Globally, soil erosion is a significant problem contributing to nutrient loss, water quality degradation, and sand accumulation in water bodies. Currently, various climate factors are affecting the natural resources entire worldwide. Agricultural intensification, soil degradation, and some other human impacts all contribute to soil erosion, which is a significant issue. Management and conservation efforts in a watershed can benefit from a soil erosion study. Modeling can establish a scientific and accurate method to calculate sediment output and soil erosion below a variety of circumstances. The measured soil loss tolerance was compared to the risk of soil erosion (T value).In this study, GIS and remote sensing techniques have been integrated with the Revised Universal Soil Loss Equation (RUSLE) model to estimate soil loss in the Mayurakshi river basin of eastern India. To determine soil erosion-prone areas, rainfall, land use, and land cover maps, as well as a digital elevation model (DEM), were used as input. The annual soil loss in the basin area is estimated to be 4,629,714.8 tons. Accordingly, the study basin was categorized into five soil loss severity classes: very low (40.92%), low (49%), moderate (6.5%), high (2.4%) and very high (1.18%) risk classes. Soil erosion rates ranged from very slight to slight throughout the majority of the region. The section of the basin’s lower plain has been discovered to be least affected by soil loss. The results of study area can be helpful to conservation of soil management practices and watershed development program in the basin area.

Background: Peri-urbanization, the expansion of large metropolitan centers into adjacent peri-urban regions, is a growing concern due to land scarcity and escalating housing costs. These zones, a blend of rural and urban features, blur the line between urban and rural areas, creating new landscapes. This study examines historical, present, and potential growth trends in the peri-urban area surrounding Durgapur Municipal Corporation (DMC). Analytical techniques and spatial metrics are used to track development intensity changes over time, including built-up density, Shannon’s entropy, Landscape expansion index, Average Weighted Mean Expansion Index, Annual Built-Up Expansion Rate, Built-Up Expansion Intensity Index, and Built-Up Expansion Difference Index. Landscape indices like Patch Density, Edge Density, Landscape Shape Index, Largest Patch Index, Ratio of Open Space, and Area Weighted Mean Patch Fractal are used to understand fragmentation, connectivity, and spatial relationships. The Logistic Regression Model (LRM) is used to identify influencing factors and CA-Markov modeling for future built-up areas. Results: Between 1991 and 2001, built-up area in the region increased significantly, primarily due to urban development near industrial zones, roadways, and mining areas. The growth was primarily concentrated in the western sector and near National Highway-2 (NH-2). Urban sprawl was a continuous trend, with the highest built-up density in the South-South-East (SSE) direction from 1991 to 2011. Additionally, a key determinant of built-up development was the distance to the city core. By 2031, the built-up area is expected to concentrate in the western and southeast regions, reaching 177.90 km². Conclusions: This expansion is attributed to urban development near industrial zones, roadways, mining areas, and other infrastructure. The study identifies distance to the city center as a significant influencing factor for built-up development. The results emphasize the need for inclusive urban planning methods prioritizing sustainable development principles and prudent resource management for future growth and efficient management in the DMC’s peri-urban area.

Landslides pose significant threats to ecosystems, lives, and economies, particularly in the geologically fragile Sub-Himalayan region of West Bengal, India. This study enhances landslide susceptibility prediction by developing an ensemble framework integrating Recursive Feature Elimination (RFE) with meta-learning techniques. Seven advanced machine learning models- Logistic Regression (LR), Support Vector Machine (SVM), Random Forest (RF), Extremely Randomized Trees (ET), Gradient Boosting (GB), Extreme Gradient Boosting (XGBoost), and a Meta Classifier (MC) were applied using Remote Sensing and GIS tools to identify key landslide-conditioning factors and classify susceptibility zones. Model performance was assessed through metrics such as accuracy, precision, recall, F1 score, and AUC of the ROC curve. Among the models, the Meta Classifier (MC) achieved the highest accuracy (0.956) and AUC (0.987), demonstrating superior predictive ability. Gradient Boosting (GB), XGBoost, and RF also performed well, with accuracies of 0.943 and AUC values of 0.987 (GB and XGBoost) and 0.983 (RF). Extremely Randomized Trees (ET) exhibited the highest accuracy (0.946) among individual models and an AUC of 0.985. SVM and LR, while slightly less accurate (0.941 and 0.860, respectively), provided valuable insights, with SVM achieving an AUC of 0.972 and LR achieving 0.935. The models effectively delineated landslide susceptibility into five zones (very low, low, moderate, high, and very high), with high and very high susceptibility zones concentrated in Darjeeling and Kalimpong subdivisions. These zones are influenced by intense rainfall, unstable geological structures, and anthropogenic activities like deforestation and urbanization. Notably, ET, RF, GB, and XGBoost demonstrated efficiency in feature selection, requiring fewer input variables while maintaining high performance. This study establishes a benchmark for landslide susceptibility mapping, providing a scalable and adaptable framework for geospatial hazard prediction. The findings hold significant implications for land-use planning, disaster management, and environmental conservation in vulnerable regions worldwide.