Researchers Develop Method to Detect Building Destruction Using Satellite Imagery
LMU and TUM researchers have developed a cost-effective method to detect building destruction in conflict zones using public satellite imagery in near real-time.
Researchers at Ludwig-Maximilians-Universität München (LMU) and the Technical University of Munich (TUM) have developed a new method to quickly and affordably detect building destruction in conflict zones. The method utilizes publicly available Sentinel-1 radar satellite imagery, enabling the identification of damage without the need for expensive commercial images or specific training data.
The developed technique is based on Interferometric Synthetic Aperture Radar (InSAR). It compares successive images of the same area and calculates a coherence measure indicating the similarity of radar signals. A sudden drop in coherence suggests structural changes, such as damage or destruction of a building. The researchers statistically analyze the results and combine them with building footprints from OpenStreetMap to refine location data.
The method's effectiveness has been demonstrated through case studies involving the Beirut port explosion (2020), the destruction of Mariupol following the start of the Russian invasion (2022), and the war in Gaza (from 2023). The researchers view the technique as a fast and cost-effective tool for humanitarian situation assessments, academic research, and post-conflict reconstruction planning.
Dr. Daniel Racek, the study's first author, emphasized that "using freely accessible data, we can track how destruction evolves across space and time almost in real time." The Sentinel-1 mission's satellites provide global imagery at 12-day intervals, and the radar technology operates independently of cloud cover and daylight, making it particularly suitable for conflict zones.