Fast Regression of the Tritium Breeding Ratio in Fusion Reactors

TL;DR

This paper develops and evaluates surrogate models, especially neural networks, to rapidly approximate the tritium breeding ratio in fusion reactors, significantly reducing computational costs while maintaining high accuracy.

Contribution

It introduces a novel adaptive sampling algorithm and compares multiple surrogate models, highlighting the neural network's superior speed and accuracy for TBR prediction.

Findings

Neural network surrogate achieved R^2=0.985.

Prediction time reduced to 0.898 microseconds.

Speedup of approximately 8 million times compared to Monte Carlo model.

Abstract

The tritium breeding ratio (TBR) is an essential quantity for the design of modern and next-generation D-T fueled nuclear fusion reactors. Representing the ratio between tritium fuel generated in breeding blankets and fuel consumed during reactor runtime, the TBR depends on reactor geometry and material properties in a complex manner. In this work, we explored the training of surrogate models to produce a cheap but high-quality approximation for a Monte Carlo TBR model in use at the UK Atomic Energy Authority. We investigated possibilities for dimensional reduction of its feature space, reviewed 9 families of surrogate models for potential applicability, and performed hyperparameter optimisation. Here we present the performance and scaling properties of these models, the fastest of which, an artificial neural network, demonstrated $R^2=0.985$ and a mean prediction time of $0.898\ \mu\mathrm{s}$, representing a relative speedup of $8\cdot 10^6$ with respect to the expensive MC model. We further present a novel adaptive sampling algorithm, Quality-Adaptive Surrogate Sampling, capable of interfacing with any of the individually studied surrogates. Our preliminary testing on a toy TBR theory has demonstrated the efficacy of this algorithm for accelerating the surrogate modelling process.