Seismic multi-hazard and impact estimation via causal inference from satellite imagery
Citation
Xu, S., Dimasaka, J., Wald, D. J., Noh, H. Y. (2022). Seismic multi-hazard and impact estimation via causal inference from satellite imagery. Nature Communications, 13: 7793. Link to paper
Abstract
Rapid post-earthquake reconnaissance is important for emergency responses and rehabilitation, by providing accurate and timely information about secondary hazards and impacts, including landslide, liquefaction, and building damage. Despite the extensive collection of geospatial data and satellite images, existing physics-based and data-driven methods suffer from low estimation performance, due to the complex and event-specific causal dependencies underlying the cascading processes of earthquake-triggered hazards and impacts. This study presents a rapid seismic multi-hazard and impact estimation system that leverages advanced statistical causal inference and remote sensing techniques. The framework provides accurate and high-resolution estimations on a regional scale by jointly inferring multiple hazards and building damage from satellite images through modeling their causal dependencies. A probabilistic graphical model explicitly represents the causal relationships between earthquakes, ground failures (landslides and liquefaction), and building damage. The framework integrates physics-based empirical models with data-driven approaches through a Bayesian network structure, enabling effective fusion of domain knowledge with observational data. Evaluation on multiple earthquake events demonstrates substantial improvements in estimation accuracy compared to existing methods, particularly for areas with complex cascading hazard processes.