A procedure for rule extraction from a Self-Organising plasma disruption predictor for JET

In a previous paper, a Self-Organizing Map had proven to be able to identify the regions of the plasma operative space characterizing the pre-disruptive phase at JET without relying on any a priori information. One of the strengths of this disruption predictor lies in its inherent self-organization capability. The Self-Organizing Map discovers non-trivial relationships and captures the complicated interplay of device diagnostics on the internal plasma states directly from the experimental data. Moreover, the provided model allows the visualization of high-dimensional plasma parameters and facilitates easy interrogation of the model to understand the reasons behind its correlations. In this paper, an additional step is taken towards the interpretability of models for predicting disruptions by training a Decision Tree to classify the plasma states according to the interpretation provided by the Self-Organizing Map (stable or at high risk of disruptions). The Decision tree provides a set of rules which describe the transition of the plasma towards the pre-disruptive phase as visualized in the Self-Organizing Map. The obtained rules for the database explored in the study identify four regions in the map, two of which are at risk of disruption. These regions correspond to partitions of a 3D space based on the peaking factors of the core and divertor radiation, as well as the Locked Mode. The agreement between the Self-Organizing Map answers and the rules supplied by the Decision Tree is confirmed by the comparison of the performance exhibited by the two models in the prediction of disruptions.

Authors

Institutions

Publication Details

Journal
Scientific Reports
Published
2026-04-10
DOI
https://doi.org/10.1038/s41598-026-38318-9
Primary Topic
Magnetic confinement fusion research
Type
article
Field-Weighted Citation Impact
0.00

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

A procedure for rule extraction from a Self-Organising plasma disruption predictor for JET

J. Alguacil, PG Bhat, M. Alonzo, H. Betar et al.
Scientific Reports
Magnetic confinement fusion research
article

A procedure for rule extraction from a Self-Organising plasma disruption predictor for JET

J. Alguacil, PG Bhat, M. Alonzo, H. Betar, F. Pisano, P. Aleynikov, G. Artaserse, M. Ariola, Muhammad Afzal, M. Bassan, R. Ambrosino, M. Berry, J. Bielecki, J.F. Artaud, M. Akhtar, V. Artigues, B. Bauvir, R. Bisson, R. Barnsley, C. Barcellona, N. Abid, S. Aleiferis, E. Alessi, I. Balboa, P. Batistoni, R. Bilato, M. Balden, Darren Beckett, G. Sias, J.M. Bentley, B. Cannas, G. Arnoux, Domenico Abate, Matthew Beidler, M. Bernert, F. Auriemma, L. Appel, Ö. Asztalos, E. Anderson Sundén, A. Ash, R. Albanese, Alessandra Fanni, E. Aymerich, Ioannis Antoniou, Edson Pantaleão Alves, Juan Ayllón, J. Banks, P. Bílková, S. Benkadda, M. Beurskens, Sarah Bickerton, M. Baruzzo, L. Bertalot, C. Bearcroft, P. Abreu, G. Birkenmeier, L. Baylor, A.Banon Navarro, L. Avotina, M. Angelone, D. Auld, M. Barnes, L. Bähner, O. Bardsley, A. Bleasdale, J.P.S. Bizarro, E. Bernard, Y. Austin, V.K. Bandaru, C. Aramunde, I. Ahmad, J. Alhage, J. Bernardo, P. Andrew, F. Bairaktaris, M. Beldishevski, M. Allinson, M. Ali, The JET contributors, W. Arter, L. Baumane, E. Belli, A. Baciero, F.J. Artola, C.F. Maggi, T. Biewer, O. Adabonyan, A. Batista, N. Bekris, P. Beaumont, H. Allen, Samuele Setzu, A. Begolli, P. Blatchford, N. Balshaw, C. Appelbee, F. Belli, C. Angioni
article en

Abstract

In a previous paper, a Self-Organizing Map had proven to be able to identify the regions of the plasma operative space characterizing the pre-disruptive phase at JET without relying on any a priori information. One of the strengths of this disruption predictor lies in its inherent self-organization capability. The Self-Organizing Map discovers non-trivial relationships and captures the complicated interplay of device diagnostics on the internal plasma states directly from the experimental data. Moreover, the provided model allows the visualization of high-dimensional plasma parameters and facilitates easy interrogation of the model to understand the reasons behind its correlations. In this paper, an additional step is taken towards the interpretability of models for predicting disruptions by training a Decision Tree to classify the plasma states according to the interpretation provided by the Self-Organizing Map (stable or at high risk of disruptions). The Decision tree provides a set of rules which describe the transition of the plasma towards the pre-disruptive phase as visualized in the Self-Organizing Map. The obtained rules for the database explored in the study identify four regions in the map, two of which are at risk of disruption. These regions correspond to partitions of a 3D space based on the peaking factors of the core and divertor radiation, as well as the Locked Mode. The agreement between the Self-Organizing Map answers and the rules supplied by the Decision Tree is confirmed by the comparison of the performance exhibited by the two models in the prediction of disruptions.

Scientific Reports
Karlsruhe Institute of Technology (DE), ITER (FR), National Agency for New Technologies, Energy and Sustainable Economic Development (IT), Uppsala University (SE), Oak Ridge National Laboratory (US), Centre National de la Recherche Scientifique (FR), University of Padua (IT), University of Cagliari (IT), National Technical University of Athens (GR), Universidad Nacional de Educación a Distancia (ES), Aix-Marseille Université (FR), Commissariat à l'Énergie Atomique et aux Énergies Alternatives (FR), Ghent University (BE), University of Catania (IT), University of Oxford (GB), Istituto Nazionale di Fisica Nucleare, Sezione di Padova (IT), Institute of Nuclear Physics, Polish Academy of Sciences (PL), CEA Cadarache (FR), Czech Academy of Sciences, Institute of Plasma Physics (CZ), Max Planck Institute for Plasma Physics (DE), Instituto Superior de Educação e Ciências (PT), Institut Jean Lamour (FR), Institute for the Science and Technology of Plasmas (IT), Consorzio CREO (Italy) (IT), HUN-REN Centre for Energy Research (HU), United Kingdom Atomic Energy Authority (GB), General Atomics (United States) (US), Comenius University Bratislava (SK), Universidad de Sevilla (ES), KTH Royal Institute of Technology (SE), Université de Lorraine (FR), University of Latvia (LV)
EUROfusion, European Commission, Euratom Research and Training Programme
Peace, Justice and strong institutions
Openalex Percentile: Top 25%
Magnetic confinement fusion research
DOIOpen Access PDFOpenAlex
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.