Spatially-Heterogeneous Causal Bayesian Networks for Seismic Multi-Hazard Estimation: A Variational Approach with Gaussian Processes and Normalizing Flows

2025-04-05

AI Summary

Traditional models for post-earthquake multi-hazard coupling assessment suffer from fixed parameters and limited capability of remote sensing to discriminate co-occurring hazards. To address these limitations, this paper proposes a Spatially Heterogeneous Causal Bayesian Network (SH-CBN). SH-CBN is the first framework to explicitly embed geographical spatial heterogeneity into the causal structure, employing location-specific parameters to characterize how geology and topography modulate hazard-generation mechanisms. Furthermore, it introduces a novel variational paradigm integrating Gaussian processes with normalizing flows to enable location-adaptive joint probabilistic inference. Evaluated on three real-world earthquake events, SH-CBN achieves up to a 35.2% improvement in AUC, significantly enhancing both spatial resolution and joint prediction accuracy for landslides, liquefaction, and building damage.

Technology Category

• Reasoning under Uncertainty: Relational Probabilistic Models
• Machine Learning: Causal Learning
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Web Mining and Content Analysis: Models for Web evolution

Abstract

Post-earthquake hazard and impact estimation are critical for effective disaster response, yet current approaches face significant limitations. Traditional models employ fixed parameters regardless of geographical context, misrepresenting how seismic effects vary across diverse landscapes, while remote sensing technologies struggle to distinguish between co-located hazards. We address these challenges with a spatially-aware causal Bayesian network that decouples co-located hazards by modeling their causal relationships with location-specific parameters. Our framework integrates sensing observations, latent variables, and spatial heterogeneity through a novel combination of Gaussian Processes with normalizing flows, enabling us to capture how same earthquake produces different effects across varied geological and topographical features. Evaluations across three earthquakes demonstrate Spatial-VCBN achieves Area Under the Curve (AUC) improvements of up to 35.2% over existing methods. These results highlight the critical importance of modeling spatial heterogeneity in causal mechanisms for accurate disaster assessment, with direct implications for improving emergency response resource allocation.

Problem

• Modeling spatially-varying seismic hazards accurately
• Decoupling co-located hazards using causal relationships
• Improving disaster assessment with spatial heterogeneity

Innovation

• Spatially-aware causal Bayesian network for hazards
• Gaussian Processes with normalizing flows integration
• Location-specific parameters for seismic effects