[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-127498-en":3,"doc-seo-127498-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},127498,962085662650,"Jiven","https://ap-avatar.wpscdn.com/davatar_29158cc5080c5b710cf443261637dec0",8,"Research & Report","Performance Comparison of Machine Learning Disruption Predictors at JET","Reliable disruption prediction (DP) and disruption mitigation are essential for international thermonuclear experimental reactor operations and next-generation fusion systems such as DEMO and CFETR. Over the past two decades, many data-driven DP systems have been developed, improving performance through better diagnostics, input features, and more powerful modelling techniques. Yet proposals have rarely been compared directly. This work contrasts DP models on the same JET real-time signals using common performance indices, including a conventional MLP-NN and more advanced GTM- and CNN-based approaches, with results thoroughly discussed to expose strengths, limitations, and guidance for plasma-protection needs.","applied sciences  \nArticle  \nPerformance Comparison of Machine Learning Disruption Predictors at JET  \nEnrico Aymerich 1, *, Barbara Cannas 1, Fabio Pisano 1, Giuliana Sias 1, Carlo Sozzi 2, Chris Stuart 3, Pedro Carvalho 3, Alessandra Fanni 1 and the JET Contributors †  \nCitation: Aymerich, E.; Cannas, B.; Pisano, F.; Sias, G.; Sozzi, C.; Stuart, C.; Carvalho, P.; Fanni, A.; the JET Contributors. Performance Comparison of Machine Learning Disruption Predictors at JET. Appl. Sci. 2023, 13, 2006. [https://doi.org/](https://doi.org/)[ ](https://doi.org/)[10.3390/app13032006](10.3390/app13032006)  \nAcademic Editor: Xianpeng Wang  \nReceived: 29 December 2022  \nRevised: 26 January 2023  \nAccepted: 1 February 2023  \nPublished: 3 February 2023  \nCopyright: © 2023 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license ([https://](https://)[ ](https://)[creativecommons.org/licenses/by/](creativecommons.org/licenses/by/)[ ](creativecommons.org/licenses/by/)[4.0/](4.0/)) .  \n1 Department of Electrical and Electronic Engineering, University of Cagliari, 09123 Cagliari, Italy  \n2 Istituto per la Scienza e Tecnologia dei Plasmi, Consiglio Nazionale Delle Ricerche, Via R. Cozzi, 53,  \n20125 Milano, Italy  \n3 UK Atomic Energy Authority, Culham Science Centre, Abingdon OX14 3DB, UK  \n* Correspondence: [enrico.aymerich@unica.it](enrico.aymerich@unica.it); Tel.: +39-0706755871 † See the author list of J. Mailloux et al. 2022 Nucl. Fusion 62 042026 .  \nAbstract: Reliable disruption prediction (DP) and disruption mitigation systems are considered unavoidable during international thermonuclear experimental reactor (ITER) operations and in the view of the next fusion reactors such as the DEMOnstration Power Plant (DEMO) and China Fusion Engineering Test Reactor (CFETR) . In the last two decades, a great number of DP systems have been developed using data-driven methods. The performance of the DP models has been improved over the years both for a more appropriate choice of diagnostics and input features and for the availability of increasingly powerful data-driven modelling techniques. However, a direct comparison among the proposals has not yet been conducted. Such a comparison is mandatory, at least for the same device, to learn lessons from all these efforts and finally choose the best set of diagnostic signals and the best modelling approach. A first effort towards this goal is made in this paper, where different DP models will be compared using the same performance indices and the same device. In particular, the performance of a conventional Multilayer Perceptron Neural Network (MLP-NN) model is compared with those of two more sophisticated models, based on Generative Topographic Mapping (GTM) and Convolutional Neural Networks (CNN), on the same real time diagnostic signals from several experiments at the JET tokamak. The most common performance indices have been used to compare the different DP models and the results are deeply discussed. The comparison confirms the soundness of all the investigated machine learning approaches and the chosen diagnostics, enables us to highlight the pros and cons of each model, and helps to consciously choose the approach that best matches with the plasma protection needs.  \nKeywords: tokamak; disruption prediction; machine learning; deep learning; data analysis; plasma diagnostics  \n1. Introduction  \nTokamak nuclear fusion devices suffer from several instabilities that may interact nonlinearly with each other, degenerating into the ultimate plasma destabilization and possibly into a disruption [1] . During a disruption, the plasma current drops to within a few milliseconds generating huge electromechanical and thermal forces, which may severely damage the plasma-facing components (PFC) . Therefore, a strict requirement to develop a strategy for disruption prevention is needed, to contro","cbCaivgDTZZGn5yl","https://ap.wps.com/l/cbCaivgDTZZGn5yl","pdf",3849957,1,20,"English","en",105,"# Introduction\n## Disruption prediction need and motivation\n## Data-driven vs physics-based DP models\n# Performance comparison approach\n## Models evaluated (MLP-NN, GTM, CNN)\n## Shared diagnostics and real-time signals\n## Performance indices and discussion","[{\"question\":\"Why is disruption prediction (DP) important for tokamak operations?\",\"answer\":\"Disruptions can cause rapid plasma-current collapse and generate large electromechanical and thermal forces that may damage plasma-facing components. DP supports prevention and control throughout the discharge duration.\"},{\"question\":\"What gap does this paper address in disruption-prediction research?\",\"answer\":\"Different DP proposals have often not been compared directly, which limits lessons learned and the ability to select the best diagnostic signals and modelling approach.\"},{\"question\":\"Which disruption-prediction models are compared at JET in this study?\",\"answer\":\"The study compares a conventional Multilayer Perceptron Neural Network (MLP-NN) with more advanced models based on Generative Topographic Mapping (GTM) and Convolutional Neural Networks (CNN) using the same real-time JET diagnostic signals.\"}]","Performance Comparison of Machine Learning Disruption Predictors at JET | PDF",1785939482,50,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"performance-comparison-of-machine-learning-disruption-predictors-at-jet","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/performance-comparison-of-machine-learning-disruption-predictors-at-jet/127498/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-05",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"Why is disruption prediction (DP) important for tokamak operations?","Question",{"text":75,"@type":76},"Disruptions can cause rapid plasma-current collapse and generate large electromechanical and thermal forces that may damage plasma-facing components. DP supports prevention and control throughout the discharge duration.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What gap does this paper address in disruption-prediction research?",{"text":80,"@type":76},"Different DP proposals have often not been compared directly, which limits lessons learned and the ability to select the best diagnostic signals and modelling approach.",{"name":82,"@type":73,"acceptedAnswer":83},"Which disruption-prediction models are compared at JET in this study?",{"text":84,"@type":76},"The study compares a conventional Multilayer Perceptron Neural Network (MLP-NN) with more advanced models based on Generative Topographic Mapping (GTM) and Convolutional Neural Networks (CNN) using the same real-time JET diagnostic signals.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,114,119,122,126,129,133],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":29,"slug":113},6,"Technology","technology",{"id":115,"doc_module":4,"doc_module_name":46,"category_name":116,"show_sort_weight":117,"slug":118},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":21,"slug":125},9,"Religion & Spirituality","religion-spirituality",{"id":21,"doc_module":4,"doc_module_name":46,"category_name":127,"show_sort_weight":21,"slug":128},"World Cup","world-cup",{"id":130,"doc_module":4,"doc_module_name":46,"category_name":131,"show_sort_weight":130,"slug":132},10,"Lifestyle","lifestyle",{"id":134,"doc_module":4,"doc_module_name":46,"category_name":135,"show_sort_weight":106,"slug":136},19,"General","general"]