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

TL;DR

This paper introduces a Mamba-based multimodal network that combines blast-loading data with remote sensing images to enhance rapid structural damage assessment after explosions.

Contribution

It presents a novel multimodal network integrating physical blast data with remote sensing for improved damage assessment accuracy.

Findings

Significant performance improvement over existing methods on Beirut explosion data.

Effective integration of blast-loading information enhances damage detection.

Rapid assessment capability demonstrated in post-blast scenarios.

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