Unsupervised detection of building destruction during war from publicly available radar satellite imagery
Daniel Racek, Qi Zhang, Paul Wilhelm Thurner, Xiao Xiang Zhu, Göran Kauermann · 2025
Read Unsupervised detection of building destruction during war from publicly available radar satellite imagery by Daniel Racek, Qi Zhang, Paul Wilhelm Thurner, Xiao Xiang Zhu, Göran Kauermann (2025) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-12687346.txt.
Description
Racek and co-authors present a 2025 method for spotting destroyed buildings in war zones from free radar satellite images. Older tools need pricey photos, labeled examples that war zones lack, or clear skies. Radar from the Sentinel-1 satellites sees through clouds and costs nothing. Their statistics watch how radar echo coherence shifts over time, flagging likely destruction building by building.
Each flag carries a probability, so users see the doubt attached. Updates can land every twelve days from a single fresh pass. Beirut, Mariupol, and Gaza served as test cases against known event records. The authors aim the tool at rights monitors, aid planners, and researchers who need fast, honest damage maps.
Catalog record
| CREATOR | Daniel Racek, Qi Zhang, Paul Wilhelm Thurner, Xiao Xiang Zhu, Göran Kauermann |
|---|---|
| YEAR | 2025 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 47 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |