Deep learning for hazard quantification from imagery
Christian N. Svinth, Nell Byler, Kirsten Chojnicki · 2024
Fast and accurate quantification of a dangerous chemical release can reduce human exposure and environmental contamination. We demonstrate that deep learning models can provide quick and practical source term estimates from images of chemical releases, using a dataset compiled from volcanic plume observations. We nd that the best performing deep learning models are able to predict "large," "medium," or "small" SO2 releases from unseen images of volcanic plumes with over 80% accuracy, and can be trained on imagery taken from the ground, air, or space. We test a range of model architectures, training strategies, and optimization approaches to determine what combination of properties produce a model that is robust and operates in the widest possible variety of situations. We evaluate how well the model generalizes to images of industrial SO2 plumes and find that the best-performing volcanic plume model achieves 70% accuracy on images of industrial SO2 plumes, demonstrating the potential of using deep learning for image-based hazard quantification.