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.
Abstract
When a large disaster strikes, responders need a map of which buildings are damaged within hours. The models that do well on public benchmarks assume matched before-and-after imagery and a training set drawn from similar past events, and neither is usually available for a new disaster in its first day. We present 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. HASTE implements two methods that share one interface. The first requires the user to label polygons over the post-disaster scene, trains a small semantic segmentation model on that single scene, runs it over the whole image, and joins the per-pixel output to existing building footprints. The second embeds every footprint with a pretrained vision model, requires the user to label a handful of buildings, and fits a logistic regression in the browser that scores the rest of the scene in seconds. We describe the platform, both methods, and the engineering that supports them. We also report preliminary experiments on xBD showing that foundation-model embeddings pooled over footprints separate damaged from intact buildings using post-disaster imagery alone, matching a fully supervised ResNet-50 baseline with a twentieth of its labels. HASTE and its predecessors have supported more than thirty real-world disaster responses since 2023, spanning earthquakes, hurricanes, cyclones, floods, wildfires, and tornadoes, delivering results to humanitarian partners within hours to days of imagery becoming available. We close with the directions we think are most promising, including vision-language assessment, active learning, and damage models for roads and other infrastructure. HASTE is open source at https://github.com/microsoft/haste.
Rapid post-disaster response requires timely, building-level information on whether structures remain intact, are damaged, or are destroyed. Post-event optical imagery, however, may be unavailable because of cloud, smoke, or darkness. The Bright Challenge evaluated all-weather building damage mapping from a submeter-resolution pre-event optical image and a post-event SAR image. Participants were required to detect and delineate each building and assign exactly one of three mutually exclusive damage labels. The challenge extended the globally distributed \textsc{Bright} dataset with instance-level annotations for about 291,000 buildings across 16 disaster events spanning seven disaster types. The final phase was evaluated exclusively on two 2025 events absent from training: a wildfire event in California and a hurricane in Jamaica. A total of 157 participants made 1,289 submissions, and 46 teams entered the final phase. The two winning solutions achieved test mAPs of 0.182 and 0.181, approximately 8.7 times the public baseline of 0.021, but remained far below the best in-domain holdout score of 0.513. Across teams ranked in both phases, performance declined sharply and the rank order changed substantially. The two leading solutions independently favored modality-specific encoding, staged or late optical--SAR fusion, and an optical-dominant separation of building localization from damage recognition. The winning method additionally used scene-aware threshold adjustment and pseudo-label adaptation. These results identify cross-event generalization and stable severity discrimination as the principal remaining challenges. All data, annotations, baseline code, and winning solutions are publicly available at https://github.com/ChenHongruixuan/BRIGHT.
Hongruixuan Chen, He Huang, Haifeng Wang et al.· 0 citations
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.
Ravi K. Rajendran, Biplob Debnath, Murugan Sankaradas et al.· 0 citations
Rapid, reliable assessment of building damage immediately after an earthquake is essential for prioritising search and rescue, allocating scarce resources, and establishing early situational awareness. This study develops and evaluates a deep learning classifier that uses terrestrial images-which provide critical ground-level detail often missed by aerial or satellite views-to categorise buildings as not damaged, damaged, or collapsed. Trained on a curated corpus of post-event building images sourced from multiple earthquakes, a ResNet50-based model achieved 93.5 per cent overall accuracy in terms of validation. The results demonstrate the feasibility of fast, initial triage at building scale and serve to complement existing aerial/remote sensing workflows, including potential integration into crowdsourced and reconnaissance imagery streams. This approach offers a practical path to accelerating post-event decision support while recognising that finer-grained damage classification may be developed for later recovery phases, ultimately improving urban resilience and saving human lives during critical, time-sensitive operations in vulnerable, disaster-stricken communities.
