Review article · 2026 · Open access
Physics-informed neural networks and neural operators for PDEs: A review of architectures, training pathologies, and method selection
Neural Networks, 205(Pt C), 109640 · Published 15 September 2026 · DOI 10.1016/j.neunet.2026.109640
In brief
“Physics-informed neural networks and neural operators for PDEs: A review of architectures, training pathologies, and method selection” is a 2026 review article by Namhyeon Kim and 2 co-authors, published in Neural Networks. OpenAlex counts 0 citations as of 15 November 2026. It is open access under a CC BY licence: the full text is free to read at Neural Networks.
- Citations
- 0
- References
- 122
- Authors
- 3
Abstract
Physics-informed neural networks (PINNs) and neural operators are increasingly used to learn solutions and solution operators for partial differential equations, but the literature remains fragmented across architectures, training objectives, and benchmark protocols. This review organizes these developments for a neural-network audience. We separate two design axes that are often conflated: representation level (solution-level vs. operator-level) and training paradigm (data-driven vs. physics-informed). The resulting taxonomy positions classical PINNs, domain-decomposition and weak-form variants, Fourier and transformer-based neural operators, and hybrid physics-informed operators within a common design space. We further analyze recurring training pathologies, including gradient imbalance, spectral bias, optimization stiffness, and constraint enforcement, and relate them to PDE properties through a PDE Complexity Matrix with explicit scoring criteria. The review combines a 60-study PRISMA-screened methodological core set with a 155-paper contextual corpus covering benchmarks, applications, and operator-learning studies. Across the surveyed evidence, PDE complexity emerges as a useful organizing lens: classical PINNs remain attractive for sparse-data and inverse settings, whereas operator-level and hybrid models are often better suited to parametric, multiscale, or repeated-query regimes. We conclude with standardized evaluation recommendations, a method-selection flowchart, and open problems in generalization, uncertainty quantification, and foundation-model-based scientific learning.
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Kim, N., Toshpulatov, M. A., & Lee, S. (2026). Physics-informed neural networks and neural operators for PDEs: A review of architectures, training pathologies, and method selection. Neural Networks, 205(Pt C), 109640. https://doi.org/10.1016/j.neunet.2026.109640
MLA 9
Kim, Namhyeon, et al. “Physics-informed neural networks and neural operators for PDEs: A review of architectures, training pathologies, and method selection.” Neural Networks, vol. 205, no. Pt C, 2026, p. 109640. https://doi.org/10.1016/j.neunet.2026.109640.
Chicago
Kim, Namhyeon, Mukhiddin Amonkulovich Toshpulatov, and Suan Lee. 2026. “Physics-informed neural networks and neural operators for PDEs: A review of architectures, training pathologies, and method selection.” Neural Networks 205 (Pt C): 109640. https://doi.org/10.1016/j.neunet.2026.109640.
Harvard
Kim, N., Toshpulatov, M. A. and Lee, S. (2026) ‘Physics-informed neural networks and neural operators for PDEs: A review of architectures, training pathologies, and method selection’, Neural Networks, 205(Pt C), p. 109640. doi:10.1016/j.neunet.2026.109640.
IEEE
N. Kim, M. A. Toshpulatov, and S. Lee, “Physics-informed neural networks and neural operators for PDEs: A review of architectures, training pathologies, and method selection,” Neural Networks, vol. 205, no. Pt C, p. 109640, 2026, doi: 10.1016/j.neunet.2026.109640.
BibTeX
@article{kim2026physics,
title = {{Physics-informed neural networks and neural operators for PDEs: A review of architectures, training pathologies, and method selection}},
author = {Kim, Namhyeon and Toshpulatov, Mukhiddin Amonkulovich and Lee, Suan},
journal = {Neural Networks},
year = {2026},
volume = {205},
number = {Pt C},
pages = {109640},
doi = {10.1016/j.neunet.2026.109640},
url = {https://doi.org/10.1016/j.neunet.2026.109640}
}
Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)
Topic and keywords
Physical Sciences › Physics and Astronomy › Statistical and Nonlinear Physics › Model Reduction and Neural Networks
- physics-informed neural networks
- neural operators
- partial differential equations
- operator learning
- gradient imbalance
- spectral bias
- constraint enforcement
- domain decomposition
Work with this paper
Most-cited papers in Physics and Astronomy
- Generalized Gradient Approximation Made SimpleJohn P. Perdew, Kieron Burke, Matthias Ernzerhof · Physical Review Letters · 1996 · 217,345 citations
- Efficient iterative schemes for ab initio total-energy calculations using a plane-wave basis setGeorg Kresse, Jürgen Furthmüller · Physical review. B, Condensed matter · 1996 · 125,164 citations
- Density-functional thermochemistry. III. The role of exact exchangeAxel D. Becke · The Journal of Chemical Physics · 1993 · 104,772 citations
- Development of the Colle-Salvetti correlation-energy formula into a functional of the electron densityChengteh Lee, Weitao Yang, Robert G. Parr · Physical review. B, Condensed matter · 1988 · 101,730 citations
- Projector augmented-wave methodPeter E. Blöchl · Physical review. B, Condensed matter · 1994 · 93,520 citations
Questions about this paper
How do I cite this paper in APA style?
Kim, N., Toshpulatov, M. A., & Lee, S. (2026). Physics-informed neural networks and neural operators for PDEs: A review of architectures, training pathologies, and method selection. Neural Networks, 205(Pt C), 109640. https://doi.org/10.1016/j.neunet.2026.109640
How many times has this paper been cited?
0 times, according to OpenAlex on 15 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.
Is this paper free to read?
Yes. It is open access: read the free full text at Neural Networks.
Who wrote this paper?
Namhyeon Kim, Mukhiddin Amonkulovich Toshpulatov, Suan Lee.
What is the DOI of this paper?
10.1016/j.neunet.2026.109640. The permanent link is https://doi.org/10.1016/j.neunet.2026.109640.
Bibliographic data from OpenAlex (CC0), last checked 15 November 2026. ResearchGuru does not host this paper; the links go to the publisher or the repository that does.