Quantifying human risk from rainfall‐induced landslides across different return periods: A case study of Ba To, Quang Ngai, Vietnam

Abstract Landslides, intensified by climate change, pose a growing threat to human life, yet studies on their direct human impact remain limited. This study introduces an advanced framework for assessing human risk from rainfall‐induced landslides, focusing on Ba To, a landslide‐prone district in Quang Ngai Province, Vietnam. The framework follows six key steps: (1) assessing landslide spatial probability using deep neural networks, (2) evaluating temporal probability with Monte Carlo simulation and infinite slope modelling, (3) estimating hazard by combining spatial and temporal probabilities, (4) analysing landslide propagation via Flow‐R software, (5) determining population density in building areas and (6) calculating human risk using a hybrid quantitative–semi‐quantitative approach. Each step was validated against real landslide data, confirming the model's reliability. The framework effectively quantifies human risk and estimates risk for different return periods, improving landslide risk assessment and aiding decision‐making in disaster management.