Automatic Quantification of Settlement Damage using Deep Learning of Satellite Images
This work addresses the need for real-time damage assessment to inform relief operations and rebuilding planning for humanitarian and disaster response systems, representing an incremental improvement by applying existing deep learning methods to a specific domain.
The paper tackled the problem of real-time quantification of settlement damage from disasters by using satellite images to train deep learning models (ResNet and PSPPNet) for identifying destruction and quantifying built environment damage with accuracies of 92% and 84%, respectively, and combined them with a multi-linear regression model to predict overall damage, validated on the 2020 Beirut port explosion.
Humanitarian disasters and political violence cause significant damage to our living space. The reparation cost to homes, infrastructure, and the ecosystem is often difficult to quantify in real-time. Real-time quantification is critical to both informing relief operations, but also planning ahead for rebuilding. Here, we use satellite images before and after major crisis around the world to train a robust baseline Residual Network (ResNet) and a disaster quantification Pyramid Scene Parsing Network (PSPNet). ResNet offers robustness to poor image quality and can identify areas of destruction with high accuracy (92\%), whereas PSPNet offers contextualised quantification of built environment damage with good accuracy (84\%). As there are multiple damage dimensions to consider (e.g. economic loss and fatalities), we fit a multi-linear regression model to quantify the overall damage. To validate our combined system of deep learning and regression modeling, we successfully match our prediction to the ongoing recovery in the 2020 Beirut port explosion. These innovations provide a better quantification of overall disaster magnitude and inform intelligent humanitarian systems of unfolding disasters.