DamageScope is a retrieval-augmented framework that combines satellite imagery with Vision-Language Models (VLMs) and Large Language Models (LLMs) to automate property damage analysis and introduces a novel multi-vector embedding-based clustering algorithm that outperforms traditional single-vector embedding approaches while reducing indexing time by up to 14x.
Abstract
Timely and accurate assessment of property damage is critical following natural disasters. Traditional on-site inspections are labor-intensive, costly, and often pose safety risks. Advances in satellite imagery and vision-language models (VLMs) enable scalable remote damage assessment; however, integrating VLMs into large-scale Earth observation pipelines presents challenges in computational efficiency, data organization, and information retrieval. To address these challenges, we present DamageScope, a retrieval-augmented framework that combines satellite imagery with Vision-Language Models (VLMs) and Large Language Models (LLMs) to automate property damage analysis. Built on a Retrieval-Augmented Generation (RAG) framework, DamageScope extracts structured visual representations from satellite imagery to support interactive natural language queries for damage assessment. To address scalability, we introduce a novel multi-vector embedding-based clustering algorithm that outperforms traditional single-vector embedding approaches while reducing indexing time by up to 14x. Furthermore, a dual-store data architecture minimizes LLM API calls, reducing both operational cost and response latency by up to approximately 3x. By effectively balancing scalability and operational efficiency, DamageScope provides a robust and practical solution for real-world damage assessment tasks.
Abstract. In the aftermath of a disaster, whether natural, industrial, or war-related, a rapid and accurate assessment of building damage is crucial for rescue forces to conduct an effective emergency response. Very high-resolution satellite imagery enables such assessments and serves as an important indicator for understanding the scale of destruction, supporting time-critical rescue operations, and guiding resource allocation. While deep learning models have shown promising results in automating building damage assessment (BDA) from pre- and post-disaster optical satellite imagery, they often fail to generalize to new disasters due to domain shifts. This paper studies the challenge of rapid domain adaptation for BDA in the context of the war in Ukraine. We create a new, challenging dataset annotated with damage grades across six cities in Ukraine, using pre- and post-disaster optical imagery. To facilitate rapid adaptation, we propose an efficient fine-tuning workflow using Low-Rank Adaptation. Our experiments show that this approach substantially improves performance in both out-of-domain and in-domain settings, presenting a practical and data-efficient study for deploying BDA models in time-critical emergency scenarios.
Sebastian Gapp, C. Henry, Pablo d'Angelo et al.· ISPRS Annals of the Photogra...· 0 citations
This work presents HASTE (High-speed Assessment and Satellite Tracking for Emergencies), a no-code web platform that lets analysts who are not machine learning engineers produce per-building damage maps from post-disaster satellite imagery, and describes the platform, methods, and the engineering that supports them.
Caleb Robinson, Anthony Ortiz, S. Nsutezo et al.· 0 citations
Social media imagery (SMI) provides timely and fine-grained ground perspectives that are valuable for situational awareness and emergency response. Unlike satellite or aerial imagery, SMI can capture disaster impacts and ground-level conditions in a timely manner. However, geographic references in SMI are often vague or ambiguous, making accurate geolocalization challenging. To address this issue, we propose Disaster TD, a disaster toponym disambiguation framework that integrates multimodal large language models (MLLMs)-based semantic reasoning with cross-view geolocalization. First, MLLMs extract toponyms and generate candidate geolocations from noisy textual inputs. Then, cross-view matching between SMI, remote sensing imagery (RSI), and optionally street-view imagery (SVI) is used to verify and refine these candidate results. A Vision Transformer (ViT)-based visual foundation model, DINOv2, is used to bridge the domain gap between overhead and ground-level imagery. We evaluate DisasterTD on the Hurricane Harvey dataset, where SMI is augmented with collected RSI and SVI to construct a cross-view benchmark for disaster geolocalization. The dataset is divided into four categories based on toponym clarity and ambiguity, allowing a fine-grained performance analysis across scenarios. Results show that DisasterTD consistently outperforms MLLM-only and cross-view-only baselines without disambiguation, achieving geolocalization accuracies of 71.62% within 1000 m, 62.36% within 500 m, 57.99% within 250 m, 52.09% within 100 m, and 47.01% within 50 m, while reducing the mean and median errors to 11.33 and 0.68 km, respectively. The largest improvements appear in ambiguous toponyms, where semantic reasoning with cross-view evidence reduces candidate dispersion and errors. These findings demonstrate the effectiveness of integrating MLLM-based candidate generation with cross-view verification for fine-grained disaster geolocalization.
Wenping Yin, Ziqi Liu, Naixia Mou et al.· IEEE Transactions on Geoscie...· 0 citations
A hybrid framework that decouples detection from damage assessment is proposed, combining the precision of CV models with the reasoning power of LVLMs, and the best combination under this framework accurately counts intact, partially damaged and completely destroyed buildings.
H. Ung, Guillaume Habault, Roberto Legaspi et al.· 0 citations
Effective management of industrial land is essential given its substantial environmental footprint, intensive resource consumption, and implications for urban planning and public health. Accurate visual grounding of industrial parcels in remote sensing imagery provides a critical basis for assessing associated environmental risks and supporting evidence-based resource allocation. However, existing approaches often rely primarily on visual cues and remain vulnerable to domain-specific ambiguity in complex urban environments. To address these limitations, we propose retrieval-augmented geospatial vision–language grounding (RAGVLG), a model-agnostic framework that integrates structured knowledge retrieval with vision–language models (VLMs) to improve industrial land grounding in remote sensing imagery. RAGVLG retrieves domain knowledge and contextual exemplars to guide grounding decisions, enabling flexible adaptation to different VLM backbones. We construct an industrial land-grounding dataset and systematically evaluate the proposed framework, demonstrating consistent improvements over baseline VLMs across multiple backbones. We further demonstrate its utility through city-scale applications in Shenzhen and Hong Kong, where industrial land is mapped, and the spatial distribution of potential environmental risks is assessed by integrating key environmental parameters. Local indicators of spatial association are used to quantify spatial clustering of risk. The results show that high–high hotspots account for 10.62% of all grids in Shenzhen, forming a continuous coastal corridor primarily across Nanshan and Baoan Districts. Hong Kong exhibits a higher proportion of high–high clusters, at 15.31%, with more fragmented high-risk areas concentrated in Kwai Tsing and Kowloon. These findings provide quantitative and spatially explicit evidence for regional industrial planning, environmental risk management, and sustainable industrial development.
Yuling Wu, Xiyu Jin, Ruiqian Zhang et al.· IEEE Journal of Selected Top...· 0 citations
This study explores AI-driven image classification to expedite damage evaluation by identifying damaged buildings from post-disaster photos much faster than conventional methods, providing a more detailed understanding of structural integrity across affected areas.
M. Kovačević, F. Đorđević, Đorđe Nedeljković et al.· Bulletin of Earthquake Engin...· 0 citations