Skip navigation
Please use this identifier to cite or link to this item:
Title: Deep convolutional neural networks for multi-scale time-series classification and application to disruption prediction in fusion devices
Contributors: Churchill, R.M
the DIII-D team
U. S. Department of Energy
Keywords: fusion
plasma physics
machine learning
deep learning
convolutional neural networks
Issue Date: Oct-2019
Publisher: Princeton Plasma Physics Laboratory, Princeton University
Related Publication: arxiv
Abstract: 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 ({$\sim$}30k), achieving an $F_1$-score of {$\sim$}91\% on individual time-slices using only the ECEi data.
Appears in Collections:Theory and Computation

Files in This Item:
File Description SizeFormat 
README.txt757 BTextView/Download
ARK_DATA.zip4.49 MBUnknownView/Download

Items in Dataspace are protected by copyright, with all rights reserved, unless otherwise indicated.