Search:
Match:
1 results

Analysis

This paper introduces BF-APNN, a novel deep learning framework designed to accelerate the solution of Radiative Transfer Equations (RTEs). RTEs are computationally expensive due to their high dimensionality and multiscale nature. BF-APNN builds upon existing methods (RT-APNN) and improves efficiency by using basis function expansion to reduce the computational burden of high-dimensional integrals. The paper's significance lies in its potential to significantly reduce training time and improve performance in solving complex RTE problems, which are crucial in various scientific and engineering fields.
Reference

BF-APNN substantially reduces training time compared to RT-APNN while preserving high solution accuracy.