Weak form theory-guided neural network (TgNN-wf) for deep learning of subsurface single- and two-phase flow

DOI10.1016/j.jcp.2021.110318MaRDI QIDQ2131089

Yanyan Li

Publication date: 25 April 2022

Published in: Journal of Computational Physics (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2009.04543

zbMATH Keywords

two-phase flow; Lagrangian duality; weak form; single-phase flow; theory-guided neural network

Mathematics Subject Classification ID

68Txx: Artificial intelligence

65Mxx: Numerical methods for partial differential equations, initial value and time-dependent initial-boundary value problems

35Rxx: Miscellaneous topics in partial differential equations

Uses Software

• MODFLOW
• MODFLOW-2000
• PyTorch
• DGM
• FPINNs
• hp-VPINNs