AI Insight
Researchers developed DisasterAgent, an AI system that generates verifiable disaster assessment reports from before-and-after satellite imagery. The system uses a three-phase workflow: it first builds a structured spatial-temporal graph of disaster changes using specialized vision tools, then extracts evidence with inline citations linking each statement to supporting visual data, and finally generates comprehensive reports. Testing on two benchmarks showed the system improved disaster report accuracy by 13.5-15.34% compared to existing models, while providing traceable evidence for each claim.
Why it matters
Emergency responders need reliable, verifiable information to coordinate disaster response and recovery efforts. This system addresses a critical gap by not only identifying damage but also providing traceable visual evidence for each assessment, enabling faster verification and more confident decision-making during high-stakes disaster situations.
Understand the Science
⚠️ Preprint – Noch nicht peer-reviewed
Dieser Artikel wurde noch nicht von unabhängigen Experten begutachtet. Die Ergebnisse sind vorläufig und sollten mit Vorsicht interpretiert werden.
Abstract: Remote sensing disaster assessment is moving from simple damage classification toward comprehensive report-level analysis. In this setting, responders need not only damage descriptions but also verifiable evidence to guide response and recovery. Recent vision-language models (VLMs) and tool-augmented agents offer strong multimodal reasoning and perception, but they struggle to provide the evidence required for high-stakes verification. To address these limitations, we propose DisasterAgent, an evidence-driven agent that uses a Perception-Augmentation-Generation workflow to generate verifiable disaster reports from bitemporal optical imagery. DisasterAgent first invokes a specialized vision expert toolkit in the perception phase to build a Spatiotemporal Perception Graph (STPG), serving as a structured memory to store and organize disaster-induced changes across space and time. Evidence-based Augmentation (EA) then extracts evidence from the STPG, attaching inline citations that form a closed evidence loop from each statement to the supporting visual evidence. Extensive experiments on the DisasterM3 and RSCC benchmarks demonstrate that DisasterAgent consistently outperforms general-domain VLMs, remote sensing-specialized models, and existing remote sensing agents. Notably, compared with the original model, it improves the average score for disaster report generation on DisasterM3 by 13.5% and ST5-SCS on RSCC by 15.34%, providing a more accurate and verifiable solution for disaster emergency response. The code will be available at https://github.com/ZhijianLi2003/DisasterAgent.