Abstract
The extent of war-induced destruction in urban areas is critical information for international relief efforts, impact assessments and restoration decisions. However, precise geotargeting of zones with severe destruction is still a great challenge. Here we present a novel temporal-knowledge-guided detection scheme (TKDS) with a pixel-based transformer network (PtNet) for monitoring urban destruction using satellite imagery, applied to conflict zones in the Syrian civil war and the Russia–Ukraine conflict. Compared with state-of-the-art methods, the TKDS-PtNet model enhances war damage identification by 44.0 (72.5 versus 28.5) in the F1 score for six Syrian cities and 34.2 (83.5 versus 49.3) for four Ukrainian cities. The identified damaged buildings are further utilized to estimate the affected population and damage to critical infrastructures such as hospitals and schools in these areas. Our results demonstrate the high potential of a repeatable and relatively low-cost scheme for the near real-time monitoring of damage in urban areas resulting from wars, earthquakes or extreme weather events. Our findings underscore the crucial importance of taking action to stop the conflict and developing mechanisms to prevent present and future urban-related damage from military actions.
This is a preview of subscription content, access via your institution
Access options
Subscribe to this journal
Receive 12 digital issues and online access to articles
$119.00 per year
only $9.92 per issue
Buy this article
- Purchase on Springer Link
- Instant access to full article PDF
Prices may be subject to local taxes which are calculated during checkout
Similar content being viewed by others
Data availability
The original labels of the completely destroyed buildings are publicly available via UNITAR at https://www.unitar.org/maps (ref. 27). The 0.5-resolution satellite images in 2009 and 2018 are available via Google Earth at https://www.google.com/earth (ref. 37). The sentinel-2 satellite images are available from https://dataspace.copernicus.eu/. The bombing events are available from http://liveuamap.com. The WorldPop population dataset is available from https://hub.worldpop.org/. Building footprints in Syria and Ukraine are available from https://www.openstreetmap.org/ and via GitHub at https://github.com/microsoft/GlobalMLBuildingFootprints (ref. 32).
Code availability
The source codes are available on GitHub at https://github.com/Houzy116/TKDS-PtNet (ref. 38).
References
Piccoli, G. B., Brunori, G., Gesualdo, L. & Kalantar-Zadeh, K. The impact of the Russian–Ukrainian war for people with chronic diseases. Nat. Rev. Nephrol. 18, 411–412 (2022).
Aiken, E., Bellue, S., Karlan, D., Udry, C. & Blumenstock, J. E. Machine learning and phone data can improve targeting of humanitarian aid. Nature 603, 864–870 (2022).
Smythe, I. S. & Blumenstock, J. E. Geographic microtargeting of social assistance with high-resolution poverty maps. Proc. Natl Acad. Sci. USA 119, 2120025119 (2022).
Wagner, Z. et al. Armed conflict and child mortality in Africa: a geospatial analysis. Lancet 392, 857–865 (2018).
Mueller, H., Groeger, A., Hersh, J., Matranga, A. & Serrat, J. Monitoring war destruction from space using machine learning. Proc. Natl Acad. Sci. USA 118, 2025400118 (2021).
Dando, B. D. E. et al. Identifying attacks in the Russia–Ukraine conflict using seismic array data. Nature 621, 767–772 (2023).
Lubin, A. & Saleem, A. Remote sensing-based mapping of the destruction to Aleppo during the Syrian civil war between 2011 and 2017. Appl. Geogr. 108, 30–38 (2019).
Kahraman, F., Imamoglu, M. & Ates, H. F. Battle damage assessment based on self-similarity and contextual modeling of buildings in dense urban areas. In Proc. 2016 IEEE International Geoscience and Remote Sensing Symposium 5161–5164 (IEEE, 2016).
Nabiee, S., Harding, M., Hersh, J. & Bagherzadeh, N. Hybrid u-net: semantic segmentation of high-resolution satellite images to detect war destruction. Mach. Learn. Appl. 9, 100381 (2022).
Nex, F., Duarte, D., Tonolo, F. G. & Kerle, N. Structural building damage detection with deep learning: assessment of a state-of-the-art CNN in operational conditions. Remote Sensing 11, 2765 (2019).
Tilon, S., Nex, F., Kerle, N. & Vosselman, G. Post-disaster building damage detection from Earth observation imagery using unsupervised and transferable anomaly detecting generative adversarial networks. Remote Sensing 12, 4193 (2020).
Wu, C. et al. Building damage detection using u-net with attention mechanism from pre- and post-disaster remote sensing datasets. Remote Sensing 13, 905 (2021).
Kalantar, B., Ueda, N., Al-Najjar, H. A. H. & Halin, A. A. Assessment of convolutional neural network architectures for earthquake-induced building damage detection based on pre- and post-event orthophoto images. Remote Sensing 12, 3529 (2020).
Janalipour, M. & Mohammadzadeh, A. Building damage detection using object-based image analysis and anfis from high-resolution image (case study: Bam earthquake, Iran). IEEE J. Select. Top. Appl. Earth Obs. Remote Sensing 9, 1937–1945 (2016).
