Skip to main content

Thank you for visiting nature.com. You are using a browser version with limited support for CSS. To obtain the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles and JavaScript.

  • Perspective
  • Published:

Disruption prediction with artificial intelligence techniques in tokamak plasmas

Abstract

In nuclear fusion reactors, plasmas are heated to very high temperatures of more than 100 million kelvin and, in so-called tokamaks, they are confined by magnetic fields in the shape of a torus. Light nuclei, such as deuterium and tritium, undergo a fusion reaction that releases energy, making fusion a promising option for a sustainable and clean energy source. Tokamak plasmas, however, are prone to disruptions as a result of a sudden collapse of the system terminating the fusion reactions. As disruptions lead to an abrupt loss of confinement, they can cause irreversible damage to present-day fusion devices and are expected to have a more devastating effect in future devices. Disruptions expected in the next-generation tokamak, ITER, for example, could cause electromagnetic forces larger than the weight of an Airbus A380. Furthermore, the thermal loads in such an event could exceed the melting threshold of the most resistant state-of-the-art materials by more than an order of magnitude. To prevent disruptions or at least mitigate their detrimental effects, empirical models obtained with artificial intelligence methods, of which an overview is given here, are commonly employed to predict their occurrence—and ideally give enough time to introduce counteracting measures.

This is a preview of subscription content, access via your institution

Access options

Buy this article

Prices may be subject to local taxes which are calculated during checkout

Fig. 1: Disruption precursors.
Fig. 2: Performance of adaptive disruption predictors on JET with the ILW.
Fig. 3: Non-disruptive and disruptive regions of the operational space in JET.
Fig. 4: Warning time intervals for predictors.

Similar content being viewed by others

References

  1. Boozer, A. H. Theory of tokamak disruptions. Phys. Plasmas 19, 058101 (2012).

    Article  ADS  Google Scholar 

  2. de Vries, P. C. et al. Requirements for triggering the ITER disruption mitigation system. Fusion Sci. Technol. 69, 471–484 (2016).

    Article  Google Scholar 

  3. Wenninger, R. et al. Power handling and plasma protection aspects that affect the design of the DEMO divertor and first wall. In Proc. 26th IAEA Fusion Energy Conference (FEC, 2018); https://nucleus.iaea.org/sites/fusionportal/Shared%20Documents/FEC%202016/fec2016-preprints/preprint0322.pdf

  4. Sozzi, C. et al. Termination of discharges in high performance scenarios in JET. In Proc. 28th IAEA Fusion Energy Conference (FEC, 2020); https://conferences.iaea.org/event/214/contributions/17328/

  5. Strait, E. J. et al. Progress in disruption prevention for ITER. Nucl. Fusion 59, 112012 (2019).

    Article  ADS  Google Scholar 

  6. Hollmann, E. M. et al. Status of research toward the ITER disruption mitigation system. Phys. Plasmas 22, 021802 (2015).

    Article  ADS  Google Scholar 

  7. Esposito, B. et al. Disruption avoidance in the Frascati tokamak upgrade by means of magnetohydrodynamic mode stabilization using electron-cyclotron-resonance heating. Phys. Rev. Lett. 100, 045006 (2008).

    Article  ADS  Google Scholar 

  8. Maraschek, M. et al. Path-oriented early reaction to approaching disruptions in ASDEX upgrade and TCV in view of the future needs for ITER and DEMO. Plasma Phys. Control. Fusion 60, 014047 (2017).

    Article  ADS  Google Scholar 

  9. Baylor, L. R. et al. Disruption mitigation system developments and design for ITER. Fusion Sci. Technol. 68, 211–215 (2015).

    Article  Google Scholar 

  10. Pautasso, G. et al. On-line prediction and mitigation of disruptions in ASDEX upgrade. Nucl. Fusion 42, 100–109 (2002).

    Article  ADS  Google Scholar 

  11. Cannas, B., Fanni, A., Pautasso, G., Sias, G. & Sonato, P. An adaptive real-time disruption predictor for ASDEX Upgrade. Nucl. Fusion 50, 075004 (2010).

    Article  ADS  Google Scholar 

  12. Kates-Harbeck, J., Svyatkovskiy, A. & Tang, W. Predicting disruptive instabilities in controlled fusion plasmas through deep learning. Nature 568, 526–531 (2019).

    Article  ADS  Google Scholar 

  13. Churchill, R. M. et al. Deep convolutional neural networks for multi-scale time-series classification and application to tokamak disruption prediction using raw, high temporal resolution diagnostic data. Phys. Plasmas 27, 062510 (2020).

    Article  ADS  Google Scholar 

  14. Akçay, Cihan et al. Machine learning methods for probabilistic locked-mode predictors in tokamak plasmas. Phys. Plasmas 28, 082106 (2021).

    Article  ADS  Google Scholar 

  15. Ferreira, D. R., Carvalho, P. J. & Fernandes, H. Deep learning for plasma tomography and disruption prediction from bolometer data. IEEE Trans. Plasma Sci. 48, 36–45 (2019).

