A Mamba-Based Multimodal Network for Multiscale Blast-Induced Rapid Structural Damage Assessment

2026-04-13

AI Summary

This study addresses the limitations of conventional post-disaster structural damage assessment, which relies on manual inspections hindered by accessibility constraints, safety hazards, and delays, as well as existing remote sensing approaches that lack explicit modeling of blast load physics and require extensive labeled data. To overcome these challenges, this work proposes a multimodal network based on the Mamba state space model that, for the first time, integrates multiscale physical characteristics of blast loads with optical remote sensing imagery to construct a lightweight, efficient few-shot damage assessment framework. Experimental results on data from the 2020 Beirut explosion demonstrate that the proposed method significantly outperforms current state-of-the-art approaches, confirming its effectiveness and generalization capability.

Technology Category

• Computer Vision: Multi-modal Vision
• Machine Learning: Multimodal Learning
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Web Mining and Content Analysis: Mining multimedia, multimodal, multilingual, cross-lingual Web data
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs

Abstract

Accurate and rapid structural damage assessment (SDA) is crucial for post-disaster management, helping responders prioritise resources, plan rescues, and support recovery. Traditional field inspections, though precise, are limited by accessibility, safety risks, and time constraints, especially after large explosions. Machine learning with remote sensing has emerged as a scalable solution for rapid SDA, with Mamba-based networks achieving state-of-the-art performance. However, these methods often require extensive training and large datasets, limiting real-world applicability. Moreover, they fail to incorporate key physical characteristics of blast loading for SDA. To overcome these challenges, we propose a Mamba-based multimodal network for rapid SDA that integrates multi-scale blast-loading information with optical remote sensing images. Evaluated on the 2020 Beirut explosion, our method significantly improves performance over state-of-the-art approaches. Code is available at: https://github.com/IMPACTSquad/Blast-Mamba

Problem

• structural damage assessment
• blast-induced damage
• remote sensing
• multimodal learning
• Mamba-based networks

Innovation

• Mamba-based network
• multimodal fusion
• blast-induced damage assessment
• multiscale blast loading
• remote sensing