Search

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. [ABSTRACT FROM AUTHOR]

Climate change significantly challenges smallholder mixed crop-livestock (MCL) systems in sub-Saharan Africa (SSA), affecting food and feed production. This study enhances the SIMPLACE modeling framework by incorporating crop-vegetation-livestock models, which contribute to the development of sustainable agricultural practices in response to climate change. Applying such a framework in a domain in West Africa (786,500 km2) allowed us to estimate the changes in crop (Maize, Millet, and Sorghum) yield, grass biomass, livestock numbers, and greenhouse gas emission in response to future climate scenarios. We demonstrate that this framework accurately estimated the key components of the domain for the past (1981–2005) and enables us to project their future changes using dynamically downscaled Global Circulation Model (GCM) projections (2020–2050). The results demonstrate that in the future, the northern part of the study area will likely experience a significant decline in crop biomass (up to -56%) and grass biomass (up to -57%) production leading to a decrease in livestock numbers (up to -43%). Consequently, this will impact total emissions (up to -47% CH4) and decrease of -41% in milk production, and − 47% in meat production concentrated in the Sahelian zone. Whereas, in pockets of the Sudanian zone, an increase in livestock population and CH4 emission of about + 24% has been estimated, indicating that variability in climate change impact is amplifying with no consistent pattern evident across the study domain. [ABSTRACT FROM AUTHOR]