Normalizing flow-based deep variational Bayesian network for seismic multi-hazards and impacts estimation from InSAR imagery
This addresses the need for rapid and accurate multi-hazard estimation for post-disaster response, representing a domain-specific advancement in geospatial AI.
The paper tackles the problem of low accuracy in predicting multiple seismic hazards and impacts from noisy InSAR imagery by introducing a novel stochastic variational inference method with normalizing flows, achieving joint approximation of posteriors for improved estimation.
Onsite disasters like earthquakes can trigger cascading hazards and impacts, such as landslides and infrastructure damage, leading to catastrophic losses; thus, rapid and accurate estimates are crucial for timely and effective post-disaster responses. Interferometric Synthetic aperture radar (InSAR) data is important in providing high-resolution onsite information for rapid hazard estimation. Most recent methods using InSAR imagery signals predict a single type of hazard and thus often suffer low accuracy due to noisy and complex signals induced by co-located hazards, impacts, and irrelevant environmental changes (e.g., vegetation changes, human activities). We introduce a novel stochastic variational inference with normalizing flows derived to jointly approximate posteriors of multiple unobserved hazards and impacts from noisy InSAR imagery.