{"paper":{"title":"Real-time virtual circuits for plasma shape control via neural network emulators","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Neural network emulators produce accurate real-time virtual circuits to control tokamak plasma shape.","cross_cats":["cs.LG"],"primary_cat":"physics.plasm-ph","authors_text":"Adriano Agnello, Alasdair Ross, Aran Garrod, Charles Vincent, George K. Holt, Graham McArdle, Kamran Pentland, Nicola C. Amorisco, Pedro Cavestany, Timothy Nunn","submitted_at":"2026-05-14T15:15:43Z","abstract_excerpt":"Reliable position and shape control in tokamak plasmas requires accurate real-time regulation of several strongly coupled shape parameters. The control vectors that disentangle these couplings, referred to as \\textit{virtual circuits} (VCs), enable independent shape parameter control for a specific Grad--Shafranov (GS) equilibrium. Numerical calculation of VCs is not currently feasible in real time, therefore VCs are usually computed prior to each experiment, using a small number of reference GS equilibria sampled along the desired scenario trajectory, with each VC used to control the plasma w"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"The neural-network-based approach delivers high accuracy and orthogonality across a diverse range of equilibria. This work establishes the physical validity of emulated VCs as a scalable and general alternative to schedules of precomputed VCs.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That neural networks trained exclusively on simulated Grad-Shafranov equilibria will generalize accurately enough to real experimental plasmas in MAST-U to produce usable virtual circuits in real time.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Neural network emulators of Grad-Shafranov equilibria enable real-time derivation of virtual circuits that disentangle plasma shape control parameters in tokamaks.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Neural network emulators produce accurate real-time virtual circuits to control tokamak plasma shape.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"60f5472672e0212b9ee5ebc0574b62860915900cd459300d155b0f991e2252a3"},"source":{"id":"2605.14939","kind":"arxiv","version":1},"verdict":{"id":"f0bcbb6b-66e1-41e7-9858-bf6e40d6ce09","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T14:24:13.564776Z","strongest_claim":"The neural-network-based approach delivers high accuracy and orthogonality across a diverse range of equilibria. This work establishes the physical validity of emulated VCs as a scalable and general alternative to schedules of precomputed VCs.","one_line_summary":"Neural network emulators of Grad-Shafranov equilibria enable real-time derivation of virtual circuits that disentangle plasma shape control parameters in tokamaks.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That neural networks trained exclusively on simulated Grad-Shafranov equilibria will generalize accurately enough to real experimental plasmas in MAST-U to produce usable virtual circuits in real time.","pith_extraction_headline":"Neural network emulators produce accurate real-time virtual circuits to control tokamak plasma shape."},"references":{"count":39,"sample":[{"doi":"","year":2008,"title":"M. Ariola and A. Pironti.Magnetic Control of Tokamak Plasmas. Advances in Industrial Control. Springer London, 2008","work_id":"4b71b566-fb81-4f7a-8139-7e7b40b05442","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2020,"title":"Walker, Peter De Vries, Federico Felici, and Eugenio Schuster","work_id":"44b9a816-8137-4496-a77f-18f232f3259f","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"Design and implementation of a model-based hierarchical architecture for plasma shape control in the tcv tokamak","work_id":"6e8b9f33-8d4d-42d4-8b0f-a85b0fedd974","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2020,"title":"The mast upgrade plasma control system.Fusion Engineering and Design, 159:111764, 2020","work_id":"3c723623-7e6e-42d8-aeb4-315cb26f1660","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2026,"title":"J. T. Wai, M. D. Boyer, D. J. Battaglia, F. Carpanese, F. Felici, W. P. Wehner, A. S. Welander, and E. Kolemen. A tutorial on inversion-based shape control with design application to nstx-u, 2026","work_id":"ff7cef4f-e6a5-463b-916a-816e6426d263","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":39,"snapshot_sha256":"3bd9459b2826fd884c106d31917b1225c599933d2c225c851895e3b86ba0ed95","internal_anchors":1},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"}