Data-Driven Design of Stellarators

Stellarators are 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. Machine learning (ML) has the potential to mitigate this problem by providing surrogates and generative procedures for rapidly designing stellarator configurations. In this talk, we will discuss recent advancements in the development of large scale datasets for stellarator design, and show how generative models have been used to accelerate the design process.