A method developed by researchers at LMU and TUM makes the destruction of buildings in war visible quickly and cost-effectively.

A team of researchers from LMU and the Technical University of Munich (TUM), funded by the Munich School for Data Science (MUDS), has developed a method that automatically detects building destruction in conflict zones – without relying on expensive commercial satellite imagery or training data. Crucially, destruction can be identified using the very next available satellite image, enabling detection without long delays. The study has been published in PNAS Nexus. “Using freely accessible data, we can track how destruction evolves across space and time almost in real time,” says Dr. Daniel Racek, first author of the study and former doctoral researcher at the Institute of Statistics at LMU.

The method is based on synthetic aperture radar (SAR) images from the European Sentinel-1 mission, which are available globally at 12-day intervals. Because radar operates independently of cloud cover and daylight, it is particularly well suited for conflict and war zones. The team applies an interferometric technique known as InSAR: repeated images of the same region are compared and a so-called coherence measure is calculated, indicating how similar the backscattered radar signals are. A sudden drop in coherence often points to structural changes in buildings, such as damage or destruction.

To ensure that such signals are not confused with random fluctuations, they are assessed statistically. For each pixel, a “normal” pattern of variation over time is estimated, and deviations are quantified using probabilities known as p-values. By combining this information with building footprints from OpenStreetMap, the results can be aggregated at the building level, including a measure of uncertainty.

In case studies of the Beirut port explosion (2020), the destruction of Mariupol following the start of the Russian invasion (2022), and the war in Gaza (from 2023 onwards), the method successfully reconstructed both the spatial patterns and timing of destruction. The researchers view the approach as a fast and cost-effective tool for humanitarian situation assessments, academic research, and post-conflict reconstruction planning.