Hybrid Ensemble Machine Learning for Landslide Susceptibility Mapping and Management Planning in the Kamchik Pass, Uzbekistan

Abstract

Landslide susceptibility assessment is essential for maintaining resilient mountain transport corridors where slope failures can disrupt mobility, freight movement, and economic activity. This study evaluated standalone and hybrid machine-learning models for the Kamchik Pass corridor of Uzbekistan, which carries the A-373 Tashkent–Osh highway. Thirteen topographic, hydrological, geological, climatic, vegetation, and land-cover factors were integrated with a landslide inventory. K-nearest neighbours (KNN), Random Forest (RF), XGBoost, and artificial neural network (ANN) models were compared to three RF-based hybrids: RF + KNN, RF + XGBoost, and RF + ANN. Performance was assessed using confusion-matrix metrics and receiver operating characteristic area under the curve (ROC–AUC), together with variable-importance and class-area analyses. All predictors were retained because variance inflation factors remained below 3.3. Slope and elevation were the most consistent predictors across the standalone models. RF + KNN achieved the best performance, with an accuracy of 0.8429, kappa of 0.6857, sensitivity of 0.8857, specificity of 0.8000, and AUC of 0.88. Its map classified 16.94 km2, approximately 10.8% of the study area, as high or very high susceptibility. Compared to standalone RF, RF + KNN increased accuracy by 2.86 percentage points and AUC by 0.03, while sensitivity decreased from 0.9429 to 0.8857 and specificity increased from 0.6857 to 0.8000. Because these differences were obtained from a small point-level hold-out set without spatially independent validation, they are interpreted as descriptive rather than evidence of universal model superiority. The maps provide a first-pass susceptibility screening layer for subsequent field verification and asset-exposure analysis; they do not constitute an implemented infrastructure-risk assessment.