Gueguen, L. & Hamid, R. Large-scale damage detection using satellite imagery. In Proc. 2015 IEEE Conference on Computer Vision and Pattern Recognition 1321–1328 (IEEE, 2015).
Fujita, A. et al. Damage detection from aerial images via convolutional neural networks. In Proc. 2017 15th IAPR International Conference on Machine Vision Applications 5–8 (IAPR, 2017).
Dong, L. & Shan, J. A comprehensive review of earthquake-induced building damage detection with remote sensing techniques. ISPRS J. Photogramm. Remote Sensing 84, 85–99 (2013).
Abdi, G. & Jabari, S. A multi-feature fusion using deep transfer learning for earthquake building damage detection. Can. J. Remote Sensing 47, 337–352 (2021).
Stramondo, S., Bignami, C., Chini, M., Pierdicca, N. & Tertulliani, A. Satellite radar and optical remote sensing for earthquake damage detection: results from different case studies. Int. J. Remote Sensing 27, 4433–4447 (2006).
Oksuz, K., Cam, B. C., Kalkan, S. & Akbas, E. Imbalance problems in object detection: a review. IEEE Trans. Pattern Anal. Mach. Intell. 43, 3388–3415 (2021).
Aung, T. S. Satellite analysis of the environmental impacts of armed-conflict in Rakhine, Myanmar. Sci. Total Environ. 781, 146758 (2021).
Wind, B. & Ibrahim, B. The war-time urban development of Damascus: how the geography- and political economy of warfare affects housing patterns. Habitat Int. 96, 102109 (2020).
Yuksel, A. S. Cities at war: global insecurity and urban resistance. Ethnic Racial Stud. 44, 527–529 (2021).
Weinthal, E. & Sowers, J. Targeting infrastructure and livelihoods in the West Bank and Gaza. Int. Affairs 95, 319–340 (2019).
Schölkopf, B., Platt, J. & Hofmann, T. A Kernel Method for the Two-Sample-Problem. Advances in Neural Information Processing Systems 19, 513–520 (MIT Press, 2007).
Khosla, P. et al. Supervised contrastive learning. Adv. Neural Inform. Process. Syst. 33, 18661–18673 (2020).
United Nations Institute for Training and Research Operational Satellite Applications Programme. UNITAR https://www.unitar.org/maps/ (accessed 25 April 2023).
Liveuamap. Liveuamap https://www.liveuamap.com/ (accessed 25 April 2023).
Selvaraju, R.R. et al. Grad-cam: visual explanations from deep networks via gradient-based localization. In Proc. 2017 IEEE International Conference on Computer Vision (ICCV) 618–626 (IEEE, 2017).
University of Southampton WorldPop. WorldPop https://hub.worldpop.org/ (accessed 20 September 2023).
OpenStreetMap Contributors OpenStreetMap. OpenStreetMap https://www.openstreetmap.org/ (accessed 20 September 2023).
Bing Maps GlobalMLBuildingFootprints. GitHub https://github.com/microsoft/GlobalMLBuildingFootprints (accessed 20 September 2023).
Sticher, V., Wegner, J. D. & Pfeifle, B. Toward the remote monitoring of armed conflicts. Proc. Natl Acad. Sci. Nexus 2, 181 (2023).
Besley, T. & Mueller, H. Estimating the peace dividend: the impact of violence on house prices in Northern Ireland. Am. Econ. Rev. 102, 810–833 (2012).
Burke, M., Hsiang, S. M. & Miguel, E. Climate and conflict. Annu. Rev. Econom. 7, 577–617 (2015).
Manacorda, M. & Tesei, A. Liberation technology: mobile phones and political mobilization in Africa. Econometrica 88, 533–567 (2020).
Google Earth. Google Earth https://www.google.com/earth (accessed 25 April 2023).
TKDS-PtNet. GitHub https://github.com/Houzy116/TKDS-PtNet (accessed 25 March 2024).
Acknowledgements
This work was supported by the National Natural Science Foundation of China under grant numbers 41925006 (L.Z.), 42293272 (L.Z.) and 42201368 (Y.Q.).
Author information
Authors and Affiliations
Contributions
Z.H., Y.Q., L.Z. and C.Z. conceptually designed the study; Z.H., Y.Q., Q.Y. and X.Y. performed the research; Z.H., Y.Q., L.Z., J.L., F.W., A.Z., Z.C., H.T., Y.W., J.R. and S.L. drafted the manuscript; Y.Z., Z.H., X.L., Y.L., S.P. and X.M. analyzed the data.
Corresponding authors
Ethics declarations
Competing interests
The authors declare no competing interests.
Peer review
Peer review information
Nature Cities thanks Ali Darvishi Boloorani, Stergios-Aristoteles Mitoulis and Valerie Sticher for their contribution to the peer review of this work.
Additional information
Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Supplementary information
Supplementary Information
Supplementary technical terms, note, Figs. 1–12 and Tables 1–3.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Hou, Z., Qu, Y., Zhang, L. et al. War city profiles drawn from satellite images. Nat Cities 1, 359–369 (2024). https://doi.org/10.1038/s44284-024-00060-6
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1038/s44284-024-00060-6
