Journal article · 2024 · Open access

Learning Only on Boundaries: A Physics-Informed Neural Operator for Solving Parametric Partial Differential Equations in Complex Geometries

Zhiwei Fang, Sifan Wang, Paris G. Perdikaris

Neural Computation, 36(3), 475–498 · Published 16 February 2024 · DOI 10.1162/neco_a_01647

Free PDFView at the publisherCite this paper

In brief

“Learning Only on Boundaries: A Physics-Informed Neural Operator for Solving Parametric Partial Differential Equations in Complex Geometries” is a 2024 journal article by Zhiwei Fang and 2 co-authors, published in Neural Computation. OpenAlex counts 35 citations as of 16 November 2026, which puts it in the top 2% of works published in 2024 by citations. It is open access: the full text is free to read at arXiv (Cornell University).

Citations
35
Most cited in
2026 (22)
Field-weighted impact
4.04
References
38
Authors
3

Abstract

Recently, deep learning surrogates and neural operators have shown promise in solving partial differential equations (PDEs). However, they often require a large amount of training data and are limited to bounded domains. In this work, we present a novel physics-informed neural operator method to solve parameterized boundary value problems without labeled data. By reformulating the PDEs into boundary integral equations (BIEs), we can train the operator network solely on the boundary of the domain. This approach reduces the number of required sample points from O(Nd) to O(Nd-1), where d is the domain's dimension, leading to a significant acceleration of the training process. Additionally, our method can handle unbounded problems, which are unattainable for existing physics-informed neural networks (PINNs) and neural operators. Our numerical experiments show the effectiveness of parameterized complex geometries and unbounded problems.

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

Fang, Z., Wang, S., & Perdikaris, P. G. (2024). Learning Only on Boundaries: A Physics-Informed Neural Operator for Solving Parametric Partial Differential Equations in Complex Geometries. Neural Computation, 36(3), 475–498. https://doi.org/10.1162/neco_a_01647

MLA 9

Fang, Zhiwei, et al. “Learning Only on Boundaries: A Physics-Informed Neural Operator for Solving Parametric Partial Differential Equations in Complex Geometries.” Neural Computation, vol. 36, no. 3, 2024, pp. 475–498. https://doi.org/10.1162/neco_a_01647.

Chicago

Fang, Zhiwei, Sifan Wang, and Paris G. Perdikaris. 2024. “Learning Only on Boundaries: A Physics-Informed Neural Operator for Solving Parametric Partial Differential Equations in Complex Geometries.” Neural Computation 36 (3): 475–498. https://doi.org/10.1162/neco_a_01647.

Harvard

Fang, Z., Wang, S. and Perdikaris, P. G. (2024) ‘Learning Only on Boundaries: A Physics-Informed Neural Operator for Solving Parametric Partial Differential Equations in Complex Geometries’, Neural Computation, 36(3), pp. 475–498. doi:10.1162/neco_a_01647.

IEEE

Z. Fang, S. Wang, and P. G. Perdikaris, “Learning Only on Boundaries: A Physics-Informed Neural Operator for Solving Parametric Partial Differential Equations in Complex Geometries,” Neural Computation, vol. 36, no. 3, pp. 475–498, 2024, doi: 10.1162/neco_a_01647.

BibTeX

@article{fang2024learning,
  title     = {{Learning Only on Boundaries: A Physics-Informed Neural Operator for Solving Parametric Partial Differential Equations in Complex Geometries}},
  author    = {Fang, Zhiwei and Wang, Sifan and Perdikaris, Paris G.},
  journal   = {Neural Computation},
  year      = {2024},
  volume    = {36},
  number    = {3},
  pages     = {475--498},
  doi       = {10.1162/neco_a_01647},
  url       = {https://doi.org/10.1162/neco_a_01647}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Citations by year

YearCitationsShare of the best year
202466
202577
20262222

Its field-weighted citation impact is 4.04: it has been cited 4.04 times as often as the average work of the same field, type and year (1.00 is the world average).

Topic and keywords

Physical Sciences › Physics and Astronomy › Statistical and Nonlinear Physics › Model Reduction and Neural Networks

  • physics-informed neural operators
  • parametric partial differential equations
  • boundary integral equations
  • unbounded domains
  • physics-informed neural networks
  • surrogate models

Work with this paper

Most-cited papers in Physics and Astronomy

All highly cited Physics and Astronomy papers

Questions about this paper

How do I cite this paper in APA style?

Fang, Z., Wang, S., & Perdikaris, P. G. (2024). Learning Only on Boundaries: A Physics-Informed Neural Operator for Solving Parametric Partial Differential Equations in Complex Geometries. Neural Computation, 36(3), 475–498. https://doi.org/10.1162/neco_a_01647

How many times has this paper been cited?

35 times, according to OpenAlex on 16 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 arXiv (Cornell University).

Who wrote this paper?

Zhiwei Fang, Sifan Wang, Paris G. Perdikaris.

What is the DOI of this paper?

10.1162/neco_a_01647. The permanent link is https://doi.org/10.1162/neco_a_01647.

Bibliographic data from OpenAlex (CC0), last checked 16 November 2026. ResearchGuru does not host this paper; the links go to the publisher or the repository that does.