Work

Anchored Physics-Informed Neural Network for Two-Phase Flow Simulation in Heterogeneous Porous Media

Year: 2025

Type: article

Abstract: In this study, we propose a tensorization-anchoring strategy based on adaptive architectures to accelerate the computation of Enriched Physics-Informed Neural Networks (EPINN) for two-phase flow simulations. Specifically, we design an adaptive tensorization mechanism for the adjacency matrix embedding, the activation function, and the skip-gated connection in EPINN, which collectively expand the neural network's (NN) parameter space for learning more generalized patterns. Moreover, we developed an anchoring strategy by establishing Anchors-EPINN (An-EPINN). By detaching tensorization parameters from the computational graph and anchoring weighted nodes to fixed positions, the NN can benefit from tensorized fusion effects while reducing high-dimensional matrix calculations during forward and backward propagation, thereby enhancing simulation efficiency. This approach reduces execution time by 31.47% in homogeneous cases and 27.91% in heterogeneous cases, while maintaining higher computational accuracy.

Source: InterPore Journal

DOI: 10.69631/ipj.v2i3nr67

Authors: Jingqi Lin, Xia Yan, Kai Zhang, Zhao Zhang, Jun Yao

Institutions: China University of Petroleum, East China, Qingdao University of Technology, Shandong University

Language: English

Topic: Model Reduction and Neural Networks

Subfield: Statistical and Nonlinear Physics

Field: Physics and Astronomy

Domain: Physical Sciences

Open Access status: diamond

Funders: National Natural Science Foundation of China, China National Offshore Oil Corporation, Higher Education Discipline Innovation Project

Awards: G1474490597, G2764545674, G5786398370, G6799016500, G6909825370