Amiya Gayen’s research while affiliated with University of Calcutta and other places

What is this page?


This page lists works of an author who doesn't have a ResearchGate profile or hasn't added the works to their profile yet. It is automatically generated from public (personal) data to further our legitimate goal of comprehensive and accurate scientific recordkeeping. If you are this author and want this page removed, please let us know.

Publications (36)


Location of the study area (sheded). The red circles indicate major cities from the area. Each green dot indicates Schistocerca gregaria occurrence during 2019–2020.
Predisposing parameters projected for locust suitability. (a) maximum temperature, (b) minimum temperature, (c) temperature, (d) precipitation, (e) wind speed, (f) wind direction, (g) visibility, (h) cloud cover, and (i) relative humidity.
The spatial distribution of projected locust suitability maps by WoE (top) and FR (below) models.
Significant locust upsurge-related components and their corresponding correlation coefficients (r) as determined using PCA and Karl Pearson’s method. In the above plot, the distribution of each variable is shown on the diagonal. On the bottom of the diagonal: the bivariate scatter plots with a fitted line are displayed. On the top of the diagonal: the value of the correlation plus the significance level as stars. Each significance level is associated to a symbol: p-values (0.001, 0.01, 0.05, and 1) symbolizes with ***, **, * and no star.
Principal Component plot in Rotated Space. Parameters are indicative how close they are related for locust occurrence.

+3

Influence of climate on desert locust (Schistocerca gregaria Forskål, 1775) Plague and migration prediction in tropics
  • Article
  • Full-text available

October 2024

·

149 Reads

·

Amiya Gayen

·

·

Amlan Das

The outbreak of the desert locust Schistocerca gregaria Forskål, 1775, which originated from the Horn of Africa in 2019–2020 created an episodic plague under bio-geographical settings in the arid and semi-arid areas of South and Southwest Asia. In India, it happened after twenty-seven years due to the persistence of a few favourable conditions caused by its plague, resulting in hundreds of crores in crop damage. Keeping this in mind, the study aims to assess the suitability and likelihood of the desert locust epidemic occurring in India, utilizing two widely recognized statistical models: Weight-of-Evidence (WoE) and Frequency Ratio (FR). This work evaluated nine critical climatic factors for the study considering western and central parts of India. The ‘Projected Locust Suitability’ (PLS) was calculated by analyzing the correlation of the considered variables and the occurrence of locust swarms and bands. The significance (importance) of each variable on PLS was determined using Principal Component Analysis (PCA) and Random Forest (RF) algorithms. The PLS maps clearly show that 42.7–52.8% of the areas fall under high and very high locust suitability zones. The result suggests that the Ajmer-Gwalior-Allahabad tract is highly prone to future locust occurrences, while the Aligarh-Bareilly-Lakhimpur tract is moderately susceptible. The effectiveness of both modelled PLS maps was determined with the help of the ROC curve. The AUC results indicate that both the WoE (0.92) and the RF (0.90) models worked remarkably well in precisely predicting PLS. The RF-based IncNodePurity analysis indicates that low to moderate temperatures in the presence of cloud cover significantly impact locust occurrence and migration. The present findings are projected to direct the development of sustainable locust management strategies utilizing proper land use policies in the tropical climate.

Download

Gully Erosion Susceptibility Using Advanced Machine Learning Method in Pathro River Basin, India

