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 F1-score of ~91% on individual time-slices using only the ECEi data.
Princeton University Machine Learning for the Sciences - New Start Time
Deep Convolutional Neural Networks for Multi-Scale Time-Series Classification and Application to Disruption Prediction in Fusion Devices
Princeton Plasma Physics Laboratory (PPPL)
Lunch will be served.
Date & Time
February 14, 2020 | 12:30 – 1:30pm
Center for Statistics and Machine Learning (CSML), 26 Prospect Ave, Auditorium 103