Utilizing Post-Hurricane Satellite Imagery to Identify Flooding Damage with Convolutional Neural Networks
This addresses the need for faster and safer damage assessment after hurricanes, though it is incremental as it applies existing deep learning methods to a specific disaster scenario.
The paper tackled the problem of post-hurricane damage assessment by using convolutional neural networks to classify satellite imagery of buildings as flooded/damaged or undamaged, achieving over 99% accuracy on a dataset from Hurricane Harvey in Houston.
Post-hurricane damage assessment is crucial towards managing resource allocations and executing an effective response. Traditionally, this evaluation is performed through field reconnaissance, which is slow, hazardous, and arduous. Instead, in this paper we furthered the idea of implementing deep learning through convolutional neural networks in order to classify post-hurricane satellite imagery of buildings as Flooded/Damaged or Undamaged. The experimentation was conducted employing a dataset containing post-hurricane satellite imagery from the Greater Houston area after Hurricane Harvey in 2017. This paper implemented three convolutional neural network model architectures paired with additional model considerations in order to achieve high accuracies (over 99%), reinforcing the effective use of machine learning in post-hurricane disaster assessment.