Saved in:
Bibliographic Details
Main Authors: Wang, Yuhe, Wang, Min
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2602.17776
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914464442351616
author Wang, Yuhe
Wang, Min
author_facet Wang, Yuhe
Wang, Min
contents Physics-governed models are increasingly paired with machine learning for accelerated predictions, yet most "physics--informed" formulations treat the governing equations as a penalty loss whose scale and meaning are set by heuristic balancing. This blurs operator structure, thereby confounding solution approximation error with governing-equation enforcement error and making the solving and learning progress hard to interpret and control. Here we introduce the Neural Basis Method, a projection-based formulation that couples a predefined, physics-conforming neural basis space with an operator-induced residual metric to obtain a well-conditioned deterministic minimization. Stability and reliability then hinge on this metric: the residual is not merely an optimization objective but a computable certificate tied to approximation and enforcement, remaining stable under basis enrichment and yielding reduced coordinates that are learnable across parametric instances. We use advective multiscale Darcian dynamics as a concrete demonstration of this broader point. Our method produce accurate and robust solutions in single solves and enable fast and effective parametric inference with operator learning.
format Preprint
id arxiv_https___arxiv_org_abs_2602_17776
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Solving and learning advective multiscale Darcian dynamics with the Neural Basis Method
Wang, Yuhe
Wang, Min
Numerical Analysis
Machine Learning
Physics-governed models are increasingly paired with machine learning for accelerated predictions, yet most "physics--informed" formulations treat the governing equations as a penalty loss whose scale and meaning are set by heuristic balancing. This blurs operator structure, thereby confounding solution approximation error with governing-equation enforcement error and making the solving and learning progress hard to interpret and control. Here we introduce the Neural Basis Method, a projection-based formulation that couples a predefined, physics-conforming neural basis space with an operator-induced residual metric to obtain a well-conditioned deterministic minimization. Stability and reliability then hinge on this metric: the residual is not merely an optimization objective but a computable certificate tied to approximation and enforcement, remaining stable under basis enrichment and yielding reduced coordinates that are learnable across parametric instances. We use advective multiscale Darcian dynamics as a concrete demonstration of this broader point. Our method produce accurate and robust solutions in single solves and enable fast and effective parametric inference with operator learning.
title Solving and learning advective multiscale Darcian dynamics with the Neural Basis Method
topic Numerical Analysis
Machine Learning
url https://arxiv.org/abs/2602.17776