Paper · 2025 · Open access

Data and Modeling Assumptions in Physics-Informed Operator Learning

Martin Hofmann-Wellenhof, A. Fuchs, Bernhard Geiger, Franz Pernkopf

Zenodo (CERN European Organization for Nuclear Research) · Published 27 November 2025 · DOI 10.5281/zenodo.20830451

Read the free full textCite this paper

In brief

“Data and Modeling Assumptions in Physics-Informed Operator Learning” is a 2025 paper by Martin Hofmann-Wellenhof and 3 co-authors, published in Zenodo (CERN European Organization for Nuclear Research). OpenAlex counts 0 citations as of 16 November 2026. It is open access: the full text is free to read at Zenodo (CERN European Organization for Nuclear Research).

Citations
0
Authors
4

Abstract

Operator networks have emerged as promising surrogate models, replacing computationally expensive numerical solvers for differential equations. Beyond achieving competitive accuracy with traditional solvers, the practical viability of this approach greatly depends on its training cost, which is comprised of ground truth data acquisition and network optimization. Physics-informed machine learning seeks to reduce reliance on labeled data by embedding the governing differential equations into the loss function; however, such models are often very challenging to train using physics constraints alone. In this paper, we study how varying amounts of labeled data and architectural choices affect convergence and final performance in operator learning. Specifically, we compare an architecture developed for operator learning, i.e., Deep Operator Network, with a simpler MLP baseline across three training regimes: purely data-driven, purely physics-informed with no labeled data, and hybrid approaches that leverage both data and physics information. Our experiments on the double-mass-spring-damper system indicate that the physics-informed Deep Operator Network converges faster to the same performance if small amounts of labeled data are used. For the MLP architecture, which is not as well-tailored to the underlying dynamics, a purely physics-informed approach fails. In this case, incorporating labeled data mitigates architectural deficiencies and always substantially improves convergence and performance.

Cite this paper

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

APA 7

Hofmann-Wellenhof, M., Fuchs, A., Geiger, B., & Pernkopf, F. (2025). Data and Modeling Assumptions in Physics-Informed Operator Learning. Zenodo (CERN European Organization for Nuclear Research). https://doi.org/10.5281/zenodo.20830451

MLA 9

Hofmann-Wellenhof, Martin, et al. “Data and Modeling Assumptions in Physics-Informed Operator Learning.” Zenodo (CERN European Organization for Nuclear Research), 2025. https://doi.org/10.5281/zenodo.20830451.

Chicago

Hofmann-Wellenhof, Martin, A. Fuchs, Bernhard Geiger, and Franz Pernkopf. 2025. “Data and Modeling Assumptions in Physics-Informed Operator Learning.” Zenodo (CERN European Organization for Nuclear Research). https://doi.org/10.5281/zenodo.20830451.

Harvard

Hofmann-Wellenhof, M. et al. (2025) ‘Data and Modeling Assumptions in Physics-Informed Operator Learning’, Zenodo (CERN European Organization for Nuclear Research). doi:10.5281/zenodo.20830451.

IEEE

M. Hofmann-Wellenhof, A. Fuchs, B. Geiger, and F. Pernkopf, “Data and Modeling Assumptions in Physics-Informed Operator Learning,” Zenodo (CERN European Organization for Nuclear Research), 2025, doi: 10.5281/zenodo.20830451.

BibTeX

@article{hofmannwellenhof2025data,
  title     = {{Data and Modeling Assumptions in Physics-Informed Operator Learning}},
  author    = {Hofmann-Wellenhof, Martin and Fuchs, A. and Geiger, Bernhard and Pernkopf, Franz},
  journal   = {Zenodo (CERN European Organization for Nuclear Research)},
  year      = {2025},
  doi       = {10.5281/zenodo.20830451},
  url       = {https://doi.org/10.5281/zenodo.20830451}
}

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 machine learning
  • operator networks
  • DeepONet
  • annotated dataset
  • convergence
  • network architecture
  • training costs

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?

Hofmann-Wellenhof, M., Fuchs, A., Geiger, B., & Pernkopf, F. (2025). Data and Modeling Assumptions in Physics-Informed Operator Learning. Zenodo (CERN European Organization for Nuclear Research). https://doi.org/10.5281/zenodo.20830451

How many times has this paper been cited?

0 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 Zenodo (CERN European Organization for Nuclear Research).

Who wrote this paper?

Martin Hofmann-Wellenhof, A. Fuchs, Bernhard Geiger, Franz Pernkopf.

What is the DOI of this paper?

10.5281/zenodo.20830451. The permanent link is https://doi.org/10.5281/zenodo.20830451.

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.