{"slug": "neural-operator-surrogates-for-two-dimensional-neutron-flux-estimation", "title": "Neural Operator Surrogates for Two-Dimensional Neutron Flux Estimation", "summary": "Researchers extended neural operator surrogate models for neutron flux estimation from one to two dimensions, testing Fourier neural operators (FNOs) and U-shaped neural operators (UNOs) on one-group transport with isotropic scattering. Three surrogates were trained over three random seeds: two direct maps (FNO and UNO) from material and source fields to flux, and an FNO that also takes a single-sweep approximation as input. The study found that the single-sweep input improved accuracy over direct maps, and training on the logarithm of the flux enhanced accuracy in strongly attenuated shielding regions.", "body_md": "arXiv:2607.19388v1 Announce Type: new\nAbstract: This work extends our one-dimensional single-sweep neural-operator studies to two dimensions. We consider one-group transport with isotropic scattering. As in the one-dimensional work, we use Fourier neural operators (FNOs) to approximate the high-fidelity scalar flux. Additionally, we also investigate U-shaped neural operators (UNOs) in this study. We consider three surrogates. The first two map the material and source fields directly to the flux, one using an FNO and one using a UNO. The third is an FNO that additionally takes the scalar flux after one source iteration, the single-sweep approximation, as an input. Each case is solved to high fidelity with a verified discrete-ordinates solver, and an average relative L_2 error norm is used to characterize the quality of the inferred maps. We train every surrogate over three random seeds so that differences between them can be assessed against run-to-run variability. Two questions guide the study: whether the single-sweep input improves accuracy over the direct maps, and whether training on the logarithm of the flux improves accuracy in the strongly attenuated regions relevant to shielding.", "url": "https://wpnews.pro/news/neural-operator-surrogates-for-two-dimensional-neutron-flux-estimation", "canonical_source": "https://arxiv.org/abs/2607.19388", "published_at": "2026-07-23 04:00:00+00:00", "updated_at": "2026-07-23 04:12:45.187083+00:00", "lang": "en", "topics": ["machine-learning", "neural-networks"], "entities": ["Fourier neural operators", "U-shaped neural operators"], "alternates": {"html": "https://wpnews.pro/news/neural-operator-surrogates-for-two-dimensional-neutron-flux-estimation", "markdown": "https://wpnews.pro/news/neural-operator-surrogates-for-two-dimensional-neutron-flux-estimation.md", "text": "https://wpnews.pro/news/neural-operator-surrogates-for-two-dimensional-neutron-flux-estimation.txt", "jsonld": "https://wpnews.pro/news/neural-operator-surrogates-for-two-dimensional-neutron-flux-estimation.jsonld"}}