PreprintCC BY 4.0arXiv
Towards Stellarator Geometry Optimisation for Nuclear Fusion
Abstract
We present a local geometry refinement method and a 2D latent representation that took us to the top of the ConStellaration leaderboard on the geometric task in May 2026.
Related
- Generative modeling for fusion: a large-scale benchmark of stellarator fast-ion simulations
- Geometry Parameterisation via a Structural Modal Basis for Aerodynamic Shape Optimisation
- Towards Large-Scale Heterogeneous Data Organization for Scientific Foundation Models: A Nuclear Fusion Case Study
- Maximization of nuclear fusion reactivity via optimal energy distributions
- Science of Nuclear Fusion: Insights and Ideas
BibTeX
@misc{weißberg2026towards,
title = {{Towards Stellarator Geometry Optimisation for Nuclear Fusion}},
author = {Tobias Weißberg and Moritz Heep and Zorah Lähner and Florian Bernard},
howpublished = {arXiv},
year = {2026},
month = aug,
doi = {10.48550/arxiv.2608.28224},
eprint = {2608.28224},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2608.28224},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Towards Stellarator Geometry Optimisation for Nuclear Fusion
AU - Tobias Weißberg
AU - Moritz Heep
AU - Zorah Lähner
AU - Florian Bernard
PY - 2026
DA - 2026/08/28
PB - arXiv
DO - 10.48550/arxiv.2608.28224
UR - https://arxiv.org/abs/2608.28224
AB - We present a local geometry refinement method and a 2D latent representation that took us to the top of the ConStellaration leaderboard on the geometric task in May 2026.
ER -