Computational Mathematics and Statistics Seminar by Aleksei Sorokin: A Neural Surrogate Solver for Radiation Transfer

Speaker: Aleksei Sorokin, Ph.D. student, Illinois Institute of Technology

Title: A Neural Surrogate Solver for Radiation Transfer

Abstract: Radiative transfer is often the dominant mode of heat transfer in fires, and solving the governing radiative transfer equation (RTE) in CFD fire simulations is computationally intensive. This work develops a new versatile toolkit for training neural surrogates to solve various RTEs across different geometries and boundary conditions. We generalize previous work in the area to include unknown boundary conditions and to perform Principal Component Analysis (PCA) for dimension reduction in this context. This enables efficient training of high-dimensional neural surrogate solvers for a large class of RTEs. The mesh free nature of these surrogates enables them to overcome the ray effect suffered by traditional solvers. Our results demonstrate that neural surrogates can provide fast and accurate radiation predictions for practical problems important to fire safety research.

 

Computational Mathematics and Statistics Seminar

Zoom link