May 2024

·

40 Reads

The concept of gully erosion susceptibility has received more focus in recent years, and the attention has been drown by researchers for the implementation of policy and practices. Soil erosion through gully development is a natural geomorphic process that controlled by human activities and highly effected environmental quality, ecosystem, natural resources, and agricultural activities; and it promotes hazards. So, gully erosion management is a key attempt for sustainable land use practices to assess and monitor the soil quality. In this work, the researchers try to employ a gully erosion susceptibility model along with management strategies and its controlling factors in Pathro River Basin, India. Authors follow a well-accepted machine learning-based boosted regression tree (BRT) model for the assessment of urgent management within the study area. Twelve predisposing factors were used here for the development of susceptibility map to find the areas that urgently required to take a robust management policy. The model depicts high prediction capacity with a strong area under the curve (AUC is 87.40%). Finally, the dynamic nature of ecosystem service value (ESVs) and its sensitivity to land use have been examined by implementing an elasticity indicator. Badland areas were converted to forestland during 2010–2020 to manage the land degradation, but in some areas the gully erosion processes and their increasing trend were found due to unplanned land use practices. Also, the causes of erosive agents were evaluated by fitted function. For this study basin, forest is pivotal land use for both management of land degradation and ESVs so, it should be managed and conserved by afforestation programmes. The outcome of this work provides a new window for policy makers to initiate appropriate dimension about the land degradation and ecosystem management in prioritized areas of humid tropics.


Application of Ensemble Machine Learning Models to Assess the Sub-regional Groundwater Potentiality: A GIS-Based Approach

September 2022

·

79 Reads

Effective data mining models are powerful tools for the prediction and management of sub-regional groundwater resources. In this work, an integrated attempt is employed to assess the groundwater potentiality in C. D. Block of Birbhum District, India using GIS-based novel ensemble machine learning models of Radial Basis Function neural network (RBFnn) in form of RBFnn-Bagging and RBFnn-Dagging. Fourteen hydro-geomorphological factors were used to find the most potential groundwater area. To support the result, observation data of 86 sites were incorporated empirically. Out of these, 70% were randomly split for the training dataset to develop the model and remaining 30% were used for model validation. Results predict excellent groundwater potentiality by the RBFnn-Bagging and RBFnn-Dagging as they covered 17.38% and 13.97% of the study area, respectively. The prediction capacity of newly built models was established with the root mean square error (RMSE), accuracy, precision, and receiver operating characteristic (ROC) curve which shows a satisfactory result as the RMSE values of 0.05 and 0.07 and AUC values of 82.1% and 81.30% are obtained for RBFnn-Bagging and RBFnn-Dagging models respectively. Well-known mean decrease Gini (MDG) from the random forest (RF) algorithm, implemented to determine the relative importance of the factors, reveals that distance from river, pond frequency, aspect, stream junction frequency, elevation, and geomorphology are most useful determinants of groundwater potentiality in the study area. The adopted approach has a wide scope in effective planning and sustainable management of groundwater resources.KeywordsGroundwater potentialityEnsemble methodMachine learning modelsRBFnnRoot mean square error


Soil erodibility assessment of laterite dominant sub-basin watersheds in the humid tropical region of India

June 2022

·

128 Reads

·

12 Citations

CATENA

Sub-basin prioritization is an essential aspect of watershed development initiatives as a part of the sustainable management program for natural resources. The present work aims to analyse the soil erodibility at sub-basin scale in the Pathro River Basin area of Jharkhand, India. Degradation of land resources is multifaceted, and its severity leads to soil detachment, thus rendering it a complex and interlinked system. Sixteen closely correlated morphometric attributes of the erosion process are considered for prioritizing watersheds by applying the frequency ratio (FR) method. This work assigns Support Vector Machine (SVM) algorithm to evaluate the existing soil risk condition with the help of twelve soil erosion influencing geo-environmental factors at the sub-basin area. Soil samples were examined using scanning electron microscopy with energy dispersive x-ray analysis (SEM-EDX) to acquire the micro-graphic and physical condition of dominant soil forming minerals and their influences to develop susceptibility of peds to erode. The prioritisation results from both approaches show a reasonably similar output, identifying nine sub-watersheds as very high soil erosion-prone, while four sub-watersheds are recognised as low-risk. Field observation reveals that lowering of plunge pool and head retreat are dominant processes of gully extension in very high to high sub-basin prioritization areas. The final output provides a comprehensive platform for the urgency of policy interventions to minimize erosion risk and ecological damage in prioritized areas of Pathro River Basin, Jharkhand.



