Using Deep Learning to Design High Aspect Ratio Fusion Devices

TL;DR

This paper introduces a machine learning approach using mixture density networks to efficiently generate fusion device configurations with desired properties, reducing reliance on costly simulations.

Contribution

It presents a novel probabilistic inverse design method for fusion devices, enabling reliable generation of configurations with targeted confinement characteristics.

Findings

Machine learning models can predict fusion device configurations with desired properties.

Probabilistic approach captures the non-uniqueness of inverse design solutions.

Configurations can be generated reliably using the proposed method.

Abstract

The design of fusion devices is typically based on computationally expensive simulations. This can be alleviated using high aspect ratio models that employ a reduced number of free parameters, especially in the case of stellarator optimization where non-axisymmetric magnetic fields with a large parameter space are optimized to satisfy certain performance criteria. However, optimization is still required to find configurations with properties such as low elongation, high rotational transform, finite plasma beta, and good fast particle confinement. In this work, we train a machine learning model to construct configurations with favorable confinement properties by finding a solution to the inverse design problem, that is, obtaining a set of model input parameters for given desired properties. Since the solution of the inverse problem is non-unique, a probabilistic approach, based on mixture density networks, is used. It is shown that optimized configurations can be generated reliably using this method.