Generative modeling for fusion: a large-scale benchmark of stellarator fast-ion simulations
Abstract
Stellarators offer a promising magnetic confinement approach for achieving controlled nuclear fusion. However, stellarator design remains challenging, as evaluating configuration performance requires computationally expensive, high-fidelity simulations. In particular, key performance metrics derived from guiding center simulations are costly to include directly in the design optimization loop, and are almost exclusively used as diagnostics. Machine learning has the potential to advance fusion research by enabling rapid generation and evaluation of new stellarator configurations. Effectively applying ML for fusion demands large-scale datasets that capture both design diversity and high-fidelity simulation outputs. In this work, we introduce the Benchmark of Stellarator Simulations (BoSS), a dataset of stellarator designs paired with guiding center simulation results and trajectories. The BoSS is the first large-scale dataset of guiding center simulations, containing simulation data for 180,000 distinct magnetohydrodynamic equilibria spanning a wide range of magnetic geometries and confinement properties. To exemplify the utility of ML to accelerate stellarator design, we formulate and address two sets of modeling tasks: generative modeling for designing stellarators with good particle confinement, and surrogate modeling for predicting stellarator heat deposition patterns and particle trajectories. The tasks reveal the potential impact ML can have in the stellarator field and important opportunities to improve the applicability of ML models in the sciences. Our baselines generate diverse, performant stellarators and provide useful surrogate predictions, and point to long-horizon trajectory forecasting and out-of-distribution generation as key directions for future work. The BoSS can be accessed through https://boss.flatironinstitute.org/.
Related
- Towards Stellarator Geometry Optimisation for Nuclear Fusion
- Numerical error analysis of EMC3-EIRENE simulations in the HSX stellarator
- Design and conceptual modeling of a tokamak-like X-point divertor for the Helios quasi-axisymmetric stellarator
- Deep Generative Crystal Structure Prediction: A Benchmark Study and a Controlled Test of Prototype Dependence
- Benchmark of First-Principles Titanium K-Edge X-Ray Absorption Spectral Simulations on Titanium-containing Oxides
BibTeX
@misc{padidar2026generative,
title = {{Generative modeling for fusion: a large-scale benchmark of stellarator fast-ion simulations}},
author = {Misha Padidar and Teresa Huang and Mark Goldstein and Michael Czekanski and Jeffrey Soules},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.37910},
eprint = {2610.37910},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.37910},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Generative modeling for fusion: a large-scale benchmark of stellarator fast-ion simulations
AU - Misha Padidar
AU - Teresa Huang
AU - Mark Goldstein
AU - Michael Czekanski
AU - Jeffrey Soules
PY - 2026
DA - 2026/10/27
PB - arXiv
DO - 10.48550/arxiv.2610.37910
UR - https://arxiv.org/abs/2610.37910
AB - Stellarators offer a promising magnetic confinement approach for achieving controlled nuclear fusion. However, stellarator design remains challenging, as evaluating configuration performance requires computationally expensive, high-fidelity simulations. In particular, key performance metrics derived from guiding center simulations are costly to include directly in the design optimization loop, and are almost exclusively used as diagnostics. Machine learning has the potential to advance fusion research by enabling rapid generation and evaluation of new stellarator configurations. Effectively applying ML for fusion demands large-scale datasets that capture both design diversity and high-fidelity simulation outputs. In this work, we introduce the Benchmark of Stellarator Simulations (BoSS), a dataset of stellarator designs paired with guiding center simulation results and trajectories. The BoSS is the first large-scale dataset of guiding center simulations, containing simulation data for 180,000 distinct magnetohydrodynamic equilibria spanning a wide range of magnetic geometries and confinement properties. To exemplify the utility of ML to accelerate stellarator design, we formulate and address two sets of modeling tasks: generative modeling for designing stellarators with good particle confinement, and surrogate modeling for predicting stellarator heat deposition patterns and particle trajectories. The tasks reveal the potential impact ML can have in the stellarator field and important opportunities to improve the applicability of ML models in the sciences. Our baselines generate diverse, performant stellarators and provide useful surrogate predictions, and point to long-horizon trajectory forecasting and out-of-distribution generation as key directions for future work. The BoSS can be accessed through https://boss.flatironinstitute.org/.
ER -