Deep convolutional neural networks for multi-scale time-series classification and application to disruption prediction in fusion devices
This work addresses the problem of disruption prediction in fusion tokamaks, which is critical for maintaining stable plasma operations, but it is incremental as it applies an existing neural network architecture to a specific dataset.
The paper tackled the challenge of predicting plasma disruptions in fusion devices by applying a deep convolutional neural network with dilated convolutions to multi-scale time-series data from a single diagnostic, achieving an F1-score of approximately 91% on individual time-slices.
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.