Baochao Li’s research while affiliated with Sun Yat-Sen University and other places

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.

In this paper, we study the characteristics of the spatial–temporal pattern of land used for transportation at the county level since the implementation of the reform and opening-up policy in China and discuss the factors that influence the spatial differences between lands used for transportation in order to provide a reference for the formulation of traffic policies. The authors used ArcGIS spatial analysis, an ordinary least squares (OLS) regression model, and a geographic detector model based on the data of the transportation network at the county level in China from 1978 to 2018. We obtained the following results: (1) The land used for transportation at the county level in China is divided by the Hu Huanyong Line, which is characterized by spatial variation, where the southeastern region is higher than the northwestern region. (2) Counties with a high proportion of land used for transportation show obvious changes, characterized by the transformation from the “corridor” zonal distribution of arteries to the “diamond” group distribution of major city clusters, reducing the gap in land used for transportation at the county level in China. (3) The level of industrialization, per capita gross regional product (PGRP), and ratio of the non-agricultural working population all have an incentivizing impact on the increase in land used for transportation at the county level in China. We conclude that the land used for transportation at the county level in China is jointly decided by the economy, industry, and population. Therefore, we believe that it is necessary to promote fast economic growth, the upgrading of industrial structures, and population density to achieve the balanced development of land used for transportation at the county level in China.

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.

Based on geographic information system (GIS) spatial analysis technology, the spatial pattern of raster grid transport accessibility for the Guangdong-Hong Kong-Macao Greater Bay area was studied and the states of spatial connectedness were simulated using highway passenger transport, railway passenger transport, port passenger transport and aviation passenger transport data. The result shows that transport accessibility within the Guangdong-Hong Kong-Macao Greater Bay area costs ‘one hour’ and the spatial distribution of accessibility in the area presents clear ‘core-periphery’ spatial characteristics, with Guangzhou, Foshan, Shenzhen constituting the core. The transport accessibility of Guangdong-Hong Kong-Macao is high. Average accessibility of urban nodes as measured by travel time is 0.99 h, and the areas accessible within 1.42 h occupy 79.14% of the total area. Most of the areas with the lowest accessibility are found in the peripheral area, with the worst accessibility being 4.73 h. Compared with the west-side cities, the economically developed east-side cities of the Guangdong-Hong Kong-Macao Greater Bay area have higher connectivity with roads, railways, ports, and aviation transport. Guangzhou, Foshan, Zhuhai, Shenzhen, Hong Kong and Macao are closely linked. The higher the accessibility, the closer the intercity connectedness.