    Article  ADS  Google Scholar 

  16. Rattá, G. A. et al. An advanced disruption predictor for JET tested in a simulated real-time environment. Nucl. Fusion 50, 025005 (2010).

    Article  ADS  Google Scholar 

  17. Vega, J. et al. Results of the JET real-time disruption predictor in the ITER-like wall campaigns. Fusion Eng. Des. 88, 1228–1231 (2013).

    Article  Google Scholar 

  18. Dormido-Canto, S. et al. Development of an efficient real-time disruption predictor from scratch on JET and implications for ITER. Nucl. Fusion 53, 113001 (2013).

    Article  ADS  Google Scholar 

  19. Vega, J. et al. Adaptive high learning rate probabilistic disruption predictors from scratch for the next generation of tokamaks. Nucl. Fusion 54, 123001 (2014).

    Article  ADS  Google Scholar 

  20. Agarwal, A. et al. Deep sequence to sequence learning-based prediction of major disruptions in ADITYA tokamak. Plasma Phys. Control. Fusion 63, 115004 (2021).

    Article  ADS  Google Scholar 

  21. Zhang, Y., Pautasso, G., Kardaun, O., Tardini, G. & Zhang, X. D. Prediction of disruptions on ASDEX Upgrade using discriminant analysis. Nucl. Fusion 51, 063039 (2011).

    Article  ADS  Google Scholar 

  22. Rea, C. et al. Disruption prediction investigations using machine learning tools on DIII-D and Alcator C-Mod. Plasma Phys. Control. Fusion 60, 084004 (2018).

    Article  ADS  Google Scholar 

  23. Rea, C., Montes, K. J., Erickson, K. G., Granetz, R. S. & Tinguely, R. A. A real-time machine learning-based disruption predictor in DIII-D. Nucl. Fusion 59, 096016 (2019).

    Article  ADS  Google Scholar 

  24. Rea, C. & Granetz, R. S. Exploratory machine learning studies for disruption prediction using large databases on DIII-D. Fusion Sci. Technol. 74, 89–100 (2018).

    Article  Google Scholar 

  25. Zheng, W. et al. Disruption predictor based on neural network and anomaly detection on J-TEXT. Plasma Phys. Control. Fusion 62, 045012 (2020).

    Article  ADS  Google Scholar 

  26. Gerhardt, S. P. et al. Detection of disruptions in the high-β spherical torus NSTX. Nucl. Fusion 53, 063021 (2013).

    Article  ADS  Google Scholar 

  27. Montes, K. J. et al. Machine learning for disruption warnings on Alcator C-Mod, DIII-D and EAST. Nucl. Fusion 59, 096015 (2019).

    Article  ADS  Google Scholar 

  28. Yokoyama, T. et al. Likelihood identification of high-β disruption in JT-60U. Plasma Fusion Res. 16, 1402073 (2021).

    Article  ADS  Google Scholar 

  29. Guo, B. H. et al. Disruption prediction on EAST tokamak using a deep learning algorithm. Plasma Phys. Control. Fusion 63, 115007 (2021).

    Article  ADS  Google Scholar 

  30. Guo, B. H. et al. Disruption prediction using a full convolutional neural network on EAST. Plasma Phys. Control. Fusion 63, 025008 (2020).

    Article  ADS  Google Scholar 

  31. Hu, W. H. et al. Real-time prediction of high-density EAST disruptions using random forest. Nucl. Fusion 61, 066034 (2021).

    Article  ADS  Google Scholar 

  32. Zhong, Y. et al. Disruption prediction and model analysis using LightGBM on J-TEXT and HL-2A. Plasma Phys. Control. Fusion 63, 075008 (2021).

    Article  ADS  Google Scholar 

  33. Moreno, R. et al. Robustness and increased time resolution of JET Advanced Predictor of Disruptions. Plasma Phys. Control. Fusion 56, 114003 (2014).

    Article  ADS  Google Scholar 

  34. Murari, A. et al. Adaptive predictors based on probabilistic SVM for real-time disruption mitigation on JET. Nucl. Fusion 58, 056002 (2018).

    Article  ADS  Google Scholar 

  35. López, J. M. et al. Implementation of the disruption predictor APODIS in JET’s real-time network using the MARTe framework. IEEE Trans. Nucl. Sci. 61, 741–744 (2014).

    Article  ADS  Google Scholar 

  36. Esquembri, S. et al. Real-time implementation in JET of the SPAD disruption predictor using MARTe. IEEE Trans. Nucl. Sci. 65, 836–842 (2018).

    Article  ADS  Google Scholar 

  37. Vega, J. et al. A linear equation based on signal increments to predict disruptive behaviours and the time to disruption on JET. Nucl. Fusion 60, 026001 (2019).

    Article  ADS  Google Scholar 

  38. Rea, C. et al. Progress toward interpretable machine learning-based disruption predictors across tokamaks. Fusion Sci. Technol. 76, 912–924 (2020).

    Article  Google Scholar 

  39. Zhu, J. X. et al. Hybrid deep-learning architecture for general disruption prediction across multiple tokamaks. Nucl. Fusion 61, 026007 (2020).

