Researchers have developed new neural operator models, specifically Fourier Neural Operators (FNOs) and U-shaped neural operators (UNOs), to estimate neutron flux in two-dimensional scenarios. These models are trained to approximate the scalar flux using material and source fields, with one FNO variant also incorporating a single-sweep approximation of the flux. The performance of these surrogates is evaluated against high-fidelity solutions from a discrete-ordinates solver, measuring accuracy via the average relative L2 error norm. AI
IMPACT Introduces novel neural operator architectures for complex physics simulations, potentially improving efficiency in areas like nuclear engineering.
RANK_REASON The cluster contains an academic paper detailing a new research methodology. [lever_c_demoted from research: ic=1 ai=1.0]
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →
