Abstract:We present an operator learning framework based on a coarse data-driven multiscale space for nonlinear flow in random heterogeneous porous media. The multiscale space is constructed from local representative fine-scale solution snapshots, yielding an accurate low-dimensional representation of the solution manifold. This multiscale basis serves as the trunk of a neural operator, while a branch network predicts the corresponding reduced coefficients from the input permeability field. Unlike Galerkin projection methods, the neural operator learns a global nonlinear mapping from permeability fields to solution coefficients, providing greater flexibility, improved accuracy, and eliminating the need for online nonlinear coarse-grid solves and coefficient evaluations. Numerical results show that the proposed approach achieves good accuracy and substantially lower computational cost than projection-based methods for nonlinear flow in high-contrast heterogeneous media.
From: Maria Vasilyeva [view email]
[v1]
Wed, 24 Jun 2026 13:36:31 UTC (2,388 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。