Machine Learning on Satellite Radar Images to Estimate Damages After Natural Disasters
Boyi Xie, Jeri Xu, Jungkyo Jung, Sang‐Ho Yun, Eric Zeng, Edward M. Brooks, Michaela Dolk, Lokeshkumar Narasimhalu
Abstract
Satellite radar imaging from SAR (Synthetic Aperture Radar) is a remote sensing technology that captures ground surface level changes at a relatively high resolution. This technology has been used in many applications, one of which is the estimation of damages after natural disasters, such as wildfire, earthquake, and hurricane events. An efficient and accurate assessment of damages after natural catastrophe events allows public and private sectors to quickly respond in order to mitigate losses and to better prepare for disaster relief. Advances in machine learning and image processing techniques can be applied to this dataset to survey large areas and estimate property damages. In this paper, we introduce a machine learning-based approach for taking satellite radar images and geographical data as inputs to classify the damage status of individual buildings after a major wildfire event. We believe the demonstration of this damage estimation methodology and its application to real world natural disaster events will have a high potential to improve social resilience.