Tearing mode instability prediction in EAST tokamak using multi-task contrastive learning and multimodal diagnostics
Machine Learning: Science and Technology · 01.08.2026 · 7 (4) · 045029
DOI: 10.1088/2632-2153/ae894d ↗Kurz gefasst
Fachartikel in der Zeitschrift Machine Learning: Science and Technology, online erschienen am 21.07.2026. Verfasst von Wenchong Yao und 7 weiteren Autor:innen. Die Arbeit nennt 33 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Key Research and Development Program of China.
Abstract (Originalsprache)
Accurate prediction of tearing-mode (TM) characteristics from heterogeneous diagnostics is important for tokamak monitoring and control-oriented analysis. In this work, we present MTCF-Net, a multimodal framework for joint prediction of TM existence, frequency, and strength using Mirnov probe signals and multi-channel electron cyclotron emission (ECE) measurements from EAST. The model uses three parallel feature extractors to process magnetic time-domain signals, magnetic time-frequency representations, and ECE spatiotemporal signals. We introduce a physics-motivated contrastive regularization term to encourage consistency between complementary magnetic representations while preserving the difference between magnetic perturbation features and thermodynamic responses. We also use a classification-guided multi-task objective to reduce unstable regression outputs during TM-absent intervals. The dataset contains 68 expert-annotated EAST discharges with TM activity and is split by shot number into training, validation, and independent test sets. On the independent 11-shot test set, MTCF-Net achieves an F 1-score of 0.991 for TM detection and an R 2 value of 0.966 for both frequency and strength prediction on held-out test shots. Ablation and noise-injection studies suggest that the contrastive regularization mainly improves the stability of strength prediction, while multimodal fusion improves frequency prediction. These results indicate that MTCF-Net is a promising framework for TM prediction on the curated EAST dataset, while maintaining low inference latency.
Förderung
- National Key Research and Development Program of China
Zitieren
APA
Yao, W., Zhong, K., Lan, T., Wang, W., Liu, Z., Liu, H., Song, Y., & Zhao, H. (2026). Tearing mode instability prediction in EAST tokamak using multi-task contrastive learning and multimodal diagnostics. Machine Learning: Science and Technology, 7(4), 045029. https://doi.org/10.1088/2632-2153/ae894d
Vancouver
Yao W, Zhong K, Lan T, Wang W, Liu Z, Liu H, et al. Tearing mode instability prediction in EAST tokamak using multi-task contrastive learning and multimodal diagnostics. Machine Learning: Science and Technology. 2026;7(4):045029. doi:10.1088/2632-2153/ae894d
BibTeX
@article{Yao2026,
author = {Yao, Wenchong and Zhong, Kai and Lan, Ting and Wang, Weihua and Liu, Zhihao and Liu, Haiqing and Song, Yuntao and Zhao, Hailin},
title = {Tearing mode instability prediction in EAST tokamak using multi-task contrastive learning and multimodal diagnostics},
journal = {Machine Learning: Science and Technology},
year = {2026},
volume = {7},
number = {4},
pages = {045029},
doi = {10.1088/2632-2153/ae894d}
}
EUVIMED