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

Churchill, R M

doi:10.11578/1661171

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

Dataset
Other Related Research

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:: Churchill, R M; the DIII-D team

Publication Date:: Thu May 21 00:00:00 EDT 2020

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.

Copy to clipboard


                    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

Copy to clipboard


                    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

Copy to clipboard


                    
@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         = {Thu May 21 00:00:00 EDT 2020},

  month        = {Thu May 21 00:00:00 EDT 2020}

}

Copy to clipboard

Dataset:

View Dataset

DOI: https://doi.org/10.11578/1661171

Save / Share:

Export Metadata

Save to My Library

Similar records in DOE Data Explorer and OSTI.GOV collections:

Deep convolutional neural networks for multi-scale time-series classification and application to tokamak disruption prediction using raw, high temporal resolution diagnostic data

Journal Article Churchill, R. M. ; Tobias, B. ; Zhu, Y. ; ... - Physics of Plasmas

Cited by 28
Deep convolutional neural networks for multi-scale time-series classification and application to tokamak disruption prediction using raw, high temporal resolution diagnostic data

Journal Article Churchill, R. M. ; Tobias, B. ; Zhu, Y. - Physics of Plasmas

In this paper we discuss recent advances in deep convolutional neural networks (CNN) for sequence learning, which allow identifying long-range, multi-scale phenomena in long sequences, such as those found in fusion plasmas. We point out several benefits of these deep CNN architectures, such as not requiring experts such as physicists to hand-craft input data features, the ability to capture longer range dependencies compared to the more common sequence neural networks (recurrent neural networks like long short-term memory (LSTM) networks), and the comparative computational efficiency. We apply this neural network architecture to the popular problem of disruption prediction in fusion energymore »« less
Cited by 28
Deep convolutional neural networks for multi-scale time-series classification and application to tokamak disruption prediction using raw, high temporal resolution diagnostic data

Journal Article Churchill, R. M. ; Tobias, B. ; Zhu, Y. - Physics of Plasmas

In this paper, we discuss recent advances in deep convolutional neural networks (CNNs) for sequence learning, which allow identifying longrange, multi-scale phenomena in long sequences, such as those found in fusion plasmas. We point out several benefits of these deep CNN architectures, such as not requiring experts such as physicists to hand-craft input data features, the ability to capture longer range dependencies compared to the more common sequence neural networks (recurrent neural networks like long short-term memory networks), and the comparative computational efficiency. We apply this neural network architecture to the popular problem of disruption prediction in fusion energy tokamaks,more »« less
Cited by 28
Deep convolutional neural networks for multi-scale time-series classification and application to tokamak disruption prediction using raw, high temporal resolution diagnostic data

Journal Article Churchill, R.M. ; Tobias, Benjamin ; Yu, Yilun - Physics of Plasmas

In this paper, we discuss recent advances in deep convolutional neural networks (CNNs) for sequence learning, which allow identifying longrange, multi-scale phenomena in long sequences, such as those found in fusion plasmas. We point out several benefits of these deep CNN architectures, such as not requiring experts such as physicists to hand-craft input data features, the ability to capture longer range dependencies compared to the more common sequence neural networks (recurrent neural networks like long short-term memory networks), and the comparative computational efficiency. We apply this neural network architecture to the popular problem of disruption prediction in fusion energy tokamaks,more »« less
Cited by 28
Deep convolutional neural networks for long time series classification [PowerPoint]

Conference Churchill, R. M.

Abstract not provided.

Similar Records