Bayesian updating of seismic ground failure estimates via causal graphical models and satellite imagery

Earthquake-induced secondary ground failure hazards, such as liquefaction and landslides, result in catastrophic building and infrastructure damage as well as human fatalities. To facilitate emergency responses and mitigate losses, the U.S. Geological Survey provides a rapid hazard estimation system for earthquake-triggered landslides and liquefaction using geospatial susceptibility proxies and ShakeMap ground motion estimates. However, the resolution and accuracy of these models are often limited by coarse-granularity and large uncertainties of available geospatial features provided at a regional scale. Recently, with the advancement of remote sensing technologies, synthetic aperture radar (SAR) images are captured and analyzed to obtain a rapid estimate of earthquake-induced correlation changes between pre- and post-event images. These correlation changes indicate ground failures and building damage t, showing the potential to provide supplementary information for rapid hazard and loss estimation. However, the exact causes of changes in satellite images are not directly ascertained by the DPM alone. For example, changes could be due to building damage, landslides, liquefaction, noise or any combination thereof. More importantly, the occurrence and intensity of landslides, liquefaction, and building damages are spatially correlated, which makes it yet more challenging to distinguish the sources of any such changes.

In this study, we develop a generalized causal graph-based Bayesian Network that models the physical interdependencies between geospatial features, seismic ground failures and building damage, as well as DPMs. Geospatial features provide physical insights for estimating ground failure occurrence while DPMs contain event-specific surface change observations. This physics-informed causal graph incorporate these variables with complex physical relationships in one holistic Bayesian updating scheme to effectively fuse information from both geospatial models and remote sensing data. This framework is scalable and flexible enough to deal with highly complex multi-hazard combinations. We then develop a stochastic variational inference algorithm to jointly update the intractable posterior probabilities of unobserved landslides, liquefaction, and building damage at different locations efficiently. In addition, a local graphical model pruning algorithm is presented to reduce the computational cost of large-scale seismic ground failure estimation. We apply this framework to September 2018 Hokkaido Iburi-Tobu, Japan (M6.6) earthquake and January 2020 Southwest Puerto Rico (M6.4) earthquake to evaluate the performance of our algorithm