Physics-Informed Neural Networks: A Review of Methodological Evolution, Theoretical Foundations, and Interdisciplinary Frontiers Toward Next-Generation Scientific Computing

Physics-informed neural networks (PINNs) have emerged as a transformative methodology integrating deep learning with scientific computing. This review establishes a three-dimensional analytical framework to systematically decode PINNs’ development through methodological innovation, theoretical break...

Full description

Saved in:
Bibliographic Details
Main Authors: Zhiyuan Ren, Shijie Zhou, Dong Liu, Qihe Liu
Format: Article
Language:English
Published: MDPI AG 2025-07-01
Series:Applied Sciences
Subjects:
Online Access:https://www.mdpi.com/2076-3417/15/14/8092
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850078423515398144
author Zhiyuan Ren
Shijie Zhou
Dong Liu
Qihe Liu
author_facet Zhiyuan Ren
Shijie Zhou
Dong Liu
Qihe Liu
author_sort Zhiyuan Ren
collection DOAJ
description Physics-informed neural networks (PINNs) have emerged as a transformative methodology integrating deep learning with scientific computing. This review establishes a three-dimensional analytical framework to systematically decode PINNs’ development through methodological innovation, theoretical breakthroughs, and cross-disciplinary convergence. The contributions include threefold: First, identifying the co-evolutionary path of algorithmic architectures from adaptive optimization (neural tangent kernel-guided weighting achieving 230% convergence acceleration in Navier-Stokes solutions) to hybrid numerical-deep learning integration (5× speedup via domain decomposition) and second, constructing bidirectional theory-application mappings where convergence analysis (operator approximation theory) and generalization guarantees (Bayesian-physical hybrid frameworks) directly inform engineering implementations, as validated by <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>72</mn><mo>%</mo></mrow></semantics></math></inline-formula> cost reduction compared to FEM in high-dimensional spaces (<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>p</mi><mo><</mo><mn>0.01</mn><mo>,</mo><mi>n</mi><mo>=</mo><mn>15</mn></mrow></semantics></math></inline-formula> benchmarks). Third, pioneering cross-domain knowledge transfer through application-specific architectures: TFE-PINN for turbulent flows (<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>5.12</mn><mo>±</mo><mn>0.87</mn><mo>%</mo></mrow></semantics></math></inline-formula> error in NASA hypersonic tests), ReconPINN for medical imaging (<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mo>▵</mo><mi>SSIM</mi><mo>=</mo><mo>+</mo><mn>0.18</mn><mo>±</mo><mn>0.04</mn></mrow></semantics></math></inline-formula> on multi-institutional MRI), and SeisPINN for seismic systems (<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>0.52</mn><mo>±</mo><mn>0.18</mn></mrow></semantics></math></inline-formula> km localization accuracy). We further present a technological roadmap highlighting three critical directions for PINN 2.0: neuro-symbolic, federated physics learning, and quantum-accelerated optimization. This work provides methodological guidelines and theoretical foundations for next-generation scientific machine learning systems.
format Article
id doaj-art-53aa81a1b42343df8fb7e2b8f5cc1ab0
institution DOAJ
issn 2076-3417
language English
publishDate 2025-07-01
publisher MDPI AG
record_format Article
series Applied Sciences
spelling doaj-art-53aa81a1b42343df8fb7e2b8f5cc1ab02025-08-20T02:45:33ZengMDPI AGApplied Sciences2076-34172025-07-011514809210.3390/app15148092Physics-Informed Neural Networks: A Review of Methodological Evolution, Theoretical Foundations, and Interdisciplinary Frontiers Toward Next-Generation Scientific ComputingZhiyuan Ren0Shijie Zhou1Dong Liu2Qihe Liu3School of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu 610054, ChinaSchool of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu 610054, ChinaSchool of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu 610054, ChinaSchool of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu 610054, ChinaPhysics-informed neural networks (PINNs) have emerged as a transformative methodology integrating deep learning with scientific computing. This review establishes a three-dimensional analytical framework to systematically decode PINNs’ development through methodological innovation, theoretical breakthroughs, and cross-disciplinary