GraphCSVAE: Graph Categorical Structured Variational Autoencoder for Spatiotemporal Auditing of Physical Vulnerability Towards Sustainable Post-Disaster Risk Reduction

2025-09-12

AI Summary

Global capacity for dynamic post-disaster physical vulnerability monitoring remains weak, hindering progress assessment under the UN Sendai Framework for Disaster Risk Reduction. While existing studies predominantly focus on hazard exposure modeling, spatiotemporal modeling of vulnerability—the critical risk component—remains severely underexplored. To address this gap, we propose GraphCSVAE, a novel framework integrating graph-structured representation learning with categorical variational inference. It incorporates a weakly supervised first-order transition matrix to enable interpretable, dynamic vulnerability modeling. The method jointly trains graph neural networks and variational autoencoders using time-series satellite remote sensing data fused with expert domain knowledge. Validated in cyclone-affected regions of Bangladesh and landslide-prone urban areas of Sierra Leone, GraphCSVAE accurately captures the spatiotemporal evolution of post-disaster vulnerability. It establishes a new paradigm for fine-grained, sustainable risk governance and delivers key technical support for operational disaster resilience planning.

Technology Category

• Reasoning under Uncertainty: Graphical Models
• Computer Vision: Remote Sensing / Geospatial AI
• Machine Learning: Graph-based Machine Learning

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies
• Search and Retrieval-Augmented AI: Vertical and domain-specific search

Abstract

In the aftermath of disasters, many institutions worldwide face challenges in continually monitoring changes in disaster risk, limiting the ability of key decision-makers to assess progress towards the UN Sendai Framework for Disaster Risk Reduction 2015-2030. While numerous efforts have substantially advanced the large-scale modeling of hazard and exposure through Earth observation and data-driven methods, progress remains limited in modeling another equally important yet challenging element of the risk equation: physical vulnerability. To address this gap, we introduce Graph Categorical Structured Variational Autoencoder (GraphCSVAE), a novel probabilistic data-driven framework for modeling physical vulnerability by integrating deep learning, graph representation, and categorical probabilistic inference, using time-series satellite-derived datasets and prior expert belief systems. We introduce a weakly supervised first-order transition matrix that reflects the changes in the spatiotemporal distribution of physical vulnerability in two disaster-stricken and socioeconomically disadvantaged areas: (1) the cyclone-impacted coastal Khurushkul community in Bangladesh and (2) the mudslide-affected city of Freetown in Sierra Leone. Our work reveals post-disaster regional dynamics in physical vulnerability, offering valuable insights into localized spatiotemporal auditing and sustainable strategies for post-disaster risk reduction.

Problem

• Modeling physical vulnerability for disaster risk reduction
• Integrating deep learning with graph representation for spatiotemporal auditing
• Addressing limited progress in physical vulnerability modeling post-disasters

Innovation

• GraphCSVAE probabilistic framework integrates deep learning
• Uses graph representation and categorical probabilistic inference
• Weakly supervised transition matrix models vulnerability changes