DamageScope is a retrieval‑augmented framework that combines satellite imagery, Vision‑Language Models (VLMs), and Large Language Models (LLMs) to automate property damage assessment after natural disasters. It uses a Retrieval‑Augmented Generation (RAG) architecture to extract structured visual representations from satellite images, enabling interactive natural language queries. The system introduces a multi‑vector embedding‑based clustering algorithm that improves scalability and reduces indexing time by up to 14×, and a dual‑store data architecture that cuts LLM API calls, lowering operational cost and response latency by roughly 3×.
By Ravi K. Rajendran, Biplob Debnath, Murugan Sankaradas, Srimat T. Chakradhar
The paper revisits building damage assessment (BDA) from satellite imagery, emphasizing the need for a sensor‑agnostic, instance‑based task definition that can handle missing pre‑event data. It reviews existing datasets by modality, timing, and geography, critiques current single‑score evaluation practices, and proposes a more robust, ranking‑based multi‑score protocol. The authors also survey deep learning methods, highlight challenges in generalizing to new events and regions, and outline how these insights could shape future BDA challenges and data‑sharing practices.
By Anthony Cioppa, Virgile Blua, S\'ebastien Pi\'erard, Pietro Ceccato, Marc Van Droogenbroeck
arXiv:2606. 14963v1 Announce Type: cross Abstract: Timely and accurate disaster damage assessment is crucial for effective emergency response, resource allocation, and recovery.
By Tewodros Syum Gebre, Jagrati Talreja, Leila Hashemi-Beni
DisasterInsight is a building‑centric benchmark designed to evaluate vision‑language models (VLMs) for disaster response. Built on the xBD satellite dataset, it adds OpenStreetMap‑derived functional labels to 134,108 building instances and offers 15 task types, including instance assessment, scene counting, multi‑instance reasoning, and structured report generation. Experiments show that VLMs excel at visible damage detection but struggle with building function, multi‑instance reasoning, counting, and grounded reporting, and instruction tuning only partially mitigates these gaps.
By Sara Tehrani, Yonghao Xu, Leif Haglund, Amanda Berg, Gulnaz Zhambulova, Michael Felsberg
The study investigates shortcut learning in geospatial foundation model embeddings for cross-disaster damage assessment. By holding out entire disasters during evaluation, the authors demonstrate a significant drop in mean balanced accuracy across multiple datasets, revealing that models rely on event or scene characteristics rather than transferable evidence. They further show that simple feature-level transformations, such as supervised contrastive learning or PCA, can improve generalization to unseen disasters.
By Ali Shibli, Andrea Nascetti, Yifang Ban
arXiv:2601.18493v2 Announce Type: replace
Abstract: Vision--language models (VLMs) show promise for disaster-response remote sensing, but existing benchmarks mainly emphasize scene-level or damage-ce...
By Sara Tehrani, Yonghao Xu, Leif Haglund, Amanda Berg, Gulnaz Zhambulova, Michael Felsberg