Papers
Topics
Authors
Recent
Search
2000 character limit reached

Open Access Battle Damage Detection via Pixel-Wise T-Test on Sentinel-1 Imagery

Published 10 May 2024 in cs.CV | (2405.06323v1)

Abstract: In the context of recent, highly destructive conflicts in Gaza and Ukraine, reliable estimates of building damage are essential for an informed public discourse, human rights monitoring, and humanitarian aid provision. Given the contentious nature of conflict damage assessment, these estimates must be fully reproducible, explainable, and derived from open access data. This paper introduces a new method for building damage detection-- the Pixel-Wise T-Test (PWTT)-- that satisfies these conditions. Using a combination of freely-available synthetic aperture radar imagery and statistical change detection, the PWTT generates accurate conflict damage estimates across a wide area at regular time intervals. Accuracy is assessed using an original dataset of over half a million labeled building footprints spanning 12 cities across Ukraine, Palestine, Syria, and Iraq. Despite being simple and lightweight, the algorithm achieves building-level accuracy statistics (AUC=0.88 across Ukraine, 0.81 in Gaza) rivalling state of the art methods that use deep learning and high resolution imagery. The workflow is open source and deployed entirely within the Google Earth Engine environment, allowing for the generation of interactive Battle Damage Dashboards for Ukraine and Gaza that update in near-real time, allowing the public and humanitarian practitioners to immediately get estimates of damaged buildings in a given area.

