Gaussian Processes for Surrogate Modeling of Discharged Fuel Nuclide Compositions

TL;DR

This paper demonstrates that Gaussian Processes can serve as effective surrogate models for predicting spent nuclear fuel compositions, offering uncertainty estimates and outperforming traditional spline interpolation, especially in higher-dimensional parameter spaces.

Contribution

The study introduces GP-based surrogate modeling for nuclear fuel composition prediction, comparing its performance with spline interpolation and analyzing sampling strategies.

Findings

GP models outperform spline interpolation in accuracy

GP provides reliable uncertainty estimates

Quasirandom sampling is more effective in higher dimensions

Abstract

Several applications such as nuclear forensics, nuclear fuel cycle simulations and sensitivity analysis require methods to quickly compute spent fuel nuclide compositions for various irradiation histories. Traditionally, this has been done by interpolating between one-group cross-sections that have been pre-computed from nuclear reactor simulations for a grid of input parameters, using fits such as Cubic Spline. We propose the use of Gaussian Processes (GP) to create surrogate models, which not only provide nuclide compositions, but also the gradient and estimates of their prediction uncertainty. The former is useful for applications such as forward and inverse optimization problems, the latter for uncertainty quantification applications. For this purpose, we compare GP-based surrogate model performance with Cubic- Spline-based interpolators based on infinite lattice simulations of a CANDU 6 nuclear reactor using the SERPENT 2 code, considering burnup and temperature as input parameters. Additionally, we compare the performance of various grid sampling schemes to quasirandom sampling based on the Sobol sequence. We find that GP-based models perform significantly better in predicting spent fuel compositions than Cubic-Spline-based models, though requiring longer computational runtime. Furthermore, we show that the predicted nuclide uncertainties are reasonably accurate. While in the studied two-dimensional case, grid- and quasirandom sampling provide similar results, quasirandom sampling will be a more effective strategy in higher dimensional cases.