Landslide Susceptibility Mapping Using Machine Learning: A Literature Survey

Landslide is a devastating natural disaster, causing loss of life and property. It likely to occur more frequently due increasing urbanization, deforestation, climate change. susceptibility mapping vital safeguard This article surveys machine learning (ML) models used for landslide understand the current trend by analyzing published articles based on ML models, causative factors (LCFs), study location, datasets, evaluation methods, model performance. Existing literature considered in this comprehensive survey systematically selected using ROSES protocol. The indicates growing interest field. choice LCFs depends data availability case location; China most studied area under receiver operating characteristic curve (AUC) best metric. Many have achieved an AUC value > 0.90, indicating high reliability map generated. paper also discusses recently developed hybrid, ensemble, deep (DL) mapping. Generally, DL outperform conventional models. Based survey, few recommendations future works which may help new researchers field are presented.