A Multimodal Engineering GraphRAG Framework for Post-Wind-Event Building Assessment and Recovery Inference
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.
Related
- The Deep Learning Halo Definer: A Multimodal Framework for Halo Mass and Gas Fraction Inference on Galaxy Groups and Clusters
- Towards Intelligent Educational Assessment: A Multimodal NLP Framework for Automated Feedback Generation and Personalized Learning Analytics
- Random-mapped intensity optical neural network: all-optical two-layer computing for multimodal optical-field inference
- Entanglement Meets Reality: A Network Engineering Assessment and Forecast of Rackable Entanglement Sources
- Multimodal and Multiscale Interrogation of a Mechanically Tough Glass Forming Copper-Based Metal-Organic Framework
BibTeX
@misc{mirfakhar2026multimodal,
title = {{A Multimodal Engineering GraphRAG Framework for Post-Wind-Event Building Assessment and Recovery Inference}},
author = {Seyedeh Fatemeh Mirfakhar and Reda Snaiki and Rocio Lilen Segura},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.28216},
eprint = {2610.28216},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.28216},
note = {CC BY-NC-ND 4.0},
}
RIS
TY - UNPB
TI - A Multimodal Engineering GraphRAG Framework for Post-Wind-Event Building Assessment and Recovery Inference
AU - Seyedeh Fatemeh Mirfakhar
AU - Reda Snaiki
AU - Rocio Lilen Segura
PY - 2026
DA - 2026/10/20
PB - arXiv
DO - 10.48550/arxiv.2610.28216
UR - https://arxiv.org/abs/2610.28216
AB - 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.
ER -