HFS-TransNet: A Hybrid Fixed-Stress Transferable Neural Network for Quasi-Static Biot Poroelasticity
My rating
This paper targets the quasi-static Biot system governing coupled fluid-solid interactions in poroelastic media. Its HFS-TransNet method uses a data-driven TransNet module to approximate observations on an initialization domain and provide a high-quality starting point for the fixed-stress transfer process. The work focuses on improving computational treatment of strongly coupled, multiscale poroelastic problems.
Tags: