pcNN-SN: a physics-enhanced predictor-corrector neural network algorithm coupled with the discrete ordinates method for neutron transport equations
Abstract
Super-resolution machine learning methods hold promise for addressing the high computational costs associated with high-dimensional features in traditional transport simulations. This paper proposes a physics-enhanced neural network coupling algorithm for discrete ordinates (SN) transport calculations. Based on high- and low-accuracy data, we develop a predictor-corrector neural network (pcNN) to predict correction factors for coarse-grid solutions. Based on transport equations, local physical features containing subgrid-scale information are selected as network inputs. Dimensionless transformation of physical quantities reduces the input space dimensionality and narrows parameter distributions, facilitating network training. Physical constraints are incorporated into the network model, and the corrected solution retains its original conservation properties. pcNN and SN transport sweeps are internally coupled, and numerical solutions are corrected online. Numerical results demonstrate that this algorithm can effectively improve coarse-grid solutions to achieve a level of accuracy comparable to that of fine-grid results. The physics-based network design enables the model to demonstrate a certain degree of reusability under different computational conditions. Compared to mesh refinement, the pcNN-SN algorithm reduces the computation time for the three-dimensional test problem by more than 60%.
Related
- Fast quantum algorithm for differential equations
- Coupled dynamical Boltzmann transport equations with long-range electron-phonon and electron-electron interactions in two-dimensional materials
- Quantum algorithm for high-dimensional nonlinear stochastic differential equations based on Carleman linearization
- A Quantum Algorithm for st-Transport on Flat Connection Graphs
- Quantum mechanics for classical transport equations
BibTeX
@misc{liu2026pcnnsn,
title = {{pcNN-SN: a physics-enhanced predictor-corrector neural network algorithm coupled with the discrete ordinates method for neutron transport equations}},
author = {Cong Liu and Junxia Wei and Shuai Wang and Heng Yong},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.20619},
eprint = {2610.20619},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.20619},
}
RIS
TY - UNPB
TI - pcNN-SN: a physics-enhanced predictor-corrector neural network algorithm coupled with the discrete ordinates method for neutron transport equations
AU - Cong Liu
AU - Junxia Wei
AU - Shuai Wang
AU - Heng Yong
PY - 2026
DA - 2026/10/01
PB - arXiv
DO - 10.48550/arxiv.2610.20619
UR - https://arxiv.org/abs/2610.20619
AB - Super-resolution machine learning methods hold promise for addressing the high computational costs associated with high-dimensional features in traditional transport simulations. This paper proposes a physics-enhanced neural network coupling algorithm for discrete ordinates (SN) transport calculations. Based on high- and low-accuracy data, we develop a predictor-corrector neural network (pcNN) to predict correction factors for coarse-grid solutions. Based on transport equations, local physical features containing subgrid-scale information are selected as network inputs. Dimensionless transformation of physical quantities reduces the input space dimensionality and narrows parameter distributions, facilitating network training. Physical constraints are incorporated into the network model, and the corrected solution retains its original conservation properties. pcNN and SN transport sweeps are internally coupled, and numerical solutions are corrected online. Numerical results demonstrate that this algorithm can effectively improve coarse-grid solutions to achieve a level of accuracy comparable to that of fine-grid results. The physics-based network design enables the model to demonstrate a certain degree of reusability under different computational conditions. Compared to mesh refinement, the pcNN-SN algorithm reduces the computation time for the three-dimensional test problem by more than 60%.
ER -