Neurons for Neutrons: A Transformer Model for Computation Load Estimation on Domain-Decomposed Neutron Transport Problems
This work addresses a domain-specific bottleneck for researchers in neutron transport simulations by providing a faster alternative to repeated small-scale simulations.
The paper tackles the problem of time-consuming small-scale simulations for determining optimal processor allocation in domain-decomposed neutron transport problems by proposing a Transformer model that predicts subdomain computation loads, achieving 98.2% accuracy and eliminating the need for these simulations.
Domain decomposition is a technique used to reduce memory overhead on large neutron transport problems. Currently, the optimal load-balanced processor allocation for these domains is typically determined through small-scale simulations of the problem, which can be time-consuming for researchers and must be repeated anytime a problem input is changed. We propose a Transformer model with a unique 3D input embedding, and input representations designed for domain-decomposed neutron transport problems, which can predict the subdomain computation loads generated by small-scale simulations. We demonstrate that such a model trained on domain-decomposed Small Modular Reactor (SMR) simulations achieves 98.2% accuracy while being able to skip the small-scale simulation step entirely. Tests of the model's robustness on variant fuel assemblies, other problem geometries, and changes in simulation parameters are also discussed.