A NEURAL NETWORK METHOD TO TRANSPORT INFRASTRUCTURE DAMAGE RECOGNITION DURING ARMED AGGRESSION USING SATELLITE IMAGES
DOI:
https://doi.org/10.15588/1607-3274-2026-2-7Keywords:
bridge damage, Attention U-Net, multispectral satellite imagery, deep neural networks, change detection, armed aggressionAbstract
Context. Recognizing and analyzing changes in transport infrastructure using satellite imagery is important for urban planning, emergency management, military monitoring, and post-war reconstruction. Traditional methods of assessing the condition of roads and bridges, based on ground surveys and expert interpretation of aerial photographs, are labor-intensive, time-consuming, and potentially dangerous for personnel, especially during natural disasters or armed conflicts. In this regard, it is important to develop automated methods for detecting bridge damage using machine learning from publicly available satellite imagery.
Objective. This work aims to develop a neural network method for recognizing and pixel-localizing damage to transport infrastructure using Sentinel-2 multispectral images and OSM vector data, based on a modified Attention U-Net architecture with adaptive spatial-feature weighting and the Dice Loss function to produce a probabilistic damage mask.
Method. A method for recognizing damage to transport infrastructure in Sentinel-2 multispectral images and OSM vector data using a convolutional neural network is proposed. The method is based on the improved Attention U-Net neural network architecture, in which vector data of the transport network (linear road and railway axes, bridge contours) serve as a priori structural information about the geometry and spatial location of infrastructure objects. This information is used by the decoder’s attention mechanism to limit the formation of output features to spatial areas corresponding to infrastructure objects. As a result, the loss function is calculated only within the spatial area specified by the binary mask of infrastructure objects. It reduces misclassifications in adjacent areas and increases the accuracy of boundary delineation for damaged bridge sections.
Results. Experimental studies have confirmed the effectiveness of the proposed method for automated detection of bridge damage on multispectral satellite images. The comprehensive use of spectral-temporal information, combined with binary masks of transport infrastructure, has reduced false classifications in adjacent areas and increased the accuracy of localizing damaged sections. According to the quantitative assessment results, the mIoU was 78.6%, the F1-score was 0.81, and the overall classification accuracy exceeded 93%.
Conclusions. The experiments confirmed the effectiveness of the proposed method for automated recognition of damage to road and railway bridges in satellite images. The improved Attention U-Net architecture, which combines spatial attention mechanisms with prior structural information about the transport network, has increased the accuracy of pixel-level damage area recognition compared to U-Net models. The proposed method enables the creation of analytical geospatial maps of damaged bridge sections, which can be directly integrated into geographic information systems for infrastructure monitoring, assessing the consequences of natural or military disasters, and supporting decision-making on response and recovery
References
Yongtao Yu., Tiannan Gu., Haiyan G., Dilong Li, Shenghua J. Vehicle detection from high-resolution remote sensing imagery using convolutional capsule networks. IEEE Geoscience and Remote Sensing Letters, 2019, Vol. 16, no. 12, pp. 1894–1898. DOI: 10.1109/LGRS.2019.2912582
Byun S., Shin I.-K., Moon J., Kang J., Choi S.-I. Road traffic monitoring from UAV images using deep learning networks. Remote Sensing, 2021, Vol. 13, no. 20, Art. 4027. DOI: 10.3390/rs13204027
Khrissi L., El Akkad N., Satori H., Satori K. Clustering method and sine cosine algorithm for image segmentation. Evolutionary Intelligence, 2022, Vol. 15, pp. 669–682. DOI: 10.1007/s12065-020-00544-z
Kaggle Massachusetts Roads Dataset [Electronic resource], 2020. Mode of access: https://www.kaggle.com/datasets/balraj98/massachusetts-roadsdataset
Kaggle DeepGlobe Road Extraction Dataset [Electronic resource], 2018. Mode of access: https://www.kaggle.com/datasets/balraj98/deepglobe-roadextraction-dataset
Kashtan V. Yu., Hnatushenko V. V. Machine learning for automatic extraction of water bodies using Sentinel-2 imagery. Radio Electronics, Computer Science, Control, 2024, № 1, pp. 118–127. DOI: 10.15588/1607-3274-2024-1-12
Karnik A., Pimpalkar S., Panchagnula M., Acharya S. K. Sentinel-2based dataset covering Indian regions for road detection: A dataset for infrastructure monitoring. Data in Brief, 2025, Vol. 63, Art. 112141. DOI: 10.1016/j.dib.2025.112141
Kopiika N., Karavias A., Krassakis P., Ye Z., Ninic J., Shakhovska N., Koukouzas N., Argyroudis S. A., Mitoulis S. A. Rapid Post-Disaster Infrastructure Damage Characterisation Enabled by Remote Sensing and Deep Learning Technologies –A Tiered Approach. Automation in Construction, 2025, Vol. 170, Art. 105955. DOI: 10.1016/j.autcon.2024.105955
Kashtan V., Hnatushenko V. Deep learning technology for automatic burned area extraction using satellite high spatial resolution images. Intelligent Systems of Decision-Making and Problems of Computational Intelligence : International Scientific Conference ISDMCI-2022, Zaliznyi Port, 24–28 May, 2022: roceedings. Cham, Springer, 2023, pp. 664–685. (Lecture Notes in Data Engineering, Computational Intelligence, and Decision Making, Vol. 149). DOI: 10.1007/978-3-031-16203- 9_45
Wei Y., Zhang K., Ji S. Road network extraction from satellite images using CNN based segmentation and tracing. IGARSS 2019 – 2019 IEEE International Geoscience and Remote Sensing Symposium : proceedings. Yokohama, IEEE, 2019, pp. 9591–9594. DOI: 10.1109/IGARSS.2019.8898123
Rastiveis H., Seydi S. T., Chen Z., Li J. Seismic urban damage map generation based on satellite images and Gabor convolutional neural networks. International Journal of Applied Earth Observation and Geoinformation, 2023, Vol. 122, Art. 103450.
