Domain-decomposed Evolutional Deep Neural Network with Random Features for Transient Pressure Diffusion with Discontinuous and High-Contrast Coefficients

This paper addresses the challenge of efficiently resolving transient pressure diffusion in heterogeneous porous media where permeability is discontinuous and spans several orders of magnitude. The authors develop a domain-decomposed random-feature evolutional deep neural network (DD RF-EDNN) that separates spatial approximation from temporal evolution. Permeability-informed random features are compressed into an orthonormal pressure space, and a conservative finite-volume operator is employed for the solution.