Hybrid deep-learning architecture for general disruption prediction across multiple tokamaks. (22nd December 2020)

• Record Type: Journal Article
• Authors: Zhu, J.X.; Rea, C.; Montes, K.; Granetz, R.S.; Sweeney, R.; Tinguely, R.A.
• Is Part Of: Nuclear fusion. Volume 61:Number 2(2021)
• Publication Date: 2020-12-22
• Subjects: disruption -- prediction -- machine learning -- stability -- tokamak; Nuclear fusion -- Periodicals; 621.48405
• DOI: 10.1088/1741-4326/abc664
• Languages: English
• ISSNs: 0029-5515

Abstract

Abstract: In this paper, we present a new deep-learning disruption-prediction algorithm based on important findings from explorative data analysis which effectively allows knowledge transfer from existing devices to new ones, thereby predicting disruptions using very limited disruption data from the new devices. The explorative data analysis, conducted via unsupervised clustering techniques confirms that time-sequence data are much better separators of disruptive and non-disruptive behavior than the instantaneous plasma-state data, with further advantageous implications for a sequence-based predictor. Based on such important findings, we have designed a new algorithm for multi-machine disruption prediction that achieves high predictive accuracy for the C-Mod (AUC = 0.801), DIII-D (AUC = 0.947) and EAST (AUC = 0.973) tokamaks with limited hyperparameter tuning. Through numerical experiments, we show that a boosted accuracy (AUC = 0.959) is achieved for the EAST predictions by including only 20 disruptive discharges with thousands of non-disruptive discharges from EAST in the training, combined with more than a thousand discharges from DIII-D and C-Mod. The improvement in the predictive ability obtained by combining disruption data from other devices is found to be true for all permutations of the three devices. Furthermore, by comparing the predictive performance of each individual numerical experiment, we find that non-disruption data are machine-specific, while disruption data from multiple devices contain device-independent knowledge that can be used to inform predictions for disruptions occurring in a new device.