Back to feed
arXiv cs.LG
arXiv cs.LG
7/23/2026
Neural Operator Surrogates for Two-Dimensional Neutron Flux Estimation

Neural Operator Surrogates for Two-Dimensional Neutron Flux Estimation

Short summary

This study extends 1D neural-operator transport solvers to 2D, comparing Fourier neural operators (FNOs) and U-shaped neural operators (UNOs) for approximating scalar neutron flux. Three surrogate configurations are tested: direct FNO, direct UNO, and an FNO incorporating a single-sweep approximation as additional input. The study also examines whether training on logarithmic flux improves accuracy in strongly attenuated shielding regions.

  • •Extends 1D neural-operator neutron transport studies to 2D with isotropic scattering
  • •Compares FNO and UNO surrogates, including a single-sweep-augmented FNO variant
  • •Investigates logarithmic flux training for improved accuracy in shielding-relevant attenuated regions

Generated with AI, which can make mistakes.

#research-breakthrough
Read full article at arXiv cs.LG

Is this a good recommendation for you?

Comments

Failed to load comments. Please try again.

Explore more

The user wants me to rewrite a news headline for a mobile feed based on the original title and summary.
arXiv cs.LG
Native Multi-Dimensional Subquadratic Operators via Input Dependent Long Convolutions
arXiv cs.LG
LLT: Local Linear Transformer for PDE Operator Learning
arXiv cs.LG
QFireNet: A Quantum-Enhanced U-Net for Wildfire Segmentation from Sentinel-2 Imagery
arXiv cs.LG