Deployment of neural-network-based neutron microscopic cross sections in the Griffin reactor physics application

Abstract

The use of reduced-order models for the efficient evaluation of microscopic cross sections has shown significant promise in Griffin reactor physics applications. Among various reduced-order techniques, neural network-based models stand out for their exceptional scalability, memory efficiency, prediction speed, and compatibility with the MOOSE (Multiphysics Object-Oriented Simulation Environment) framework. This work develops capabilities into the Griffin reactor physics application to utilize neural networks to predict microscopic cross-section parametric spaces for a variety of nuclides. The LibTorch interface enables Griffin’s MOOSE based materials to interact with LibTorch-trained models, allowing for the evaluation of complex microscopic cross-section spaces, which are then used to evaluate the neutronic properties of the Griffin finite-element model. This study benchmarks traditional ISOXML-formatted tabulation libraries against neural-network-based models for 279 nuclides on 20,160 grid points for zero- and two-dimensional reactor models. Benchmark metrics include the fundamental mode eigenvalue, fission and absorption rates, and various temperature coefficients of reactivity (isothermal, fuel, and moderator). From the perspective of storage space, the complete set of LibTorch models uses 11 MB, compared to the 10 GB for the ISOXML multigroup library that covers the same grid space. For the two-dimensional performance case considered in Griffin, the LibTorch model uses 97% less random access memory than the reference ISOXML dataset while runtime increases by a factor of 3 when using the LibTorch model compared to the ISOXML dataset with multilinear interpolation. The LibTorch model consistently yields errors within 0.01% for most analyzed quantities except for the temperature coefficients of reactivity where the maximum discrepancies are up to 0.3 $\frac{\text{pcm}}{\text{K}}$. Due to the neural network attempting to best predict quantities with no regard for a positive or negative bias for any given quantity, predictions may experience random fluctuations, resulting in both positive and negative errors. Future work will entail both a depletion and coupled transient analysis to determine the predictive capabilities of Griffin with neural-network-based cross sections.