convergence. The contributions include threefold: First, identifying the co-evolutionary path of algorithmic architectures from adaptive optimization (neural tangent kernel-guided weighting achieving 230% convergence acceleration in Navier-Stokes solutions) to hybrid numerical-deep learning integration (5× speedup via domain decomposition) and second, constructing bidirectional theory-application mappings where convergence analysis (operator approximation theory) and generalization guarantees (Bayesian-physical hybrid frameworks) directly inform engineering implementations, as validated by <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>72</mn><mo>%</mo></mrow></semantics></math></inline-formula> cost reduction compared to FEM in high-dimensional spaces (<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>p</mi><mo><</mo><mn>0.01</mn><mo>,</mo><mi>n</mi><mo>=</mo><mn>15</mn></mrow></semantics></math></inline-formula> benchmarks). Third, pioneering cross-domain knowledge transfer through application-specific architectures: TFE-PINN for turbulent flows (<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>5.12</mn><mo>±</mo><mn>0.87</mn><mo>%</mo></mrow></semantics></math></inline-formula> error in NASA hypersonic tests), ReconPINN for medical imaging (<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mo>▵</mo><mi>SSIM</mi><mo>=</mo><mo>+</mo><mn>0.18</mn><mo>±</mo><mn>0.04</mn></mrow></semantics></math></inline-formula> on multi-institutional MRI), and SeisPINN for seismic systems (<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>0.52</mn><mo>±</mo><mn>0.18</mn></mrow></semantics></math></inline-formula> km localization accuracy). We further present a technological roadmap highlighting three critical directions for PINN 2.0: neuro-symbolic, federated physics learning, and quantum-accelerated optimization. This work provides methodological guidelines and theoretical foundations for next-generation scientific machine learning systems.https://www.mdpi.com/2076-3417/15/14/8092partial differential equationphysics-informed neural networkscientific computingAI for scienceartificial intelligence
spellingShingle Zhiyuan Ren
Shijie Zhou
Dong Liu
Qihe Liu
Physics-Informed Neural Networks: A Review of Methodological Evolution, Theoretical Foundations, and Interdisciplinary Frontiers Toward Next-Generation Scientific Computing
Applied Sciences
partial differential equation
physics-informed neural network
scientific computing
AI for science
artificial intelligence
title Physics-Informed Neural Networks: A Review of Methodological Evolution, Theoretical Foundations, and Interdisciplinary Frontiers Toward Next-Generation Scientific Computing
title_full Physics-Informed Neural Networks: A Review of Methodological Evolution, Theoretical Foundations, and Interdisciplinary Frontiers Toward Next-Generation Scientific Computing
title_fullStr Physics-Informed Neural Networks: A Review of Methodological Evolution, Theoretical Foundations, and Interdisciplinary Frontiers Toward Next-Generation Scientific Computing
title_full_unstemmed Physics-Informed Neural Networks: A Review of Methodological Evolution, Theoretical Foundations, and Interdisciplinary Frontiers Toward Next-Generation Scientific Computing
title_short Physics-Informed Neural Networks: A Review of Methodological Evolution, Theoretical Foundations, and Interdisciplinary Frontiers Toward Next-Generation Scientific Computing
title_sort physics informed neural networks a review of methodological evolution theoretical foundations and interdisciplinary frontiers toward next generation scientific computing
topic partial differential equation
physics-informed neural network
scientific computing
AI for science
artificial intelligence
url https://www.mdpi.com/2076-3417/15/14/8092
work_keys_str_mv AT zhiyuanren physicsinformedneuralnetworksareviewofmethodologicalevolutiontheoreticalfoundationsandinterdisciplinaryfrontierstowardnextgenerationscientificcomputing
AT shijiezhou physicsinformedneuralnetworksareviewofmethodologicalevolutiontheoreticalfoundationsandinterdisciplinaryfrontierstowardnextgenerationscientificcomputing
AT dongliu physicsinformedneuralnetworksareviewofmethodologicalevolutiontheoreticalfoundationsandinterdisciplinaryfrontierstowardnextgenerationscientificcomputing
AT qiheliu physicsinformedneuralnetworksareviewofmethodologicalevolutiontheoreticalfoundationsandinterdisciplinaryfrontierstowardnextgenerationscientificcomputing