EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

Accurate and scalable deep Maxwell solvers

Chenkai Mao iD, Jonathan A Fan iD

Proceedings of the National Academy of Sciences · 05.05.2026 · 123 (18)

DOI: 10.1073/pnas.2530330123 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the National Academy of Sciences, online erschienen am 27.04.2026. Verfasst von Chenkai Mao und 1 weiteren Autor:innen. Beteiligte Einrichtung: Department of Electrical Engineering, Stanford University, Stanford, CA 94305. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 53 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: National Science Foundation (NSF), DOD | AF | AMC | AFRL | Air Force Office of Scientific Research (AFOSR).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Neural networks have promise as surrogate partial differential equation (PDE) solvers, but it remains a challenge to use these concepts to solve problems with high accuracy and scalability. In this work, we show that neural network surrogates can combine with iterative algorithms to accurately solve PDE problems featuring different scales, resolutions, and boundary conditions. We develop a subdomain neural operator model that supports arbitrary Robin-type boundary condition inputs, and we show that it can be utilized as a flexible preconditioner to iteratively solve subdomain problems with bounded accuracy. We further show that our subdomain models can facilitate the construction of global coarse spaces to enable accelerated, large scale PDE problem solving based on iterative multilevel domain decomposition. With two-dimensional Maxwell’s equations as a model system, we train a single network to simulate large scale problems with different sizes, resolutions, wavelengths, and dielectric media distribution. We further demonstrate the utility of our platform in performing the accurate inverse design of multiwavelength nanophotonic devices. Our work presents a promising path to building accurate and scalable multiphysics surrogate solvers for large practical problems.

Schlagwörter

Stichwörter der Autor:innen

GMRESdomain decompositioniterative methodsneural operatorsurrogate models

Autor:innen und Institutionen

  • Department of Electrical Engineering, Stanford University, Stanford, CA 94305.

ORCID-Profile: Chenkai Mao, Jonathan A Fan

Förderung

  • National Science Foundation (NSF)
  • DOD | AF | AMC | AFRL | Air Force Office of Scientific Research (AFOSR)

Zitieren

APA

Mao, C., & Fan, J. A. (2026). Accurate and scalable deep Maxwell solvers. Proceedings of the National Academy of Sciences, 123(18). https://doi.org/10.1073/pnas.2530330123

Vancouver

Mao C, Fan JA. Accurate and scalable deep Maxwell solvers. Proceedings of the National Academy of Sciences. 2026;123(18). doi:10.1073/pnas.2530330123

BibTeX
@article{Mao2026,
  author = {Mao, Chenkai and Fan, Jonathan A},
  title = {Accurate and scalable deep Maxwell solvers},
  journal = {Proceedings of the National Academy of Sciences},
  year = {2026},
  volume = {123},
  number = {18},
  doi = {10.1073/pnas.2530330123}
}
Kostenlos starten →