H. Kashani, Amirmohammad Sahebzadeh, Mahdi Naimi Jamal et al.· Disasters. The Journal of Di...· 0 citations
Two free satellite signals carry real information about glacial-lake outburst risk in the Nepal Himalaya: radar interferometry sees a moraine dam slowly sagging, and satellite weather marks the weeks when a primed lake is under stress. A companion feasibility study found that deformation indicates which lake is destabilizing and weather indicates when it is at risk, but proposed no predictive model. To address this gap, we propose and evaluate models that predict which site is susceptible and when a trigger arrives. We test three related hazards on free data alone: large moraine- and ice-dammed bursts, rainfall-triggered landslides, and smaller floods from ponds on and around a glacier. Each hazard gets two questions, never blended. Using 589 dated outbursts from HMAGLOFDB and several thousand catalogued landslides, we match each event against similar but unfailed sites, and hold every model to a strong simple baseline under spatial cross-validation that withholds whole map tiles, so no model succeeds by recognising a trained-on neighbourhood. Antecedent weather times the trigger at ROC 0.73 for big bursts, 0.83 for landslides, and 0.82 for small floods. Terrain ranks susceptibility only in part: scored naively it appears near 0.9, largely because catalogued failures cluster in wetter ranges; matched against comparable nearby sites the honest figures are 0.76, 0.71, and 0.54 (no better than chance). The burst signal holds within single regions, reaching 0.89 in Nepal alone. Five deep-learning models do not decisively beat a simple gradient-boosted baseline. Three score marginally higher on landslides, a hint too small to confirm. For the lake hazards the baseline wins outright, reproduced by a three-rule decision tree on ruggedness and monsoon rainfall. We close with a ranked Nepal watchlist, a prioritisation aid, not a prediction, and note where free data reaches its limits.
Matthew E. Kahn, Milan Arjel, Nirmala Adhikari et al.· 0 citations
Rapid and accurate post-disaster building damage assessment is essential, yet remains a challenging task. Unmanned Aerial Vehicle (UAV) imagery offers a timely and high-resolution view of affected areas, but existing Computer Vision (CV) models often demand large annotated datasets, generalize poorly across geographic regions and their assessment policies, and are confined to the specific tasks they were trained for. Large Vision-Language Models (LVLMs) offer a promising alternative through their strong reasoning and generalization capabilities, but fall short on precise, low-level perception tasks such as object detection and accurate bounding box generation. Furthermore, they often require a substantial amount of data for effective fine-tuning on domain-specific tasks. In this paper, we propose a hybrid framework that decouples detection from damage assessment, combining the precision of CV models with the reasoning power of LVLMs. A CV model first detects buildings and generates bounding boxes on the image that are then passed to an LVLM for damage classification and contextual interpretation. We evaluated our framework on two real-world benchmarks: RescueNet and FloodNet. In particular, the best combination under this framework accurately counts intact, partially damaged and completely destroyed buildings, surpassing isolated baselines by up to 2.1 R^2 points, while requiring only limited annotated data for the detection stage. Beyond reporting aggregate gains, we provide a detailed analysis of failure scenarios and edge cases, offering practical insights for practitioners and concrete directions for future work. Our source code and data are publicly available to the research community via the following repository: https://github.com/ungquanghuy-kddi/VLM_GDINO.git
H. Ung, Guillaume Habault, Roberto Legaspi et al.· 0 citations
Post-disaster debris detection is important for rapid damage assessment, emergency response, and recovery planning. However, debris objects in aerial imagery are often fragmented, irregularly shaped, partially occluded, and visually confused with shadows, vegetation, roofs, vehicles, and damaged structures. This study proposes YOLO-SDD, a YOLO-based Shape-Guided Debris Detector built on YOLOv8 for localized debris identification in high-resolution post-disaster aerial imagery. YOLO-SDD combines a high-resolution P2 detection pathway with a shape-guided feature refinement module that uses box-supervised pseudo-mask and pseudo-boundary cues to refine P2-level features before final debris detection. A multi-event aerial imagery dataset was constructed from NOAA Emergency Response Imagery using images collected after hurricanes and a tornado in the United States. The model was evaluated using an image-level split, an event-level holdout test, component-level ablation studies, COCO-style scale-specific evaluation, and multi-seed stability analysis. On the image-level test set, YOLO-SDD achieved a precision of 0.959, recall of 0.933, mAP@50 of 0.970, and mAP@50:95 of 0.755, remaining competitive with larger YOLO-family models at lower computational complexity. In the event-level holdout test, YOLO-SDD achieved an AP@50 of 0.80 and an F1 score of 0.79, outperforming the YOLOv8s baseline and the selected large YOLO-family comparison model. The scale-specific evaluation showed improved AP@50 and recall for small and medium debris groups, while failure cases remained associated with shadows, vegetation, low contrast, and highly fragmented debris. The results indicate that shape-guided P2 refinement can improve localized debris screening under the tested conditions, although broader datasets, workflow integration, and human-in-the-loop validation are still needed before operational deployment.
Hassan R. Al-Derham, Mahitha Veeramachaneni, Lu Gao et al.· Algorithms· 0 citations