{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,11]],"date-time":"2026-04-11T04:13:00Z","timestamp":1775880780628,"version":"3.50.1"},"reference-count":62,"publisher":"Springer Science and Business Media LLC","issue":"7753","license":[{"start":{"date-parts":[[2019,4,1]],"date-time":"2019-04-01T00:00:00Z","timestamp":1554076800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Nature"],"published-print":{"date-parts":[[2019,4]]},"DOI":"10.1038\/s41586-019-1116-4","type":"journal-article","created":{"date-parts":[[2019,4,17]],"date-time":"2019-04-17T18:06:13Z","timestamp":1555524373000},"page":"526-531","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":325,"title":["Predicting disruptive instabilities in controlled fusion plasmas through deep learning"],"prefix":"10.1038","volume":"568","author":[{"given":"Julian","family":"Kates-Harbeck","sequence":"first","affiliation":[]},{"given":"Alexey","family":"Svyatkovskiy","sequence":"additional","affiliation":[]},{"given":"William","family":"Tang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2019,4,17]]},"reference":[{"key":"1116_CR1","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1016\/J.ENG.2016.01.025","volume":"2","author":"C Mote Jr","year":"2016","unstructured":"Mote, C. Jr, Dowling, A. & Zhou, J. The power of an idea: the international impacts of the grand challenges for engineering. Engineering 2, 4\u20137 (2016).","journal-title":"Engineering"},{"key":"1116_CR2","doi-asserted-by":"publisher","first-page":"A135","DOI":"10.1088\/0741-3335\/37\/11A\/009","volume":"37","author":"F Schuller","year":"1995","unstructured":"Schuller, F. Disruptions in tokamaks. Plasma Phys. Contr. Fusion 37, A135 (1995).","journal-title":"Plasma Phys. Contr. Fusion"},{"key":"1116_CR3","doi-asserted-by":"publisher","first-page":"471","DOI":"10.13182\/FST15-176","volume":"69","author":"P Vries De","year":"2016","unstructured":"De Vries, P. et al. Requirements for triggering the ITER disruption mitigation system. Fus. Sci. Technol. 69, 471\u2013484 (2016).","journal-title":"Fus. Sci. Technol."},{"key":"1116_CR4","doi-asserted-by":"publisher","first-page":"39","DOI":"10.1016\/j.jnucmat.2014.10.075","volume":"463","author":"M Lehnen","year":"2015","unstructured":"Lehnen, M. et al. Disruptions in ITER and strategies for their control and mitigation. J. Nucl. Mater. 463, 39\u201348 (2015).","journal-title":"J. Nucl. Mater."},{"key":"1116_CR5","volume-title":"Scientific grand challenges: fusion energy science and the role of computing at the extreme scale","author":"W Tang","year":"2009","unstructured":"Tang, W. et al. Scientific grand challenges: fusion energy science and the role of computing at the extreme scale (US Department of Energy\u2019s Office of Fusion Energy Sciences, Workshop March 18\u201320, Washington DC, 2009)."},{"key":"1116_CR6","doi-asserted-by":"publisher","first-page":"519","DOI":"10.1088\/0741-3335\/44\/5\/304","volume":"44","author":"R Aymar","year":"2002","unstructured":"Aymar, R., Barabaschi, P. & Shimomura, Y. The ITER design. Plasma Phys. Contr. Fusion 44, 519 (2002).","journal-title":"Plasma Phys. Contr. Fusion"},{"key":"1116_CR7","doi-asserted-by":"publisher","first-page":"725","DOI":"10.1088\/0029-5515\/37\/6\/I02","volume":"37","author":"D Wroblewski","year":"1997","unstructured":"Wroblewski, D., Jahns, G. & Leuer, J. Tokamak disruption alarm based on a neural network model of the high-beta limit. Nucl. Fusion 37, 725 (1997).","journal-title":"Nucl. Fusion"},{"key":"1116_CR8","doi-asserted-by":"publisher","first-page":"68","DOI":"10.1088\/0029-5515\/44\/1\/008","volume":"44","author":"B Cannas","year":"2004","unstructured":"Cannas, B., Fanni, A., Marongiu, E. & Sonato, P. Disruption forecasting at JET using neural networks. Nucl. Fusion 44, 68 (2004).","journal-title":"Nucl. Fusion"},{"key":"1116_CR9","doi-asserted-by":"publisher","first-page":"035010","DOI":"10.1088\/0029-5515\/48\/3\/035010","volume":"48","author":"A Murari","year":"2008","unstructured":"Murari, A. et al. Prototype of an adaptive disruption predictor for JET based on fuzzy logic and regression trees. Nucl. Fusion 48, 035010 (2008).","journal-title":"Nucl. Fusion"},{"key":"1116_CR10","doi-asserted-by":"publisher","first-page":"1228","DOI":"10.1016\/j.fusengdes.2013.03.003","volume":"88","author":"J Vega","year":"2013","unstructured":"Vega, J. et al. Results of the JET real-time disruption predictor in the ITER-like wall campaigns. Fusion Eng. Des. 88, 1228\u20131231 (2013).","journal-title":"Fusion Eng. Des."},{"key":"1116_CR11","doi-asserted-by":"publisher","first-page":"337","DOI":"10.1088\/0029-5515\/45\/5\/004","volume":"45","author":"C Windsor","year":"2005","unstructured":"Windsor, C. et al. A cross-tokamak neural network disruption predictor for the JET and ASDEX upgrade tokamaks. Nucl. Fusion 45, 337 (2005).","journal-title":"Nucl. Fusion"},{"key":"1116_CR12","doi-asserted-by":"publisher","first-page":"614","DOI":"10.1088\/0029-5515\/42\/5\/313","volume":"42","author":"JL Luxon","year":"2002","unstructured":"Luxon, J. L. A design retrospective of the DIII-D tokamak. Nucl. Fusion 42, 614 (2002).","journal-title":"Nucl. Fusion"},{"key":"1116_CR13","doi-asserted-by":"publisher","first-page":"014001","DOI":"10.1088\/0031-8949\/2011\/T145\/014001","volume":"2011","author":"G Matthews","year":"2011","unstructured":"Matthews, G. et al. JET ITER-like wall\u2014overview and experimental programme. Phys. Scr. 2011, 014001 (2011).","journal-title":"Phys. Scr."},{"key":"1116_CR14","doi-asserted-by":"crossref","unstructured":"Freidberg, J. P. Plasma Physics and Fusion Energy (Cambridge Univ. Press, 2008).","DOI":"10.1017\/CBO9780511755705"},{"key":"1116_CR15","doi-asserted-by":"publisher","first-page":"1872","DOI":"10.1063\/1.873445","volume":"6","author":"P Taylor","year":"1999","unstructured":"Taylor, P. et al. Disruption mitigation studies in DIII-D. Phys. Plasmas 6, 1872\u20131879 (1999).","journal-title":"Phys. Plasmas"},{"key":"1116_CR16","doi-asserted-by":"publisher","first-page":"R1","DOI":"10.1088\/0741-3335\/47\/2\/R01","volume":"47","author":"WM Tang","year":"2005","unstructured":"Tang, W. M. & Chan, V. Advances and challenges in computational plasma science. Plasma Phys. Contr. Fusion 47, R1 (2005).","journal-title":"Plasma Phys. Contr. Fusion"},{"key":"1116_CR17","doi-asserted-by":"publisher","first-page":"053018","DOI":"10.1088\/0029-5515\/51\/5\/053018","volume":"51","author":"P Vries De","year":"2011","unstructured":"De Vries, P. et al. Survey of disruption causes at JET. Nucl. Fusion 51, 053018 (2011).","journal-title":"Nucl. Fusion"},{"key":"1116_CR18","doi-asserted-by":"publisher","first-page":"602","DOI":"10.1126\/science.aag2302","volume":"355","author":"G Carleo","year":"2017","unstructured":"Carleo, G. & Troyer, M. Solving the quantum many-body problem with artificial neural networks. Science 355, 602\u2013606 (2017).","journal-title":"Science"},{"key":"1116_CR19","doi-asserted-by":"publisher","first-page":"431","DOI":"10.1038\/nphys4035","volume":"13","author":"J Carrasquilla","year":"2017","unstructured":"Carrasquilla, J. & Melko, R. G. Machine learning phases of matter. Nat. Phys. 13, 431\u2013434 (2017).","journal-title":"Nat. Phys."},{"key":"1116_CR20","doi-asserted-by":"publisher","first-page":"10F328","DOI":"10.1063\/1.2965020","volume":"79","author":"G Ratt\u00e1","year":"2008","unstructured":"Ratt\u00e1, G. et al. Feature extraction for improved disruption prediction analysis at JET. Rev. Sci. Instr. 79, 10F328 (2008).","journal-title":"Rev. Sci. Instr."