Rainfall-induced landslides are widespread in Indonesia, particularly in West Java, where volcanic residual soils are typically stable but may become unstable during heavy rainfall. This study aims to back analyze the geotechnical factors contributing to the Cimanggung landslide in 2021. The methods applied in this study include site investigations, laboratory testing, and numerical modeling. We performed deterministic, coupled seepage-slope stability analysis and Monte Carlo probabilistic analysis to assess the slope performance prior to and after rainfall infiltration. The results reveal that the initial water level significantly affects slope stability, and heavy rainfall infiltration triggered the landslide’s initiation. The deep water table (over 20 m below ground level) maintains the slope stability, and increasing the water table to 16 m compromises its stability. Heavy rainfall infiltration reduces suction in the unsaturated zone, decreasing the shear strength and triggering landslides. The heavy rainfall infiltration did not penetrate deep enough to raise the water table; rather, poor urban drainage on the upper slope caused it. Rainfall infiltration caused wetting in the upper zone, weakening the slope and causing loss of support. It is recommended that effective drainage management and integrated slope monitoring be applied to mitigate landslide risks in this region.

Landslides represent a recurrent hazard in tropical mountain environments, where rapid urbanization and extreme rainfall amplify disaster risk. The Sentani region of Papua, Indonesia, is highly vulnerable, as demonstrated by the catastrophic debris flows of March 2019 that caused fatalities and widespread losses. This study developed high-resolution landslide susceptibility maps for Sentani using an ensemble machine learning framework. Three base learners—Random Forest, eXtreme Gradient Boosting (XGBoost), and CatBoost—were combined through a logistic regression meta-learner. Predictor redundancy was controlled using Pearson correlation and Variance Inflation Factor/Tolerance (VIF/TOL). The landslide inventory was constructed from multitemporal satellite imagery, integrating geological, topographic, hydrological, environmental, and seismic factors. Results showed that lithology, Slope Length and Steepness Factor (LS Factor), and earthquake density consistently dominated model predictions. The ensemble achieved the most balanced predictive performance, Area Under the Curve (AUC) > 0.96, and generated susceptibility maps that aligned closely with observed landslide occurrences. SHapley Additive Explanations (SHAP) analyses provided transparent, case-specific insights into the directional influence of key factors. Collectively, the findings highlight both the robustness and interpretability of ensemble learning for landslide susceptibility mapping, offering actionable evidence to support disaster preparedness, land-use planning, and sustainable development in Papua.