Summary
After severe wind events like tornadoes, it's important to understand how damaged buildings can be safely repaired and restored. The authors developed a new computer method that looks at photos and text reports about damaged buildings and connects the damage with what needs to be fixed, how long repairs might take, and how safe the buildings are. Their approach carefully tracks different sources of evidence and deals with missing or uncertain information, giving more trustworthy recommendations. They tested this method on real tornado-damaged homes and found it improves how well damage and recovery are understood compared to current techniques.
What this means in practice
- •For emergency response teams: Estimate building safety and recovery needs from incomplete disaster damage reports and images to guide rescue and repair efforts.
- •For insurance claim processors: Automate linking building damage evidence with repair actions and downtime estimates to speed damage evaluation after wind events.$Commercial implications: Enables insurance companies to provide faster, more accurate claims services by integrating multimodal evidence into damage and recovery assessments.
Abstract
Post-event building assessment requires linking observed physical damage to its consequences for safety, habitability, functionality, and recovery. Yet post-disaster evidence is often heterogeneous, incomplete, and distributed across images and reconnaissance reports, while recovery models typically require structured engineering inputs. This study develops a multimodal engineering Graph Retrieval-Augmented Generation (GraphRAG) framework that connects post-wind-event damage evidence to physical consequences, building-condition states, recovery actions, and downtime. Image- and text-based evidence is transformed into a provenance-preserving, component-level representation distinguishing confirmed damage, explicit negative evidence, unresolved conditions, and temporary measures. Graph-aligned retrieval combines comparable building scenarios with explicit engineering relationships, while compatibility, contradiction, evidence-precedence, and abstention mechanisms constrain inference under partial observability. Recovery actions are derived from supported damage-consequence relationships, and downtime uncertainty is propagated through an action-dependency network using Monte Carlo simulation. The framework is demonstrated for tornado-affected low-rise residential buildings using reconnaissance and image-based evidence. Comparisons with BaselineRAG and Structured Baseline RAG show improved agreement for key building-condition and recovery outcomes, together with traceable engineering reasoning and preserved evidence provenance. Ablation analyses demonstrate the contributions of engineering context, evidence safeguards, and graph-path traversal. The results support transparent, recovery-oriented assessment from incomplete multimodal post-event evidence.