Regional Hazard Assessment of Rainfall–Induced Landslide Considering Human Activity Intensity

Landslide hazard assessment denotes the systematic evaluation of the likelihood of landslide occurrence within a defined temporal and spatial context. Rainfall-induced landslide hazard assessment methods often fail to adequately consider the impacts of human activities, resulting in assessments that lack sufficient accuracy to meet practical demands. This study proposes an innovative dynamic assessment model that integrates both environmental factors and triggering factors, enabling regional hazard evaluations that account for the dual spatial constraints imposed by slopes and hazard-bearing bodies. The study proposes an objective estimation model for quantifying human activity intensity, utilizing the Criteria Importance Through Intercriteria Correlation (CRITIC) method and the Entropy Weight Method (EWM). Subsequently, random forest and Transformer models were employed to perform a progressive assessment of landslide susceptibility and hazard. Specifically, the dynamic assessment of rainfall-induced landslide hazard incorporated human activity intensity and rainfall characteristics as key triggering factors. The case study carried out in Zhenyuan County indicates that the model substantially improves and significantly increases the accuracy of disaster warnings and reduces the required hazard assessment area by approximately 40.6%, offering a targeted and valuable reference for early warning systems and decision-making of rainfall-induced landslides.