Multi-resolution Score-Based Variational Graphical Diffusion for Causal Disaster System Modeling and Inference
This work addresses the problem of accurate prediction in disaster systems for researchers and practitioners, offering a novel method that integrates multi-resolution data and causal dependencies, though it appears incremental as it builds on existing diffusion and graphical modeling techniques.
The paper tackles the challenge of modeling complex systems with intricate causal dependencies by introducing Temporal-SVGDM, a score-based variational graphical diffusion model for multi-resolution observations, which improves prediction accuracy and causal understanding in real-world disaster scenarios like earthquakes, hurricanes, and wildfires.
Complex systems with intricate causal dependencies challenge accurate prediction. Effective modeling requires precise physical process representation, integration of interdependent factors, and incorporation of multi-resolution observational data. These systems manifest in both static scenarios with instantaneous causal chains and temporal scenarios with evolving dynamics, complicating modeling efforts. Current methods struggle to simultaneously handle varying resolutions, capture physical relationships, model causal dependencies, and incorporate temporal dynamics, especially with inconsistently sampled data from diverse sources. We introduce Temporal-SVGDM: Score-based Variational Graphical Diffusion Model for Multi-resolution observations. Our framework constructs individual SDEs for each variable at its native resolution, then couples these SDEs through a causal score mechanism where parent nodes inform child nodes' evolution. This enables unified modeling of both immediate causal effects in static scenarios and evolving dependencies in temporal scenarios. In temporal models, state representations are processed through a sequence prediction model to predict future states based on historical patterns and causal relationships. Experiments on real-world datasets demonstrate improved prediction accuracy and causal understanding compared to existing methods, with robust performance under varying levels of background knowledge. Our model exhibits graceful degradation across different disaster types, successfully handling both static earthquake scenarios and temporal hurricane and wildfire scenarios, while maintaining superior performance even with limited data.