},{"key":"1116_CR21","doi-asserted-by":"publisher","first-page":"1670","DOI":"10.1016\/j.fusengdes.2012.07.002","volume":"87","author":"G Ratt\u00e1","year":"2012","unstructured":"Ratt\u00e1, G. et al. Improved feature selection based on genetic algorithms for real time disruption prediction on JET. Fusion Eng. Design 87, 1670\u20131678 (2012).","journal-title":"Fusion Eng. Design"},{"key":"1116_CR22","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1038\/nature14539","volume":"521","author":"Y LeCun","year":"2015","unstructured":"LeCun, Y., Bengio, Y. & Hinton, G. Deep learning. Nature 521, 436\u2013444 (2015).","journal-title":"Nature"},{"key":"1116_CR23","doi-asserted-by":"publisher","first-page":"1145","DOI":"10.1016\/S0031-3203(96)00142-2","volume":"30","author":"AP Bradley","year":"1997","unstructured":"Bradley, A. P. The use of the area under the ROC curve in the evaluation of machine learning algorithms. Pattern Recognit. 30, 1145\u20131159 (1997).","journal-title":"Pattern Recognit."},{"key":"1116_CR24","first-page":"18","volume":"2","author":"A Liaw","year":"2002","unstructured":"Liaw, A. et al. Classification and regression by randomForest. R News 2, 18\u201322 (2002).","journal-title":"R News"},{"key":"1116_CR25","doi-asserted-by":"crossref","unstructured":"Chen, T. & Guestrin, C. XGoost: a scalable tree boosting system. In Proc. 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining 785\u2013794 (ACM, 2016).","DOI":"10.1145\/2939672.2939785"},{"key":"1116_CR26","unstructured":"Chollet, F. Deep Learning With Python (Manning Publications, 2018)."},{"key":"1116_CR27","doi-asserted-by":"crossref","unstructured":"Barton, J. E., Wehner, W. P., Schuster, E., Felici, F. & Sauter, O. Simultaneous closed-loop control of the current profile and the electron temperature profile in the TCV tokamak. In American Control Conference (ACC) 3316\u20133321 (IEEE, 2015).","DOI":"10.1109\/ACC.2015.7171844"},{"key":"1116_CR28","doi-asserted-by":"publisher","first-page":"10D928","DOI":"10.1063\/1.3460456","volume":"81","author":"B Tobias","year":"2010","unstructured":"Tobias, B. et al. Commissioning of electron cyclotron emission imaging instrument on the DIII-D tokamak and first data. Rev. Sci. Instr. 81, 10D928 (2010).","journal-title":"Rev. Sci. Instr."},{"key":"1116_CR29","doi-asserted-by":"publisher","first-page":"055011","DOI":"10.1088\/0029-5515\/49\/5\/055011","volume":"49","author":"P Vries De","year":"2009","unstructured":"De Vries, P., Johnson, M., Segui, I. & Contributors, J. E. Statistical analysis of disruptions in JET. Nucl. Fusion 49, 055011 (2009).","journal-title":"Nucl. Fusion"},{"key":"1116_CR30","unstructured":"Goyal, P. et al. Accurate, large minibatch SGD: training ImageNet in 1 hour. Preprint at \nhttps:\/\/arxiv.org\/abs\/1706.02677\n\n (2017)."},{"key":"1116_CR31","doi-asserted-by":"crossref","unstructured":"Svyatkovskiy, A., Kates-Harbeck, J. & Tang, W. Training distributed deep recurrent neural networks with mixed precision on GPU clusters. In Proc. Machine Learning on HPC Environments 10 (ACM, 2017).","DOI":"10.1145\/3146347.3146358"},{"key":"1116_CR32","unstructured":"Top500 supercomputers. Available at \nhttps:\/\/www.top500.org\/lists\/2017\/11\/\n\n (2018\/01\/11)."},{"key":"1116_CR33","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1038\/nature14236","volume":"518","author":"V Mnih","year":"2015","unstructured":"Mnih, V. et al. Human-level control through deep reinforcement learning. Nature 518, 529\u2013523 (2015).","journal-title":"Nature"},{"key":"1116_CR34","first-page":"1","volume":"63","author":"R Coelho","year":"2013","unstructured":"Coelho, R. et al. Synthetic diagnostics in the European Union integrated tokamak modelling simulation platform. Fus. Sci. Technol. 63, 1\u20138 (2013).","journal-title":"Sci. Technol."