Regulation compliant AI for fusion: explainable image-based feedback control of divertor detachment in DIII-D tokamak

Nathaniel Chen, C.s. Byun, Azarakhsh Jalalvand, S.k. Kim, Andrew Rothstein, F. Scotti, S. L. Allen, D. Eldon, Keith Erickson, Egemen Kolemen

Abstract

Abstract While artificial intelligence (AI) has been promising for fusion control, its inherent black-box nature will make compliant implementation in regulatory environments a challenge. This study implements and validates a real-time AI-enabled linear and interpretable control system for successful divertor detachment control with the DIII-D lower divertor camera. Using D 2 gas, we demonstrate successful feedback divertor detachment control with a mean absolute difference of 2% from the target for both detachment and reattachment. This automatic training and linear processing framework can be extended to any image-based diagnostic for future fusion reactors.
BibTeX
@inproceedings{chen2026regulation,
  author = {Nathaniel Chen and C.S. Byun and Azarakhsh Jalalvand and S.K. Kim and Andrew Rothstein and F. Scotti and S. L. Allen and D. Eldon and Keith Erickson and Egemen Kolemen},
  title = {{Regulation compliant AI for fusion: explainable image-based feedback control of divertor detachment in DIII-D tokamak}},
  booktitle = {Nuclear},
  year = {2026},
  doi = {10.1088/1741-4326/ae3972},
}
Figure