Adaptive Sampling for Automated Post-Disaster Rapid Damage Assessment via Level-Set Cost-Aware Bayesian Optimization

2026-08-03

AI Summary

This study addresses the limitations of traditional post-disaster damage assessment, which relies on static, labor-intensive data collection that is costly and ill-suited to dynamic environments. The authors propose an adaptive sampling framework that uniquely integrates level set estimation with cost-aware Bayesian optimization to guide unmanned aerial vehicles (UAVs) in autonomously targeting the most informative regions for data acquisition. This approach enables real-time updating of geospatial damage estimates by actively tracking damage boundaries. Validated on both synthetic datasets and high-fidelity R2D disaster simulations, the method rapidly reconstructs damage maps with precise boundary delineation, significantly reducing predictive uncertainty while minimizing operational costs—thereby supporting efficient and responsive emergency management.

Abstract

Natural disasters frequently inflict severe damage to the built environment, which demands a rapid, reliable, and cost-effective damage assessment for emergency response. However, traditional methods for post-disaster damage assessment often rely on static, labor-intensive data collection strategies that can be prohibitively expensive and struggle to adapt to dynamic post-disaster conditions. In this study, we propose a cost-aware Bayesian optimization framework combined with level-set estimation that continuously guides autonomous data collectors, e.g., an unmanned aerial vehicle (UAV), toward the most informative regions. By dynamically updating damage estimates across different geographic zones, our approach systematically reduces uncertainty while minimizing operational costs. The proposed framework is first validated using a controlled synthetic toy study, demonstrating the agent's ability to efficiently trace damage boundaries, recover the underlying damage map, and rapidly reduce predictive uncertainty. Furthermore, the approach is evaluated using high-fidelity disaster data generated by the Regional Resilience Determination (R2D) software. The results of the algorithm provide accurate and timely damage estimates that support informative and fast emergency response.

Problem

• post-disaster damage assessment
• adaptive sampling
• cost-aware optimization
• rapid assessment
• autonomous data collection

Innovation

• cost-aware Bayesian optimization
• level-set estimation
• adaptive sampling
• autonomous UAV
• post-disaster damage assessment