A Model for Complementing Landslide Types (Cliff Type) Missing from Areal Disaster Inventories Based on Landslide Conditioning Factors for Earthquake-Unaffected Regions

Landslides pose a significant hazard to human activities, often causing substantial damage to human lives and infrastructure. Countermeasures are measures taken to prevent or mitigate the effects of landslides. To implement suitable structural countermeasures, the type of landslide is essential. This study aims to develop a model for earthquake-unaffected regions to identify cliff-type landslides from a landslide inventory where the type is not specified . The model utilizes Forest-based and Boosted Classification and Regression tools within ArcGIS Pro software.21 LCF and 167 LS points and 167 non-LS points were used to train the model referring Tokushima Prefecture. Trained Model demonstrated an accuracy of 0.84, a sensitivity of 0.84, MCC of 0.68, F1 score of 0.84, a mean of 0.80, a median of 0.80 and a standard deviation of 0.03. This is a good indication of the model's overall the reliability. Predictions were made to Kegalle district in Sri Lanka. Validation was made referring the recently modified inventory incidents with landslide type, which showed 80.1% matched accurately. Model was used to predict cliff type LS in the inventory before modifying in KD. This model aid in identifying cliff-type landslides from inventories and to prevent future occurrences in applying appropriate countermeasures.