},{"key":"1116_CR35","doi-asserted-by":"publisher","first-page":"102001","DOI":"10.1088\/1741-4326\/aa5e28","volume":"57","author":"X Litaudon","year":"2017","unstructured":"Litaudon, X. et al. Overview of the JET results in support to ITER. Nucl. Fusion 57, 102001 (2017).","journal-title":"Nucl. Fusion"},{"key":"1116_CR36","doi-asserted-by":"crossref","unstructured":"Deng, J. et al. Imagenet: a large-scale hierarchical image database. In IEEE Conf. on Computer Vision and Pattern Recognition 248\u2013255 (IEEE, 2009).","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"1116_CR37","unstructured":"Zavaryaev, V. et al. in Plasma Diagnostics (eds Kikuchi, M., Lackner, K. & Tran, M. Q.) Ch. 4, 360\u2013534 (International Atomic Energy Agency, 2012)."},{"key":"1116_CR38","doi-asserted-by":"publisher","first-page":"1055","DOI":"10.1088\/0029-5515\/38\/7\/308","volume":"38","author":"J Ferron","year":"1998","unstructured":"Ferron, J. et al. Real time equilibrium reconstruction for tokamak discharge control. Nucl. Fusion 38, 1055 (1998).","journal-title":"Nucl. Fusion"},{"key":"1116_CR39","doi-asserted-by":"crossref","unstructured":"Alonso, J. et al. Fast visible camera installation and operation in JET. In AIP Conference Proceedings Vol. 988, 185\u2013188 (AIP, 2008).","DOI":"10.1063\/1.2905063"},{"key":"1116_CR40","unstructured":"Zadrozny, B., Langford, J. & Abe, N. Cost-sensitive learning by cost-proportionate example weighting. In Third IEEE International Conference on Data Mining 435\u2013442 (IEEE, 2003)."},{"key":"1116_CR41","doi-asserted-by":"publisher","first-page":"485","DOI":"10.13182\/FST15-167","volume":"69","author":"R Moreno","year":"2016","unstructured":"Moreno, R. et al. Disruption prediction on JET during the ILW experimental campaigns. Fus. Sci. Technol. 69, 485\u2013494 (2016).","journal-title":"Fus. Sci. Technol."},{"key":"1116_CR42","unstructured":"Maas, A. L. et al. Learning word vectors for sentiment analysis. In Proc. 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies Vol. 1 142\u2013150 (Association for Computational Linguistics, 2011)."},{"key":"1116_CR43","first-page":"313","volume":"19","author":"MP Marcus","year":"1993","unstructured":"Marcus, M. P., Marcinkiewicz, M. A. & Santorini, B. Building a large annotated corpus of English: the Penn Treebank. Comput. Linguist. 19, 313\u2013330 (1993).","journal-title":"Comput. Linguist."},{"key":"1116_CR44","unstructured":"Kates-Harbeck, J. & Svyatkovskiy, A. FRNN Codebase. https:\/\/github.com\/PPPLDeepLearning\/plasma-python (2017).\u00a0"},{"key":"1116_CR45","unstructured":"Chollet, F. et al. Keras. \nhttps:\/\/github.com\/fchollet\/keras\n\n (2015)."},{"key":"1116_CR46","unstructured":"Abadi, M. et al. Tensorflow: large-scale machine learning on heterogeneous distributed systems. Preprint at\u00a0\nhttps:\/\/arxiv.org\/abs\/1603.04467\n\n (2016)."},{"key":"1116_CR47","unstructured":"Graves, A. Generating sequences with recurrent neural networks. Preprint at\u00a0\nhttps:\/\/arxiv.org\/abs\/1308.0850\n\n (2013)."},{"key":"1116_CR48","unstructured":"Dean, J. et al. Large scale distributed deep networks. In Proc. 25th Internation Conference on Neural Information Processing Systems, vol. 1 1223\u20131231 (2012)."},{"key":"1116_CR49","unstructured":"Chetlur, S. et al. cuDNN: efficient primitives for deep learning. Preprint at\u00a0\nhttps:\/\/arxiv.org\/abs\/1410.0759\n\n (2014)."},{"key":"1116_CR50","doi-asserted-by":"crossref","unstructured":"Khomenko, V., Shyshkov, O., Radyvonenko, O. & Bokhan, K. Accelerating recurrent neural network training using sequence bucketing and multi-GPU data parallelization. In IEEE First International Conference on Data Stream Mining & Processing (DSMP) 100\u2013103 (IEEE, 2016).","DOI":"10.1109\/DSMP.2016.7583516"},{"key":"1116_CR51","unstructured":"Ruder, S. An overview of gradient descent optimization algorithms. Preprint at\u00a0\nhttps:\/\/arxiv.org\/abs\/1609.04747\n\n (2016)."