Bayesian Mapping of Landslide Hazard

This lecture by the instructor provides an in-depth exploration of high-resolution Bayesian mapping of landslide hazard, focusing on unobserved trigger events. The content covers a brief history of landslide science, the Messina landslide disaster dataset, and a modeling framework based on Log-Gaussian Cox Processes. The lecture also delves into inference techniques using INLA, model extensions, and results from different model variations. The presentation emphasizes the importance of capturing unobserved triggers, such as rainfall intensity, in landslide hazard modeling.