Location map of the study area; (a) India (b) West Bengal (c) Kunur River Basin located within the Purba and Paschim Burdwan district of West Bengal and in the lower catchment of Ajay River Basin
Flowchart illustrated the applied methodology of flood susceptibility mapping of Kunur River Basin
Factors determine the flood susceptibility of the study area: (a) elevation, (b) aspect, (c) distance from river, (d) Land use/land cover (LULC), (e) topographical wetness index (TWI), (f) slope, (g) topographical ruggedness index (TRI), (h) topographical positioning index (TPI), (i) soil type, (j) normalized difference vegetation index (NDVI), k. Geomorphology, l. rainfall intensity, m. curve number (CN), n. stream power index (SPI), o. convergence index (CI) and p. geology
Flood susceptibility maps produced by (a) MLP, (b) RF, (c) Bagging, and (d) CNN
Validation of flood susceptibility maps applying ROC curve: (a) Success rate curve (applying training dataset) and (b) Prediction rate curve (applying validation dataset)
Deep learning algorithms to develop Flood susceptibility map in Data-Scarce and Ungauged River Basin in India

March 2022

·

707 Reads

·

26 Citations

Stochastic Environmental Research and Risk Assessment

Flood is considered the most extensive natural disaster around the globe. Kunur River, a riverine landscape of Rarh Bengal, was selected as the study area because this basin has undergone several floods. This research work applied deep learning and benchmark machine learning methods for preparing the flood susceptibility maps (FSMs) at a basin scale. For this work, sixteen flood controlling factors were applied. These predisposing factors were chosen based on field knowledge, previous researches, and data availability. The FSMs were produced for the better palling and management of natural resources of Kunur River Basin, applying one deep learning model (DLM) includes convolution neural network (CNN) model and three benchmark machine learning methods (BMLMs) including multilayer perceptron (MLP), Bagging, and random forest (RF). The differences in prediction capacity between the models were assessed by applying the Friedman rank test and Wilcoxon test. Performance of the FSMs, evaluated through the precision, accuracy, AUC (area under the curve), and statistical measures revealed that CNN has the highest AUC values (0.934) followed by MLP (0.927), Bagging (0.897), and RF (0.900) respectively. The CNN model’s prediction capacity is slightly better than Bagging, RF, and MLP models. Finally, we can conclude that the deep learning model is more robust than the benchmark MLMs (RF, MLP and Bagging) and CNN is excellent alternative for FSMs considering the used variables.


Spatial modeling of river bank shifting and associated LULC changes of the Kaljani River in Himalayan foothills

February 2022

·

1,488 Reads

·

21 Citations

Stochastic Environmental Research and Risk Assessment

Channel dynamics is an inherent characteristic of river in the floodplain region. It has some significant impacts on the ecosystem and human life. GIS-based, DSAS and CA-Markov models are efficient techniques to measure historical and predictive changes following channel shifting and LULC change. In this study, forty-eight years (1972-2020) of earth observatory data were taken to demarcate and detect the channel bank position and LULC change along the Kaljani River, located at the eastern Himalayan foothill. During 1998-2008, a very high rate of erosion has been taken place on both the bankline, which are about −4.48 m/y (left bank) and −3.48 m/y (right bank), respectively. The overall result of the predicted bankline represents that the bulky expansion will occur along the left bank, and sediment accretion will take place at the right bank. Among the three zones, both banks of zone 'A' (lower part of the river) are worst affected in the past and present and will follow the same trends in future. The LULC change of all six classes from 1972 to 1998 is very high compared with the changes between 1998 and 2020. Moreover, long profile, hypsometric curve value, and the Soil Conservation Service Curve Number (SCS-CN) value have a significant help in understanding and identifying consequences reasons. The accuracy level is validated by the actual bankline positions (2020) with predicted bankline (2020) and actual LULC (2020) to predicted LULC (2020) empirically with RMSE and statistical test. The accuracy level of this study is conducted with the Kappa statistics for LULC map of 2020, and the result is 87.57%, and bankline shifting RMSE varies from 0.007 to 0.176. Therefore, the prediction output serves as the spatial guidelines for monitoring future trends of channel shift and land use planning management.


