Shrinwantu Raha

Drought is a recurring hydro-climatic hazard that heavily alters agricultural productivity and depletes water resources. This research investigates the spatiotemporal characteristics of drought in Jharkhand, India, using the Standardized Precipitation Evapotranspiration Index (SPEI) derived from long-term climatic records (1951–2025) acquired from the India Meteorological Department. This research evaluated key drought characteristics: frequency, duration, magnitude, intensity, return period and trend. Trend-Free Pre-Whitening was applied prior to Mann–Kendall and Sen’s slope analyses to ensure robust trend detection, and the Pettitt test was used to identify significant change points in regional drought dynamics. The results identified a significant hydro-climatic transition during 2008–2010, followed by intensified and more persistent drought conditions across Jharkhand. Post-change-point analysis revealed a positive upward trend in drought intensity, ranging from 121.4% to 275.9% in the northeastern part of the region, and an increase in average drought duration ranging from 91.2% to 237.5% in the eastern pockets with droughts of around 4.5 months in the northeast. The changes in drought magnitude were spatially variable, ranging from −72.2% to +150.6% with the greatest positive changes in the northeastern region. The drought frequency increased significantly in the central districts and the drought return period fluctuates overall by around −80.46% to 17% in the Jharkhand state, that is more frequent drought recurrence. Overall, the trend results showed an increasing drought trends especially apparent in the northeastern and northwestern portions, and decreasing drought tendencies in parts of the central region. The Sen’s slope analysis also revealed spatial differences in drought evolution with slopes from around −0.0134 to +0.058. Homogeneity tests (Student’s t-test, Wilcoxon rank-sum test, and F-test) revealed significant changes in mean and distribution at several stations after the identified change point, while variance remained statistically homogeneous across all stations. These findings provide valuable insights for drought monitoring.

Precise demarcation of ecotourism-suitable zones is essential for achieving sustainable development and guiding infrastructure investment across regions. This research presents a machine learning approach to assess and demarcate ecotourism suitability zones (ESZs) in Odisha using two machine learning ensembles: CatBoost and Model Averaged Neural Network (MA-NNET). The classification framework divided the state's landscape into four tourism potential categories (Very High, High, Moderate, and Low) based on several physical and social criteria. Both models achieved comparable accuracy, precision, recall, F1-score and AUC-ROC values with the training and test sets; however, CatBoost scored a marginally better consistency between training and testing performance. CatBoost spatial output revealed that more than half the area of the state has a high and very high potential as ecotourism zones. Approximately 31.44% of the total area was categorized under the moderate ecotourism potential class, and the remaining 13.31% of area was classified under the low ecotourism potentials. SHAP analysis revealed that relief and relative relief are the most influential features driving model decisions in both MA-NNET and CatBoost. The study highlights the usefulness of machine learning algorithms in regional tourism planning and provides practical results to the development of data-driven policies and sustainable sectoral development (specifically SDG 8 and SDG 11) in Odisha.

North Bengal, a region in the Indian state of West Bengal, possesses abundant water resources and a growing pond-based fishery sector that plays a vital role in rural livelihoods and food security. Despite its potential, disparities in production performance and limited adoption of scientific practices have raised concerns about efficiency. In this study, the technical efficiency of pond fisheries in two districts of North Bengal has been assessed using the Charnes–Cooper–Rhodes (CCR) and Banker–Charnes–Cooper (BCC) DEA models. Findings reveal that the average technical efficiency of the sampled ponds is 74% under the BCC model, indicating a potential 27% improvement in technical efficiency if fish farming operates under variable returns to scale (VRS). Furthermore, over one-third (35.38%) of pond fishery farmers are classified as fully technically efficient within the BCC model, underscoring that a significant portion already operates at optimal efficiency. To validate the robustness of these findings, advanced machine learning techniques, Principal Component Analysis (PCA) and t-distributed Stochastic Neighbor Embedding (t-SNE), have also been employed, confirming the consistency and reliability of the results. This suggests a pressing need for governmental intervention, particularly from the Department of Fisheries, to implement targeted measures aimed at enhancing productivity and boosting technical efficiency among pond fishery farmers.