Towards Cross-Disaster Building Damage Assessment with Graph Convolutional Networks

Abstract

In the aftermath of disasters, building damage maps are obtained using change detection to plan rescue operations. Current convolutional neural network approaches do not consider the similarities between neighboring buildings for predicting the damage. We present a novel graph-based building damage detection solution to capture these relationships. Our proposed model architecture learns from both local and neighborhood features to predict building damage. Specifically, we adopt the sample and aggregate graph convolution strategy to learn aggregation functions that generalize to unseen graphs which is essential for alleviating the time needed to obtain predictions for new disasters. Our experiments on the xBD dataset and comparisons with a classical convolutional neural network reveal that while our approach is handicapped by class imbalance, it presents a promising and distinct advantage when it comes to cross-disaster generalization.

On Transfer Learning for Building Damage Assessment from Satellite Imagery in Emergency Contexts

“…Ismail and Awad [48] proposed a novel approach based on graph convolutional network to incorporate knowledge on similar neighbour buildings for the model to make a prediction. They have introduced this technique to help cross-disaster generalization in time-limited settings after a natural disaster.…”

Research on the Exposure Risk Analysis of Wildfires with a Spatiotemporal Knowledge Graph

“…Additionally, many studies have concentrated on extracting post-disaster information about damaged buildings. Qing et al [12] developed a CNN-based hierarchical building damage assessment process, while Ismail and Awad [13] introduced a graph-based building damage detection method that leverages knowledge of adjacent structures. Notably, some related research, such as that by Beverly et al [14], closely associates fire exposure with fuel, devising a metric for fire exposure risk based on the proximity of grid cells to combustible materials.…”