Model based prioritization of urban space for the development of municipal services in Chandernagore Municipal Corporation (CMC), India

December 2021

·

143 Reads

·

1 Citation

The present article wishes to supplement the proliferating urban competitiveness research by adding the role of urban services in providing leverage to these aspirations in smaller cities. A small city with its inability to cope with the largeness, agglomeration and proximity criteria of city competitiveness can witness growth through cultural production, consumption and cultural policy. And for that to happen, urban wellbeing is considered the main criteria, which can be accomplished by providing urban services. The present study engages with micro-level secondary data to understand the existing performance of municipal services in one of the colonial cities of eastern India. Methods include micro-level spatial analysis of data, Analytical Hierarchical Process (AHP); and primary survey of the stakeholders. It is followed by quantification of information in selected municipal services and spatial distribution of population in the study area through Geographic Information System (GIS). These methods and micro-zones have also assessed functional gaps of municipal services identified for decision making.


A global observational analysis to understand changes in air quality during exceptionally low anthropogenic emission conditions

December 2021

·

1,684 Reads

·

199 Citations

Environment International

·

·

Xavier Querol

·

[...]

·

Miguel Zavala

This global study, which has been coordinated by the World Meteorological Organization Global Atmospheric Watch (WMO/GAW) programme, aims to understand the behaviour of key air pollutant species during the COVID-19 pandemic period of exceptionally low emissions across the globe. We investigated the effects of the differences in both emissions and regional and local meteorology in 2020 compared with the period 2015–2019. By adopting a globally consistent approach, this comprehensive observational analysis focuses on changes in air quality in and around cities across the globe for the following air pollutants PM2.5, PM10, PMC (coarse fraction of PM), NO2, SO2, NOx, CO, O3 and the total gaseous oxidant (OX = NO2 + O3) during the pre-lockdown, partial lockdown, full lockdown and two relaxation periods spanning from January to September 2020. The analysis is based on in situ ground-based air quality observations at over 540 traffic, background and rural stations, from 63 cities and covering 25 countries over seven geographical regions of the world. Anomalies in the air pollutant concentrations (increases or decreases during 2020 periods compared to equivalent 2015–2019 periods) were calculated and the possible effects of meteorological conditions were analysed by computing anomalies from ERA5 reanalyses and local observations for these periods. We observed a positive correlation between the reductions in NO2 and NOx concentrations and peoples’ mobility for most cities. A correlation between PMC and mobility changes was also seen for some Asian and South American cities. A clear signal was not observed for other pollutants, suggesting that sources besides vehicular emissions also substantially contributed to the change in air quality. As a global and regional overview of the changes in ambient concentrations of key air quality species, we observed decreases of up to about 70% in mean NO2 and between 30% and 40% in mean PM2.5 concentrations over 2020 full lockdown compared to the same period in 2015–2019. However, PM2.5 exhibited complex signals, even within the same region, with increases in some Spanish cities, attributed mainly to the long-range transport of African dust and/or biomass burning (corroborated with the analysis of NO2/CO ratio). Some Chinese cities showed similar increases in PM2.5 during the lockdown periods, but in this case, it was likely due to secondary PM formation. Changes in O3 concentrations were highly heterogeneous, with no overall change or small increases (as in the case of Europe), and positive anomalies of 25% and 30% in East Asia and South America, respectively, with Colombia showing the largest positive anomaly of ~70%. The SO2 anomalies were negative for 2020 compared to 2015–2019 (between ~25 to 60%) for all regions. For CO, negative anomalies were observed for all regions with the largest decrease for South America of up to ~40%. The NO2/CO ratio indicated that specific sites (such as those in Spanish cities) were affected by biomass burning plumes, which outweighed the NO2 decrease due to the general reduction in mobility (ratio of ~60%). Analysis of the total oxidant (OX = NO2 + O3) showed that primary NO2 emissions at urban locations were greater than the O3 production, whereas at background sites, OX was mostly driven by the regional contributions rather than local NO2 and O3 concentrations. The present study clearly highlights the importance of meteorology and episodic contributions (e.g., from dust, domestic, agricultural biomass burning and crop fertilizing) when analysing air quality in and around cities even during large emissions reductions. There is still the need to better understand how the chemical responses of secondary pollutants to emission change under complex meteorological conditions, along with climate change and socio-economic drivers may affect future air quality. The implications for regional and global policies are also significant, as our study clearly indicates that PM2.5 concentrations would not likely meet the World Health Organization guidelines in many parts of the world, despite the drastic reductions in mobility. Consequently, revisions of air quality regulation (e.g., the Gothenburg Protocol) with more ambitious targets that are specific to the different regions of the world may well be required.


