Solving and learning advective multiscale Darcian dynamics with the Neural Basis Method

2026-02-19

AI Summary

This work addresses the limitations of conventional physics-informed machine learning, which treats governing equations as heuristic penalty terms, conflating approximation error with constraint violation and leading to uncontrolled and uninterpretable solutions. The authors propose a neural basis approach that constructs a neural function space inherently satisfying physical laws and introduces an operator-induced residual metric to reformulate the problem as a well-posed deterministic optimization. By enforcing projection-based physical constraints, the framework ensures stability during basis enrichment and leverages the residual as a computable error certificate, enabling dimensionality-reduced coordinate learning across parameter instances. The method achieves high-fidelity, robust multiscale Darcy flow solutions in a single solve and supports efficient parametric inference.

Technology Category

• Machine Learning: Other Foundations of Machine Learning
• Constraint Satisfaction and Optimization: Constraint Learning and Acquisition
• Search and Optimization: Sampling/Simulation-based Search

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

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.

Problem

• physics-informed machine learning
• governing equations
• solution approximation error
• operator structure
• residual metric

Innovation

• Neural Basis Method
• physics-informed machine learning
• operator-induced residual metric
• multiscale Darcian dynamics
• projection-based formulation