Deep convolutional neural networks for multi-scale time-series classification and application to disruption prediction in fusion devices
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.
- Authors:
- Publication Date:
- DOE Contract Number:
- AC02-09CH11466; FC02-04ER54698; FG02-99ER54531
- Research Org.:
- Princeton Plasma Physics Lab. (PPPL), Princeton, NJ (United States)
- Sponsoring Org.:
- USDOE
- Keywords:
- fusion; plasma physics; machine learning; deep learning; convolutional neural networks; ECEi
- OSTI Identifier:
- 1661171
- DOI:
- https://doi.org/10.11578/1661171
Citation Formats
Churchill, R M, and the DIII-D team. Deep convolutional neural networks for multi-scale time-series classification and application to disruption prediction in fusion devices. United States: N. p., 2020.
Web. doi:10.11578/1661171.
Churchill, R M, & the DIII-D team. Deep convolutional neural networks for multi-scale time-series classification and application to disruption prediction in fusion devices. United States. doi:https://doi.org/10.11578/1661171
Churchill, R M, and the DIII-D team. 2020.
"Deep convolutional neural networks for multi-scale time-series classification and application to disruption prediction in fusion devices". United States. doi:https://doi.org/10.11578/1661171. https://www.osti.gov/servlets/purl/1661171. Pub date:Thu May 21 00:00:00 EDT 2020
@article{osti_1661171,
title = {Deep convolutional neural networks for multi-scale time-series classification and application to disruption prediction in fusion devices},
author = {Churchill, R M and the DIII-D team},
abstractNote = {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.},
doi = {10.11578/1661171},
journal = {},
number = ,
volume = ,
place = {United States},
year = {2020},
month = {5}
}