1. A total of 112 landslide locations were identified in the Jecheon-si region, South Korea, based on aerial photos, dronographs and Google Earth imagery. 2. GIS-based statistical models (i.e., FR, IV, CF and LR) were used for landslide susceptibility mapping. 3. The ROC curve, R-index, MAE, MSE, RMSE, and precision were used to assess the model's. 4. The LSI predicted using an integrated model exhibited good agreement with topographic and landslide characteristics.

To reduce the consequences of landslides due to rainfall, such as loss of life, economic losses, and disruption to daily living, this study describes the process of building a machine learning model which can help to estimate the volume of landslide material that can occur in a particular region, taking into account antecedent rainfall, soil characteristics, type of vegetation, etc. The findings can be useful for land use management, infrastructure design, and rainfall disaster management.

This study performed analysis on typhoon-induced coastal morphodynamics for the Mokpo coast. Wetland vegetation was severely impacted by Typhoon Soulik, with 87.35 % of shoreline transects experiencing seaward migration. This result highlights the fact that sediment resuspension controls the land alteration process over the typhoon period. The land accretion process dominated during the pre- to post-typhoon periods.

The prediction of the size of rainfall-induced debris in South Korea was analyzed. The model suitability was carried out and Random forest was the most suitable for the Size of debris prediction. The most contributing factor in the model was slope length and the most vulnerable region to higher frequency and severe debris was Gangwon province. The findings may be used for rainfall induced-debris prevention policies and post-disaster rehabilitation planning.