Proposing novel ensemble approach of particle swarm optimized and machine learning algorithms for drought vulnerability mapping in Jharkhand, India

October 2021

·

252 Reads

·

12 Citations

Drought, a natural and very complex climatic hazard, causes impacts on natural and socio-economic environments. This study aims to produce the drought vulnerability map (DVM) considering novel ensemble machine learning algorithms (MLAs) in Jharkhand, India. Forty, drought vulnerability determining factors under the categories of exposure, sensitivity, and adaptive capacity were used. Then, four machine learning and four novel ensemble approaches of particle swarm optimized (PSO) algorithms, named random forest (RF), PSO-RF, multi-layer perceptron (MLP), PSO-MLP, support vector regression (SVM), PSO-MLP, Bagging, and PSO-Bagging, were established for DVMs. The receiver operating characteristic curve (ROC), mean-absolute-error (MAE), root-mean-square-error (RMSE), precision, and K-index were utilized for judging the performance of novel ensemble MLAs. The obtained results show that the PSO-RF had the highest performance with an AUC of 0.874, followed by RF, PSO-MLP, PSO-Bagging, Bagging, MLP, PSO-SVM and SVM, respectively. Produced DVMs would be helpful for policy intervention to minimize drought vulnerability.


Citations (29)


... A greater drainage density suggested a greater possibility for runoff. Drainage density is another significant factor in flood occurrences, as higher drainage density leads to faster runoff and a higher likelihood of flooding (Saha, Gayen & Bayen, 2022 ...

Reference:

Flood risk assessment using GIS and remote sensing in Tsholotsho District, Matabeleland North in Zimbabwe
Deep learning algorithms to develop Flood susceptibility map in Data-Scarce and Ungauged River Basin in India

Stochastic Environmental Research and Risk Assessment

... Soil erodibility refers to the susceptibility of soil to erosion and is a critical indicator for assessing soil loss and implementing soil and water conservation measures [11,12]. It is influenced by various factors, including soil physicochemical properties, organic matter content, aggregate structure, soil texture, and infiltration capacity [13,14]. ...

Soil erodibility assessment of laterite dominant sub-basin watersheds in the humid tropical region of India
  • Citing Article
  • June 2022

CATENA

... erosion-accretion process, putting the inhabitants at risk (Thakur et al., 2012;Hasanuzzaman et al., 2022). Regional soil erosion rates and sediment transport to China's Lushi River Basin were greatly affected by minor land-use changes (Wang et al., 2012). ...

Spatial modeling of river bank shifting and associated LULC changes of the Kaljani River in Himalayan foothills

Stochastic Environmental Research and Risk Assessment

... Based on the theory of inter-governmental relationships and resource location, Zhou et al. established the inter-governmental coopetition measures indicators to evaluate the coordinated development level of the Pearl River Delta urban agglomeration . Haque took the development of the coopetition relationship of small cities in urban agglomerations as the research goal, built a municipal service performance model from the micro level, and evaluated the urban competitiveness of a colonial city in eastern India (Haque et al., 2021). Hu et al. constructed a promotion game model for local governments and analyzed the influence of coopetition among core cities in the Yangtze River Delta on urban development. ...

