Data reduction in deterministic neutron transport calculations using machine learning

Neutron cross section matrices for fission and scattering data are required each material, temperature, enrichment level to calculate the neutron transport equation accurately. This information can be a limiting factor when using multigroup discrete ordinates (SN) method number of energy groups is large. Machine Learning (ML) used replace need by reproducing function that maps scalar flux sources. Through use autoencoders Deep Jointly-Informed Neural Networks (DJINN), storage requirements reduced 94% original 618 group problem. accomplished while preserving flux, maintaining generality, decreasing wall clock times.