Abstract
Satellite imagery is becoming ubiquitous and is released with ever higher frequency. Research has demonstrated that Artificial Intelligence (AI) applied to satellite imagery holds promise for automated detection of war-related building destruction. While these results are promising, monitoring in real-world applications requires consistently high precision, especially when destruction is sparse and detecting destroyed buildings is equivalent to looking for a needle in a haystack. We demonstrate that exploiting the persistent nature of building destruction can substantially improve the training of automated destruction monitoring. We also propose an additional machine learning stage that leverages images of surrounding areas and multiple successive images of the same area which further improves detection significantly. By combining these steps, we construct an automated classification of building destruction which allows real-world applications and we illustrate this in the context of the Syrian civil war.