Browsing by Author "Chatterjee, Uday"

Now showing 1 - 4 of 4

Anthropogenic Drivers Induced Desertification Under Changing Climate
(Elsevier, 2023-12-17) Pal, Subodh Chandra; Chatterjee, Uday; Chakrabortty, Rabin; Roy, Paramita; Chowdhuri, Indrajit; Saha, Asish; Islam, Abu Reza Md. Towfiqul; Alam, Edris; Islam, Md Kamrul
A study of the extended desertification due to anthropogenic causes under climate change (CC) associated with its impact is presented here. Desertification, the main environmental issue, severely impacts agricultural output, causing poverty and economic instability in a nation like India. The regional distribution of desertification was determined using the RF and MaxEnt models. The western, central, and southern portions of the nation are very high, high, and moderately susceptible to desertification, respectively, according to the RF model. The MaxEnt model indicates that the western, central, and southern parts of the country exhibit a significant susceptibility to desertification, with the eastern parts also showing a moderate level of vulnerability. The remaining portion of this region, mainly in the north, east, and northeast, is particularly resistant to desertification. The outcome demonstrated that the country's desertification process had expanded from the west to the south. However, there are some spatial differences associated with the mentioned part of the country. This relevant information is crucial for decision maker of this country to take suitable remedies in regard to the reduction of the intensity of desertification.
Application of Bagging and Boosting Ensemble Machine Learning Techniques for Groundwater Potential Mapping in a Drought-prone Agriculture Region of Eastern India
(Springer, 2024-09-02) Halder, Krishnagopal; Srivastava, Amit Kumar; Ghosh, Anitabha; Nabik, Ranajit; Pan, Subrata; Chatterjee, Uday; Bisai, Dipak; Pal, Subodh Chandra; Zeng, Wenzhi; Ewert, Frank; Gaiser, Thomas; Pande, Chaitanya Baliram; Islam, Abu Reza Md. Towfiqul; Alam, Edris; Islam, Md Kamrul
Groundwater is a primary source of drinking water for billions worldwide. It plays a crucial role in irrigation, domestic, and industrial uses, and significantly contributes to drought resilience in various regions. However, excessive groundwater discharge has left many areas vulnerable to potable water shortages. Therefore, assessing groundwater potential zones (GWPZ) is essential for implementing sustainable management practices to ensure the availability of groundwater for present and future generations. This study aims to delineate areas with high groundwater potential in the Bankura district of West Bengal using four machine learning methods: Random Forest (RF), Adaptive Boosting (AdaBoost), Extreme Gradient Boosting (XGBoost), and Voting Ensemble (VE). The models used 161 data points, comprising 70% of the training dataset, to identify significant correlations between the presence and absence of groundwater in the region. Among the methods, Random Forest (RF) and Extreme Gradient Boosting (XGBoost) proved to be the most effective in mapping groundwater potential, suggesting their applicability in other regions with similar hydrogeological conditions. The performance metrics for RF are very good with a precision of 0.919, recall of 0.971, F1-score of 0.944, and accuracy of 0.943. This indicates a strong capability to accurately predict groundwater zones with minimal false positives and negatives. Adaptive Boosting (AdaBoost) demonstrated comparable performance across all metrics (precision: 0.919, recall: 0.971, F1-score: 0.944, accuracy: 0.943), highlighting its effectiveness in predicting groundwater potential areas accurately; whereas, Extreme Gradient Boosting (XGBoost) outperformed the other models slightly, with higher values in all metrics: precision (0.944), recall (0.971), F1-score (0.958), and accuracy (0.957), suggesting a more refined model performance. The Voting Ensemble (VE) approach also showed enhanced performance, mirroring XGBoost's metrics (precision: 0.944, recall: 0.971, F1-score: 0.958, accuracy: 0.957). This indicates that combining the strengths of individual models leads to better predictions. The groundwater potentiality zoning across the Bankura district varied significantly, with areas of very low potentiality accounting for 41.81% and very high potentiality at 24.35%. The uncertainty in predictions ranged from 0.0 to 0.75 across the study area, reflecting the variability in groundwater availability and the need for targeted management strategies. In summary, this study highlights the critical need for assessing and managing groundwater resources effectively using advanced machine learning techniques. The findings provide a foundation for better groundwater management practices, ensuring sustainable use and conservation in Bankura district and beyond.
Assessment of groundwater potential zones in data-scarce regions using GIS-based multicriteria decision making approach
(Scopus, 2024-02-12) Dandapat, Kishor; Chatterjee, Uday; Das, Sandipan; Patraa, Arpita; Manna, Harekrishna; Ghosh, Anitabha
Groundwater is an essential natural resource that sustains numerous ecological systems and human lifestyles. The Jhargram district is facing persistent groundwater development issues, requiring comprehensive monitoring and planning, as most farmers heavily rely on groundwater for crop production. The groundwater potential zone of the Jhargram district was classified into five classes, viz., very high (5.82%), high (50.81%), moderate (30.33%), low (13.01%), and very low (0.03%), zones, respectively. The results were assessed for validity using ROC curves, which demonstrated an accuracy rate of 80.4%. The calculation of the AUC was performed in order to assess the overall accuracy of the predicted GWPZ. The GWPZ map is crucial for implementing artificial recharge structures like percolation ponds, bunds and trenching in semi-arid regions. It aids in developing sustainable groundwater management policies, mitigating drought, climate change, and water scarcity, and aiding farmers, regional planners, policy-makers, climate change experts, and local governments.
SAR-driven flood inventory and multi-factor ensemble susceptibility modelling using machine learning frameworks
(Scopus, 2024-10-16) Halder, Krishnagopal; Ghosh, Anitabha; Srivastava, Amit Kumar; Palf, Subodh Chandra; Chatterjee, Uday; Bisai, Dipak; Ewertd, Frank; Gaiserd, Thomas; Islam, Abu Reza Md. Towfiqul; Alamj, Edris; Islam, Md Kamrul
Climate change has substantially increased both the occurrenceand intensity of flood events, particularly in the Indian subcontin-ent, exacerbating threats to human populations and economicinfrastructure. The present research employed novel ML models—LR, SVM, RF, XGBoost, DNN, and Stacking Ensemble—developedin the Python environment and leveraged 18 flood-influencingfactors to delineate flood-prone areas with precision. A compre-hensive flood inventory, obtained from Sentinel-1 SyntheticAperture Radar (SAR) data using the Google Earth Engine (GEE)platform, provided empirical data for entire model training andvalidation. Model performance was assessed using precision,recall, F1-score, accuracy, and ROC-AUC metrics. The results high-lighted Stacking Ensemble’s superior predictive ability (0.965), fol-lowed closely by, XGBoost (0.934), DNN (0.929), RF (0.925), LR(0.921), and SVM (0.920) respectively, establishing the feasibility ofML applications in disaster management. The maps depicting sus-ceptibility to flooding generated by the current research provideactionable insights for decision-makers, city planners, and author-ities responsible for disaster management, guiding infrastructuraland community resilience enhancements against flood risks