Learning PDE Solvers with Physics and Data: A Unifying View of Physics-Informed Neural Networks and Neural Operators

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Dai, Yilong, Chen, Shengyu, Wang, Ziyi, Jia, Xiaowei, Xie, Yiqun, Kumar, Vipin, Yu, Runlong
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866912912613834752
author Dai, Yilong
Chen, Shengyu
Wang, Ziyi
Jia, Xiaowei
Xie, Yiqun
Kumar, Vipin
Yu, Runlong
author_facet Dai, Yilong
Chen, Shengyu
Wang, Ziyi
Jia, Xiaowei
Xie, Yiqun
Kumar, Vipin
Yu, Runlong
contents Partial differential equations (PDEs) are central to scientific modeling. Modern workflows increasingly rely on learning-based components to support model reuse, inference, and integration across large computational processes. Despite the emergence of various physics-aware data-driven approaches, the field still lacks a unified perspective to uncover their relationships, limitations, and appropriate roles in scientific workflows. To this end, we propose a unifying perspective to place two dominant paradigms: Physics-Informed Neural Networks (PINNs) and Neural Operators (NOs), within a shared design space. We organize existing methods from three fundamental dimensions: what is learned, how physical structures are integrated into the learning process, and how the computational load is amortized across problem instances. In this way, many challenges can be best understood as consequences of these structural properties of learning PDEs. By analyzing advances through this unifying view, our survey aims to facilitate the development of reliable learning-based PDE solvers and catalyze a synthesis of physics and data.
format Preprint
id arxiv_https___arxiv_org_abs_2601_14517
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Learning PDE Solvers with Physics and Data: A Unifying View of Physics-Informed Neural Networks and Neural Operators
Dai, Yilong
Chen, Shengyu
Wang, Ziyi
Jia, Xiaowei
Xie, Yiqun
Kumar, Vipin
Yu, Runlong
Machine Learning
Analysis of PDEs
Partial differential equations (PDEs) are central to scientific modeling. Modern workflows increasingly rely on learning-based components to support model reuse, inference, and integration across large computational processes. Despite the emergence of various physics-aware data-driven approaches, the field still lacks a unified perspective to uncover their relationships, limitations, and appropriate roles in scientific workflows. To this end, we propose a unifying perspective to place two dominant paradigms: Physics-Informed Neural Networks (PINNs) and Neural Operators (NOs), within a shared design space. We organize existing methods from three fundamental dimensions: what is learned, how physical structures are integrated into the learning process, and how the computational load is amortized across problem instances. In this way, many challenges can be best understood as consequences of these structural properties of learning PDEs. By analyzing advances through this unifying view, our survey aims to facilitate the development of reliable learning-based PDE solvers and catalyze a synthesis of physics and data.
title Learning PDE Solvers with Physics and Data: A Unifying View of Physics-Informed Neural Networks and Neural Operators
topic Machine Learning
Analysis of PDEs
url https://arxiv.org/abs/2601.14517