. First, because of differences between sensors, the data are not identical even when obtained in the same year. Second, different acquisition times may lead to random or systematic fluctuations in the data obtained by satellites in different orbits. Third, a pixel saturation phenomenon also exists in the urban centres of the image. Therefore, an invariant region method was used in this article, and