    Article  ADS  Google Scholar 

  40. Zhu, J. et al. Scenario adaptive disruption prediction study for next generation burning-plasma tokamaks. Nucl. Fusion 61, 114005 (2021).

    Article  ADS  Google Scholar 

  41. Murari, A., Lungaroni, M., Gelfusa, M., Peluso, E. & Vega, J. JET Contributors Adaptive learning for disruption prediction in non-stationary conditions. Nucl. Fusion 59, 086037 (2019).

    Article  ADS  Google Scholar 

  42. Murari, A. et al. On the transfer of adaptive predictors between different devices for both mitigation and prevention of disruptions. Nucl. Fusion 60, 056003 (2020).

    Article  ADS  Google Scholar 

  43. Murari, A., Rossi, R., Lungaroni, M., Baruzzo, M. & Gelfusa, M. Stacking of predictors for the automatic classification of disruption types to optimize the control logic. Nucl. Fusion 61, 036027 (2021).

    Article  ADS  Google Scholar 

  44. Gunning, D. et al. XAI-explainable artificial intelligence. Sci. Robot. 4, eaay7120 (2019).

    Article  Google Scholar 

  45. Yokoyama, T. et al. Prediction of high-beta disruptions in JT-60U based on sparse modeling using exhaustive search. Fusion Eng. Des. 140, 67–80 (2019).

    Article  Google Scholar 

  46. Piccione, A. et al. Physics-guided machine learning approaches to predict the ideal stability properties of fusion plasmas. Nucl. Fusion 60, 046033 (2020).

    Article  ADS  Google Scholar 

  47. Li, H. X., Yang, J. L., Zhang, G. & Fan, B. Probabilistic support vector machines for classification of noise affected data. Inf. Sci. 221, 60–71 (2013).

    Article  Google Scholar 

  48. Rattá, G. A., Vega, J. & Murari, A., JET-EFDA Contributors. Improved feature selection based on genetic algorithms for real-time disruption prediction on JET. Fusion Eng. Des. 87, 1670–1678 (2012).

    Article  Google Scholar 

  49. Murari, A. et al. Investigating the physics of tokamak global stability with interpretable machine learning tools. Appl. Sci. 10, 6683 (2020).

    Article  Google Scholar 

  50. Fu, Y. et al. Machine learning control for disruption and tearing mode avoidance. Phys. Plasmas 27, 022501 (2020).

    Article  ADS  Google Scholar 

  51. Boyer, M. D., Rea, C. & Clement, M. D. Toward active disruption avoidance via real-time estimation of the safe operating region and disruption proximity in tokamaks. Nucl. Fusion 62, 026005 (2021).

    Article  ADS  Google Scholar 

  52. Rattá, G. A., Vega, J., Murari, A. & Gadariya, D., JET Contributors. PHAD: a phase-oriented disruption prediction strategy for avoidance, prevention and mitigation in JET. Nucl. Fusion 61, 116055 (2021).

    Article  ADS  Google Scholar 

  53. Rossi, R., Gelfusa, M., Malizia, A. & Gaudio, P. Adaptive quasi-unsupervised detection of smoke plume by LIDAR. Sensors 20, 6602 (2020).

    Article  ADS  Google Scholar 

  54. Murari, A., Peluso, E., Gelfusa, M., Lungaroni, M. & Gaudio, P. How to handle error bars in symbolic regression for data mining in scientific applications. In Proc. Third International Symposium on Statistical Learning and Data Sciences, Statistical Learning and Data Sciences. SLDS 2015. Lecture Notes in Computer Science Vol. 9047 (eds Gammerman, A. et al.) 347–355 (Springer, 2015).

  55. Gelfusa, M. et al. UMEL: a new regression tool to identify measurement peaks in LIDAR/DIAL systems for environmental physics applications. Rev. Sci. Instrum. 85, 063112 (2014).

    Article  ADS  Google Scholar 

Download references

Acknowledgements

This work was partially funded by the Spanish Ministry of Science and Innovation under projects nos. PID2019-108377RB-C31 and PID2019-108377RB-C32. This work has been carried out within the framework of the EUROfusion Consortium, funded by the European Union via the Euratom Research and Training Programme (grant agreement no. 101052200 — EUROfusion). Views and opinions expressed are however those of the authors only and do not necessarily reflect those of the European Union or the European Commission. Neither the European Union nor the European Commission can be held responsible for them.

Author information

Authors and Affiliations

Authors

Consortia

Corresponding author

Correspondence to J. Vega.

Ethics declarations

Competing interests

The authors declare no competing interests.

Peer review

Peer review information

Nature Physics thanks Cristina Rea and the other, anonymous, reviewer(s) for their contribution to the peer review of this work.

Additional information

Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Vega, J., Murari, A., Dormido-Canto, S. et al. Disruption prediction with artificial intelligence techniques in tokamak plasmas. Nat. Phys. 18, 741–750 (2022). https://doi.org/10.1038/s41567-022-01602-2

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1038/s41567-022-01602-2

This article is cited by

Search

Quick links

Nature Briefing

Sign up for the Nature Briefing newsletter — what matters in science, free to your inbox daily.

Get the most important science stories of the day, free in your inbox. Sign up for Nature Briefing