Deep convolutional neural networks for multi-scale time-series classification and application to disruption prediction in fusion devices

• Published in: arXiv.org
• Main Authors: Churchill, R M, the DIII-D team
• Format: Paper Journal Article
• Language: English
• Published: Ithaca Cornell University Library, arXiv.org 21.11.2019
• Subjects: Artificial neural networks; Cyclotrons; Diagnostic systems; Disruption; Electron energy; Neural networks; Physics - Plasma Physics; Plasma jets; Plasmas; Predictions; Sequences; Statistics - Machine Learning; Temporal resolution; Tokamak devices
• ISSN: 2331-8422
• DOI: 10.48550/arxiv.1911.00149

The multi-scale, mutli-physics nature of fusion plasmas makes predicting plasma events challenging. Recent advances in deep convolutional neural network architectures (CNN) utilizing dilated convolutions enable accurate predictions on sequences which have long-range, multi-scale characteristics, such as the time-series generated by diagnostic instruments observing fusion plasmas. Here we apply this neural network architecture to the popular problem of disruption prediction in fusion tokamaks, utilizing raw data from a single diagnostic, the Electron Cyclotron Emission imaging (ECEi) diagnostic from the DIII-D tokamak. ECEi measures a fundamental plasma quantity (electron temperature) with high temporal resolution over the entire plasma discharge, making it sensitive to a number of potential pre-disruptions markers with different temporal and spatial scales. Promising, initial disruption prediction results are obtained training a deep CNN with large receptive field (~30k), achieving an \(F_1\)-score of ~91% on individual time-slices using only the ECEi data.