},{"key":"1116_CR52","first-page":"27","volume":"2","author":"C-C Chang","year":"2011","unstructured":"Chang, C.-C. & Lin, C.-J. LIBSVM: a library for support vector machines. ACM Trans. Intell. Syst. Technol. 2, 27 (2011).","journal-title":"Syst. Technol."},{"key":"1116_CR53","first-page":"2825","volume":"12","author":"F Pedregosa","year":"2011","unstructured":"Pedregosa, F. et al. Scikit-learn: machine learning in Python. J. Mach. Learn. Res. 12, 2825\u20132830 (2011).","journal-title":"J. Mach. Learn. Res."},{"key":"1116_CR54","unstructured":"Das, D. et al. Distributed deep learning using synchronous stochastic gradient descent. Preprint at\u00a0\nhttps:\/\/arxiv.org\/abs\/1602.06709\n\n (2016)."},{"key":"1116_CR55","unstructured":"Wu, R., Yan, S., Shan, Y., Dang, Q. & Sun, G. Deep image: scaling up image recognition. Preprint at\u00a0\nhttps:\/\/arxiv.org\/abs\/1501.02876\n\n (2015)."},{"key":"1116_CR56","unstructured":"Chen, T. et al. MXNet: A flexible and efficient machine learning library for heterogeneous distributed systems. Preprint at\u00a0\nhttps:\/\/arxiv.org\/abs\/1512.01274\n\n (2015)."},{"key":"1116_CR57","unstructured":"Titan: advancing the era of accelerated computing. Oak Ridge National Laboratory \nhttps:\/\/www.olcf.ornl.gov\/olcf-resources\/compute-systems\/titan\/\n\n (accessed 2 April 2018)."},{"key":"1116_CR58","unstructured":"Morgan, T. P. Japan keeps accelerating with Tsubame 3.0 AI supercomputer. The Next Platform \nhttps:\/\/www.nextplatform.com\/2017\/02\/17\/japan-keeps-accelerating-tsubame-3-0-ai-supercomputer\/\n\n (accessed 2 April 2018)."},{"key":"1116_CR59","unstructured":"Summit: Oak Ridge National Laboratory\u2019s 200 PetaFlop Supercomputer. Oak Ridge National Laboratory (\nhttps:\/\/www.olcf.ornl.gov\/olcf-resources\/compute-systems\/summit\/\n\n (accessed 2 April 2018)."},{"key":"1116_CR60","doi-asserted-by":"crossref","unstructured":"Smith, L. N. Cyclical learning rates for training neural networks. In 2017 IEEE Winter Conf. on Applications of Computer Vision 464\u2013472 (IEEE, 2017).","DOI":"10.1109\/WACV.2017.58"},{"key":"1116_CR61","unstructured":"Kingma, D. & Ba, J. Adam: a method for stochastic optimization. Preprint at\u00a0\nhttps:\/\/arxiv.org\/abs\/1412.6980\n\n (2014)."},{"key":"1116_CR62","unstructured":"Gentile, C. & Warmuth, M. K. Linear hinge loss and average margin. In Proc. 1998 Conf. on Advances in Neural Information Processing Systems 225\u2013231 (MIT Press, 1999)."}],"container-title":["Nature"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/www.nature.com\/articles\/s41586-019-1116-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/www.nature.com\/articles\/s41586-019-1116-4","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/www.nature.com\/articles\/s41586-019-1116-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,5,20]],"date-time":"2023-05-20T21:54:55Z","timestamp":1684619695000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41586-019-1116-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,4]]},"references-count":62,"journal-issue":{"issue":"7753","published-print":{"date-parts":[[2019,4]]}},"alternative-id":["1116"],"URL":"https:\/\/doi.org\/10.1038\/s41586-019-1116-4","relation":{},"ISSN":["0028-0836","1476-4687"],"issn-type":[{"value":"0028-0836","type":"print"},{"value":"1476-4687","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,4]]},"assertion":[{"value":"16 May 2018","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 January 2019","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 April 2019","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}]}}