Authors (1)
Definition Search Book Streamline Icon: https://streamlinehq.com
References (47)
  1. Economist. Data from satellites reveal the vast extent of fighting in Ukraine. The Economist, 2023. ISSN 0013-0613. URL https://www.economist.com/interactive/briefing/2023/02/23/data-from-satellites-reveal-the-vast-extent-of-fighting-in-ukraine.
  2. Jared Malsin and Saeed Shah. The Ruined Landscape of Gaza After Nearly Three Months of Bombing, December 2023. URL https://www.wsj.com/world/middle-east/gaza-destruction-bombing-israel-aa528542. Section: World.
  3. Maps: Tracking the Attacks in Israel and Gaza. The New York Times, October 2023. ISSN 0362-4331. URL https://www.nytimes.com/interactive/2023/10/07/world/middleeast/israel-gaza-maps.html.
  4. xBD: A Dataset for Assessing Building Damage from Satellite Imagery, November 2019. URL http://arxiv.org/abs/1911.09296. arXiv:1911.09296 [cs] version: 1.
  5. BDANet: Multiscale Convolutional Neural Network with Cross-directional Attention for Building Damage Assessment from Satellite Images. IEEE Transactions on Geoscience and Remote Sensing, 60:1–14, 2022. ISSN 0196-2892, 1558-0644. doi:10.1109/TGRS.2021.3080580. URL http://arxiv.org/abs/2105.07364. arXiv:2105.07364 [cs, eess].
  6. A Deep Learning Application for Building Damage Assessment Using Ultra-High-Resolution Remote Sensing Imagery in Turkey Earthquake. International Journal of Disaster Risk Science, 14(6):947–962, December 2023. ISSN 2192-6395. doi:10.1007/s13753-023-00526-6. URL https://doi.org/10.1007/s13753-023-00526-6.
  7. Post-disaster building damage assessment based on improved U-Net. Scientific Reports, 12(1):15862, September 2022. ISSN 2045-2322. doi:10.1038/s41598-022-20114-w. URL https://www.nature.com/articles/s41598-022-20114-w. Publisher: Nature Publishing Group.
  8. Monitoring war destruction from space using machine learning. Proceedings of the National Academy of Sciences, 118(23):e2025400118, June 2021. ISSN 0027-8424, 1091-6490. doi:10.1073/pnas.2025400118. URL https://pnas.org/doi/full/10.1073/pnas.2025400118.
  9. AAAS. High-Resolution Satellite Imagery Ordering and Analysis Handbook | American Association for the Advancement of Science (AAAS), 2024. URL https://www.aaas.org/resources/high-resolution-satellite-imagery-ordering-and-analysis-handbook.
  10. ESA. Sentinel-1 - Missions - Sentinel Online, 2024. URL https://copernicus.eu/missions/sentinel-1.
  11. Urban change monitoring from multi-temporal TerraSAR-X images. In 2011 Joint Urban Remote Sensing Event, pages 277–280, April 2011. doi:10.1109/JURSE.2011.5764773. URL https://ieeexplore.ieee.org/abstract/document/5764773. ISSN: 2334-0932.
  12. Towards a damage assessment in a tsunami affected area using L-band and X-band SAR data. In 2017 Joint Urban Remote Sensing Event (JURSE), pages 1–4, March 2017. doi:10.1109/JURSE.2017.7924633. URL https://ieeexplore.ieee.org/document/7924633.
  13. Mapping earthquake damage in VHR radar images of human settlements: Preliminary results on the 6th April 2009, Italy case. In 2010 IEEE International Geoscience and Remote Sensing Symposium, pages 1347–1350, July 2010. doi:10.1109/IGARSS.2010.5653973. URL https://ieeexplore.ieee.org/document/5653973. ISSN: 2153-7003.
  14. Statistical analysis to assess building damage in 2008 Wenchuan earthquake from multi-temporal SAR images. In 2009 2nd Asian-Pacific Conference on Synthetic Aperture Radar, pages 121–123, October 2009. doi:10.1109/APSAR.2009.5374142. URL https://ieeexplore.ieee.org/abstract/document/5374142.
  15. A review on synthetic aperture radar-based building damage assessment in disasters. Remote Sensing of Environment, 240:111693, April 2020. ISSN 0034-4257. doi:10.1016/j.rse.2020.111693. URL https://www.sciencedirect.com/science/article/pii/S0034425720300626.
  16. Extraction of Collapsed Buildings in the 2016 Kumamoto Earthquake Using Multi-Temporal PALSAR-2 Data. Journal of Disaster Research, 12(2):241–250, 2017. doi:10.20965/jdr.2017.p0241.
  17. Coherence- and Amplitude-Based Analysis of Seismogenic Damage in Bam, Iran, Using ENVISAT ASAR Data. IEEE Transactions on Geoscience and Remote Sensing, 45(6):1571–1581, June 2007. ISSN 1558-0644. doi:10.1109/TGRS.2006.883149. URL https://ieeexplore.ieee.org/document/4244569. Conference Name: IEEE Transactions on Geoscience and Remote Sensing.
  18. Extraction of damaged regions using SAR data and neural networks. volume 33, pages 156–163, 2000. ISSN: 1682-1750.
  19. C. Yonezawa and S. Takeuchi. Decorrelation of SAR data by urban damages caused by the 1995 Hyogoken-nanbu earthquake. International Journal of Remote Sensing, 22(8):1585–1600, 2001. ISSN 0143-1161. doi:10.1080/01431160118187.
  20. Franz Meyer. Spaceborne Synthetic Aperture Radar: Principles, Data Access, and Basic Processing Techniques. In NASA SAR Handbook. 2019.
  21. Natural Resources Canada. Radar Polarimetry, January 2008. URL https://natural-resources.canada.ca/maps-tools-and-publications/satellite-imagery-and-air-photos/tutorial-fundamentals-remote-sensing/microwave-remote-sensing/radar-polarimetry/9275. Last Modified: 2015-11-20 Publisher: Natural Resources Canada.
  22. Building Damage Assessment Using Multisensor Dual-Polarized Synthetic Aperture Radar Data for the 2016 M 6.2 Amatrice Earthquake, Italy. Remote Sensing, 2017. URL https://www.mdpi.com/2072-4292/9/4/330.