DOI: 10.1016/j.jag.2023.103450
Guo G., Zhang Z. Road damage detection algorithm for improved YOLOv5. Scientific Reports, 2022, Vol. 12, Art. 15523. DOI: 10.1038/s41598-022-19674-w
Zeng J., Zhong H. YOLOv8-PD: An Improved Road Damage Detection Algorithm Based on YOLOv8n Model. Scientific Re-ports, 2024, Vol. 14, Art. 12052. DOI:10.1038/s41598-024-62846-9
Doshi K., Yilmaz Y. Road Damage Detection using Deep Ensemble Learning. arXiv preprint, 2020, arXiv:2011.00728. DOI: 10.48550/arXiv.2011.00728
Li Y., Zhang R., Wu Y. Road network extraction in high resolution SAR images based CNN features. 2017 IEEE International Geoscience and Remote Sensing Symposium (IGARSS) : proceedings. Fort Worth, IEEE, 2017, pp. 4567–4570. DOI: 10.1109/IGARSS.2017.8128034
Henry C., Azimi S. M., Merkle N. Road segmentation in SAR satellite images with deep fully convolutional neural networks.
IEEE Geoscience and Remote Sensing Letters, 2018, Vol. 15, no. 12, pp. 1867–1871. DOI: 10.1109/LGRS.2018.2864784
Naanjam R., Farnood Ahmadi F. An improved self-training network for building and road extraction in urban areas by integrating optical and radar remotely sensed data. Earth Science Informatics, 2024, Vol. 17, no. 3, pp. 2159–2176. DOI: 10.1007/s12145-024-01270-1
Sakamoto J. Proposal of a flood damage road detection method based on deep learning and elevation data. Geomatics, Natural
Hazards and Risk, 2024, Vol. 15, no. 1, Art. 2375545. DOI: 10.1080/19475705.2024.2375545
Gonzalez R., Faisal Z. Digital Image Processing, 2nd ed. New York, Pearson, 2019, 1024 p.
OpenStreetMap [Electronic resource]. OpenStreetMap Foundation, 2026. Mode of access: https://www.openstreetmap.org/
Oktay O., Schlemper J., Folgoc L. L. et al. Attention U-Net: Learning Where to Look for the Pancreas. arXiv preprint, 2018, arXiv:1804.03999. DOI: 10.48550/arXiv.1804.03999
Milletari F., Navab N., Ahmadi S. A. V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation. 2016 Fourth International Conference on 3D Vision (3DV) : proceedings. Stanford, IEEE, 2016, pp. 565–571. DOI: 10.1109/3DV.2016.79
Chengzhi Y., Hongjun G. A Method of Image Semantic Segmentation Based on PSPNet. Mathematical Problems in Engineering, 2022, Vol. 2022, Art. 8958154. DOI: 10.1155/2022/8958154
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 V. Yu. Kashtan, V. V. Hnatushenko
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Creative Commons Licensing Notifications in the Copyright Notices
The journal allows the authors to hold the copyright without restrictions and to retain publishing rights without restrictions.
The journal allows readers to read, download, copy, distribute, print, search, or link to the full texts of its articles.
The journal allows to reuse and remixing of its content, in accordance with a Creative Commons license СС BY -SA.
Authors who publish with this journal agree to the following terms:
-
Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License CC BY-SA that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
-
Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
-
Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) as it can lead to productive exchanges, as well as earlier and greater citation of published work.
