Domain-decomposed Evolutional Deep Neural Network with Random Features for Transient Pressure Diffusion with Discontinuous and High-Contrast Coefficients
A domain-decomposed random-feature evolutional deep neural network (DD RF-EDNN) that separates spatial approximation from temporal evolution and is supported as a structure-preserving and interpretable reduced formulation for transient simulations on prescribed heterogeneous media.
Pei-Qi Li, Jie Chen, Hui Zhang et al.
· 0 citations