A Transferable Machine Learning Approach for Identifying Rainfall-Induced Cliff-Type (Shallow) Landslides in Seismic and Non-Seismic Regions

Precise classification of landslide types is essential for effective hazard mitigation; however, many existing landslide inventories lack type-specific information, limiting their applicability in risk management. This study presents a transferable machine learning framework to identify rainfall-induced cliff-type (shallow) landslides from unclassified inventories across seismic and non-seismic environments. Using the Forest-based and Boosted Classification and Regression (FBCR) tool in ArcGIS Pro 3.5, two models were developed using 25 landslide conditioning factors (LCFs) from Wakayama and Tokushima Prefectures, Japan. Both models achieved strong training performance, with accuracy and sensitivity exceeding 0.84, F1 scores of 0.84–0.85, and Matthews correlation coefficients (MCC) of 0.68–0.71. Transferability was assessed by applying both models to the Kegalle District, Sri Lanka, where the non-seismic model achieved approximately 80% spatial validation accuracy. Variable importance analysis revealed that rainfall consistently ranked as a high-influence LCF in both models—second in the seismic model and seventh in the non-seismic model—confirming its role as a primary conditioning factor for cliff-type shallow landslide susceptibility regardless of tectonic setting. The proposed framework provides a practical approach for complementing missing landslide type information in existing inventories, improving hazard zonation and supporting risk-informed planning in diverse geological and climatic settings.