Building Damage Detection with UNet-Backbone Fusion in High-Resolution Satellite Imagery: 2023 Morocco Earthquake

Earthquakes and other natural disasters rank among the most destructive events, causing widespread loss of life and severe economic consequences globally. A primary consequence of earthquakes is the large-scale collapse and damage of buildings. The rapid advancement of high-resolution remote sensing...

Full description

Saved in:
Bibliographic Details
Main Authors: S. Holail, T. Saleh, X. Xiao, A. H. Ali, D. Li
Format: Article
Language:English
Published: Copernicus Publications 2025-07-01
Series:The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Online Access:https://isprs-archives.copernicus.org/articles/XLVIII-G-2025/589/2025/isprs-archives-XLVIII-G-2025-589-2025.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849729090019393536
author S. Holail
T. Saleh
T. Saleh
X. Xiao
A. H. Ali
D. Li
author_facet S. Holail
T. Saleh
T. Saleh
X. Xiao
A. H. Ali
D. Li
author_sort S. Holail
collection DOAJ
description Earthquakes and other natural disasters rank among the most destructive events, causing widespread loss of life and severe economic consequences globally. A primary consequence of earthquakes is the large-scale collapse and damage of buildings. The rapid advancement of high-resolution remote sensing technology, offering extensive coverage and multi-temporal capabilities, combined with deep learning methods, has opened new possibilities for accurately and efficiently detecting and assessing building damage to support crisis management. However, pre- and post-disaster images are often acquired under varying temporal, lighting, and weather conditions, complicating the task of accurately identifying building damage levels. This study proposes a Siamese network based on UNet to address these challenges, enabling the assessment of building damage using satellite imagery following earthquakes. The network leverages multi-scale feature differentiation to model spatial and temporal semantic relationships, addressing the issue of intra-class semantic variation. The proposed method was evaluated on the xBD disaster damage dataset and the 2023 Morocco earthquake dataset, achieving an overall accuracy of 95.5% and a kappa coefficient of 76.0%. These results highlight the potential of AI-driven solutions to meet the critical demands for speed and accuracy in disaster response scenarios.
format Article
id doaj-art-502b2c7b661141b8a99b09b372fe445c
institution DOAJ
issn 1682-1750
2194-9034
language English
publishDate 2025-07-01
publisher Copernicus Publications
record_format Article
series The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
spelling doaj-art-502b2c7b661141b8a99b09b372fe445c2025-08-20T03:09:19ZengCopernicus PublicationsThe International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences1682-17502194-90342025-07-01XLVIII-G-202558959510.5194/isprs-archives-XLVIII-G-2025-589-2025Building Damage Detection with UNet-Backbone Fusion in High-Resolution Satellite Imagery: 2023 Morocco EarthquakeS. Holail0T. Saleh1T. Saleh2X. Xiao3A. H. Ali4D. Li5State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan 430072, ChinaGeomatics Engineering Department, Faculty of Engineering at Shoubra, Benha University, Cairo 11629, EgyptSchool of Artificial Intelligence, Wuhan University, Wuhan, 430072, ChinaState Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan 430072, ChinaGeomatics Engineering Department, Faculty of Engineering at Shoubra, Benha University, Cairo 11629, EgyptState Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan 430072, ChinaEarthquakes and other natural disasters rank among the most destructive events, causing widespread loss of life and severe economic consequences globally. A primary consequence of earthquakes is the large-scale collapse and damage of buildings. The rapid advancement of high-resolution remote sensing technology, offering extensive coverage and multi-temporal capabilities, combined with deep learning methods, has opened new possibilities for accurately and efficiently detecting and assessing building damage to support crisis management. However, pre- and post-disaster images are often acquired under varying temporal, lighting, and weather conditions, complicating the task of accurately identifying building damage levels. This study proposes a Siamese network based on UNet to address these challenges, enabling the assessment of building damage using satellite imagery following earthquakes. The network leverages multi-scale feature differentiation to model spatial and temporal semantic relationships, addressing the issue of intra-class semantic variation. The proposed method was evaluated on the xBD disaster damage dataset and the 2023 Morocco earthquake dataset, achieving an overall accuracy of 95.5% and a kappa coefficient of 76.0%. These results highlight the potential of AI-driven solutions to meet the critical demands for speed and accuracy in disaster response scenarios.https://isprs-archives.copernicus.org/articles/XLVIII-G-2025/589/2025/isprs-archives-XLVIII-G-2025-589-2025.pdf
spellingShingle S. Holail
T. Saleh
T. Saleh
X. Xiao
A. H. Ali
D. Li
Building Damage Detection with UNet-Backbone Fusion in High-Resolution Satellite Imagery: 2023 Morocco Earthquake
The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
title Building Damage Detection with UNet-Backbone Fusion in High-Resolution Satellite Imagery: 2023 Morocco Earthquake
title_full Building Damage Detection with UNet-Backbone Fusion in High-Resolution Satellite Imagery: 2023 Morocco Earthquake
title_fullStr Building Damage Detection with UNet-Backbone Fusion in High-Resolution Satellite Imagery: 2023 Morocco Earthquake
title_full_unstemmed Building Damage Detection with UNet-Backbone Fusion in High-Resolution Satellite Imagery: 2023 Morocco Earthquake
title_short Building Damage Detection with UNet-Backbone Fusion in High-Resolution Satellite Imagery: 2023 Morocco Earthquake
title_sort building damage detection with unet backbone fusion in high resolution satellite imagery 2023 morocco earthquake
url https://isprs-archives.copernicus.org/articles/XLVIII-G-2025/589/2025/isprs-archives-XLVIII-G-2025-589-2025.pdf
work_keys_str_mv AT sholail buildingdamagedetectionwithunetbackbonefusioninhighresolutionsatelliteimagery2023moroccoearthquake
AT tsaleh buildingdamagedetectionwithunetbackbonefusioninhighresolutionsatelliteimagery2023moroccoearthquake
AT tsaleh buildingdamagedetectionwithunetbackbonefusioninhighresolutionsatelliteimagery2023moroccoearthquake
AT xxiao buildingdamagedetectionwithunetbackbonefusioninhighresolutionsatelliteimagery2023moroccoearthquake
AT ahali buildingdamagedetectionwithunetbackbonefusioninhighresolutionsatelliteimagery2023moroccoearthquake
AT dli buildingdamagedetectionwithunetbackbonefusioninhighresolutionsatelliteimagery2023moroccoearthquake