Version 1
: Received: 1 January 2021 / Approved: 4 January 2021 / Online: 4 January 2021 (15:58:21 CET)
How to cite:
Chen, T. Interpretability in Convolutional Neural Networks for Building Damage Classification in Satellite Imagery. Preprints2021, 2021010053. https://doi.org/10.20944/preprints202101.0053.v1
Chen, T. Interpretability in Convolutional Neural Networks for Building Damage Classification in Satellite Imagery. Preprints 2021, 2021010053. https://doi.org/10.20944/preprints202101.0053.v1
Chen, T. Interpretability in Convolutional Neural Networks for Building Damage Classification in Satellite Imagery. Preprints2021, 2021010053. https://doi.org/10.20944/preprints202101.0053.v1
APA Style
Chen, T. (2021). Interpretability in Convolutional Neural Networks for Building Damage Classification in Satellite Imagery. Preprints. https://doi.org/10.20944/preprints202101.0053.v1
Chicago/Turabian Style
Chen, T. 2021 "Interpretability in Convolutional Neural Networks for Building Damage Classification in Satellite Imagery" Preprints. https://doi.org/10.20944/preprints202101.0053.v1
Abstract
Natural disasters ravage the world's cities, valleys, and shores on a monthly basis. Having precise and efficient mechanisms for assessing infrastructure damage is essential to channel resources and minimize the loss of life. Using a dataset that includes labeled pre- and post- disaster satellite imagery, we train multiple convolutional neural networks to assess building damage on a per-building basis. In order to investigate how to best classify building damage, we present a highly interpretable deep-learning methodology that seeks to explicitly convey the most useful information required to train an accurate classification model. We also delve into which loss functions best optimize these models. Our findings include that ordinal-cross entropy loss is the most optimal loss function to use and that including the type of disaster that caused the damage in combination with a pre- and post-disaster image best predicts the level of damage caused. Our research seeks to computationally contribute to aiding in this ongoing and growing humanitarian crisis, heightened by climate change.
Engineering, Safety, Risk, Reliability and Quality
Copyright:
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