Model based prioritization of urban space for the development of municipal services in Chandernagore Municipal Corporation (CMC), India
  • Citing Article
  • December 2021

... An evaluation was performed with the co-active neuro-fuzzy inference system (CANFIS), multi-layer perceptron neural network (MLPNN), and multiple linear regression (MLR) to predict meteorological drought in the Uttarakhand region to assist in decision-making along with the preventative measures to cope with meteorological drought in the area (Rajan et al. 2020). Drought vulnerability in Jharkhand has been investigated using ensemble machine learning procedures, in conjunction with Exposure, Sensitivity, and Adaptivity aspects to minimise the negative consequences of drought (Saha et al. 2022a). A deep-learning algorithm was deployed to assess the drought susceptibility of Karnataka state for better management of water resources and land use . ...

Proposing novel ensemble approach of particle swarm optimized and machine learning algorithms for drought vulnerability mapping in Jharkhand, India
  • Citing Article
  • October 2021

... 113 114 If these measures are effective for PM 2.5 , PM 10 , NO 2 , CO and SO 2 , O 3 is resistant; 113 this is consistent with observations made during the COVID-19 confinement which showed a decrease in air pollutants except for O 3 which varies little or increases. [115][116][117][118][119][120][121][122][123][124][125] Nevertheless, these measures are the privilege of the major world sporting events, nearly exclusively the OPG, and are seldom applied to other events. International sports organisations, such as the World Athletics, have also started to address the issue and are planning ways to improve the quality of air at sporting events. ...

A global observational analysis to understand changes in air quality during exceptionally low anthropogenic emission conditions

Environment International

... Concurrently, vulnerability is a holistic measure encompassing elements of drought impact and resilience. Previous studies predominantly focused on the exposure index, delineating the spatial aspects of drought such as duration, frequency and intensity, primarily centred on meteorological drought (Liu et al. 2013;Murthy, Laxman, and Sesha Sai 2015;Saha et al. 2023;Saha, Gogoi, et al. 2021). Parameters like rainfall data, its characteristics, distribution patterns or indices like the SPI were commonly used for the exposure index in these studies (Das, Murthy, and Seshasai 2013;Liu et al. 2013). ...

Constructing the machine learning techniques based spatial drought vulnerability index in Karnataka state of India
  • Citing Article
  • June 2021

Journal of Cleaner Production

... Further, Breuer et al. (2020) highlighted that vehicles that use diesel contribute to the high emission of particulate matter. During the lockdown period, the anthropogenic origin is lesser with the closure of several sources, reducing the PM 10 level in India (Gayen et al., 2021). The findings are parallel with Orak and Ozdemir (2021), which clarified that PM 10 concentration has the lowest concentration in April 2020 in Turkey as a result of the lockdown due to less human mobility, and 67% of the cities had a lower average of PM 10 concentrations as compared to the previous 5-years. ...

COVID-19 induced lockdown and decreasing particulate matter (PM10): An empirical investigation of an Asian megacity

Urban Climate

... repeated cross-profiling [43,44,45,46,47,48], botanical evidences [38,49, [69,71,70]. The Geomorphological changes are very common natural processes which found in riverine systems [73]. ...

Channel dynamics and geomorphological adjustments of Kaljani River in Himalayan foothills

... Bar-On et al. (2020) examined the biology and properties of the SARS-CoV-2 virus that causes Covid-19 infection and the characteristics of a human host. According to statistical results, transmission of COVID-19 in environment via aerosols, droplets, fomites, and feces affected on the people's health (Von Seidlein et al., 2020;Corburn et al., 2020;Mishra et al., 2020;Tellier et al., 2019;Mao et al., 2020). In addition, control of overcrowding can significantly reduce virus transmission. ...

COVID‐19 in India transmits from the urban to the rural

International Journal of Health Planning and Management