Addressing overfitting and overestimation challenges in landslide susceptibility modeling: a case study of Penang Island, Malaysia

In the realm of landslide susceptibility prediction, the challenge of overfitting and overestimation has persisted despite various modeling attempts. This study aims to elevate the predictive capabilities of the Extreme Gradient Boosting (XGBoost) and Random Forest (RF) models for landslide susceptibility assessment through the innovative application of Bayesian Optimization (BO). Using data from Penang Island in Malaysia, we comprehensively incorporated topographical, hydrological, human, and environmental factors influencing landslides. Leveraging Geographic Information System (GIS) tools, we meticulously constructed spatial databases encompassing all pertinent landslide conditioning elements. Our findings unveil the remarkable performance of the optimized XGBoost model, achieving an astounding 100.0% Success Rate (SR) and an impressive 97.1% Prediction Rate (PR). In comparison, the optimized RF model achieved an SR of 99.7% and a PR of 96.3%, while the stacked models followed closely with an SR of 96.8% and a PR of 95.6%. These conclusive results underscore the transformative potential of addressing overfitting and overestimation challenges through the strategic combination of stacking and hyperparameter optimization. The improved accuracy of these algorithms bears immense significance, extending to applications in site selection, engineering structure health monitoring, and disaster mitigation, thus elevating the importance of Landslide Susceptibility Maps (LSMs) in safeguarding communities and infrastructure.