  23. Speckle filtering of synthetic aperture radar images: A review. Remote Sensing Reviews, 8(4):313–340, February 1994. ISSN 0275-7257. doi:10.1080/02757259409532206. URL https://doi.org/10.1080/02757259409532206. Publisher: Taylor & Francis _eprint: https://doi.org/10.1080/02757259409532206.
  24. Microsoft. microsoft/GlobalMLBuildingFootprints, February 2024. URL https://github.com/microsoft/GlobalMLBuildingFootprints. original-date: 2022-04-22T22:09:24Z.
  25. UNOSAT. Irpin Building Damage Assessment Overview Map, 2022a. URL https://unosat.org/products/3360.
  26. UNOSAT. Chernihiv Building Damage Assessment Overview Map, 2022b. URL https://unosat.org/products/3354.
  27. UNOSAT. Damage Density in the City of Aleppo, Syria, 2016. URL https://unosat.org/products/1118.
  28. UNOSAT. Damage density of Mosul, Ninawa Governorate, Iraq, 2017a. URL https://unosat.org/products/1189.
  29. UNOSAT. Damage density of Ar Raqqa, Ar Raqqa Governorate, Syria, 2017b. URL https://unosat.org/products/1192.
  30. UNOSAT. Hostomel Building Damage Assessment Overview Map, 2022c. URL https://unosat.org/products/3359.
  31. UNOSAT. Kharkiv Damage Assessment Overview, 2022d. URL https://unosat.org/products/3455.
  32. UNOSAT. Lysychansk Damage Assessment Overview, 2022e. URL https://unosat.org/products/3444.
  33. UNOSAT. Mariupol Updated Rapid Damage Assessment Overview Map, 2022f. URL https://unosat.org/products/3368.
  34. UNOSAT. Rubizhne Damage Assessment Overview, 2022g. URL https://unosat.org/products/3414.
  35. UNOSAT. Sievierodonetsk Damage Assessment Overview, 2022h. URL https://unosat.org/products/3446.
  36. UNOSAT. UNOSAT Gaza Strip Comprehensive Damage Assessment - January 2024, 2024. URL https://unosat.org/products/3793.
  37. Battle Damage Assessment based on self-similarity and contextual modeling of buildings in dense urban areas. In 2016 IEEE International Geoscience and Remote Sensing Symposium (IGARSS), pages 5161–5164, July 2016. doi:10.1109/IGARSS.2016.7730345. URL https://ieeexplore.ieee.org/document/7730345. ISSN: 2153-7003.
  38. Frank D. W. Witmer. Remote sensing of violent conflict: eyes from above. International Journal of Remote Sensing, 36(9):2326–2352, May 2015. ISSN 0143-1161. doi:10.1080/01431161.2015.1035412. URL https://doi.org/10.1080/01431161.2015.1035412. Publisher: Taylor & Francis _eprint: https://doi.org/10.1080/01431161.2015.1035412.
  39. Post-War Urban Damage Mapping Using InSAR: The Case of Mosul City in Iraq. ISPRS International Journal of Geo-Information, 10(3):140, March 2021. ISSN 2220-9964. doi:10.3390/ijgi10030140. URL https://www.mdpi.com/2220-9964/10/3/140. Number: 3 Publisher: Multidisciplinary Digital Publishing Institute.
  40. Andreas Braun. Assessment of Building Damage in Raqqa during the Syrian Civil War Using Time-Series of Radar Satellite Imagery. Journal for Geographic Information Science, 1:228–242, July 2018. doi:10.1553/giscience2018_01_s228.
  41. Monitoring Urban Change in Conflict from the Perspective of Optical and SAR Satellites: The Case of Mariupol, a City in the Conflict between RUS and UKR. Remote Sensing, 15(12):3096, January 2023. ISSN 2072-4292. doi:10.3390/rs15123096. URL https://www.mdpi.com/2072-4292/15/12/3096. Number: 12 Publisher: Multidisciplinary Digital Publishing Institute.
  42. Canty, Mortimer. Statistical Analysis of Changes in Sentinel-1 Time Series on the Google Earth Engine. Remote Sensing, 2019. URL https://www.mdpi.com/2072-4292/12/1/46.
  43. Jayawant N. Mandrekar. Receiver Operating Characteristic Curve in Diagnostic Test Assessment. Journal of Thoracic Oncology, 5(9):1315–1316, September 2010. ISSN 1556-0864. doi:10.1097/JTO.0b013e3181ec173d. URL https://www.sciencedirect.com/science/article/pii/S1556086415306043.
  44. NASA. Cloud Fraction (1 month - Terra/MODIS) | NASA, February 2024. URL https://neo.gsfc.nasa.gov/view.php?datasetId=MODAL2_M_CLD_FR. Publisher: NASA Earth Observations (NEO).
  45. LandScan HD Ukraine v1.0, 2022. URL landscan.ornl.gov. Section: January 10, 2022.
  46. Towards Rapid Response Updates of Populations at Risk. In IGARSS 2023 - 2023 IEEE International Geoscience and Remote Sensing Symposium, pages 907–910, July 2023. doi:10.1109/IGARSS52108.2023.10282319. URL https://ieeexplore.ieee.org/abstract/document/10282319?casa_token=1EOYrVMPzssAAAAA:oJnalEtZgA1IJBJLBJfF4mVIJaH76kdfCv4mnfhfjyArdE40Zv215bFTTzat9QkiiViI5epPTA. ISSN: 2153-7003.
  47. Benjamin Strick. Eyes on Russia: Documenting Russia’s war on Ukraine, March 2023. URL https://www.info-res.org/post/eyes-on-russia-documenting-conflict-and-disinformation-in-the-kremlin-s-war-on-ukraine.
Citations (1)
View on Semantic Scholar

Summary

No one has generated a summary of this paper yet.

Sign Up to Summarize

Paper to Video (Beta)

No one has generated a video about this paper yet.

Sign Up to Generate All Videos Subscribe on YouTube

Whiteboard

No one has generated a whiteboard explanation for this paper yet.

Sign Up to Generate

Open Problems

We haven't generated a list of open problems mentioned in this paper yet.

Generate Now

Continue Learning

We haven't generated follow-up questions for this paper yet.

Generate Now

Collections

Sign up for free to add this paper to one or more collections.

Sign Up