Monitoring War Destruction from Space: A Machine Learning Approach
This provides more reliable data for media, humanitarian efforts, human rights monitoring, reconstruction, and conflict studies, addressing a critical bottleneck in monitoring war destruction.
The authors tackled the problem of scarce and biased building destruction data in conflict zones by developing an automated deep learning method that analyzes high-resolution satellite images, applying it to the Syrian civil war to reconstruct damage evolution across major cities with unprecedented scope, resolution, and frequency.
Existing data on building destruction in conflict zones rely on eyewitness reports or manual detection, which makes it generally scarce, incomplete and potentially biased. This lack of reliable data imposes severe limitations for media reporting, humanitarian relief efforts, human rights monitoring, reconstruction initiatives, and academic studies of violent conflict. This article introduces an automated method of measuring destruction in high-resolution satellite images using deep learning techniques combined with data augmentation to expand training samples. We apply this method to the Syrian civil war and reconstruct the evolution of damage in major cities across the country. The approach allows generating destruction data with unprecedented scope, resolution, and frequency - only limited by the available satellite imagery - which can alleviate data limitations decisively.