Neural Empirical Interpolation Method for Nonlinear Model Reduction
SIAM Journal on Scientific Computing · 31.12.2025 · 47 (6) · C1264-C1293
DOI: 10.1137/24m1681434 ↗Kurz gefasst
Fachartikel in der Zeitschrift SIAM Journal on Scientific Computing, online erschienen am 18.11.2025. Verfasst von Max Hirsch und 2 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 42 Literaturangaben. Gefördert von: National Science Foundation Graduate Research Fellowship Program, ThinkSwiss Research Scholarship, INdAM-GNCS.
Abstract (Originalsprache)
In this paper, we introduce the neural empirical interpolation method (NEIM), a neural network-based alternative to the discrete empirical interpolation method for reducing the time complexity of computing the nonlinear term in a reduced-order model (ROM) for a parameterized nonlinear partial differential equation. NEIM is a greedy algorithm which accomplishes this reduction by approximating an affine decomposition of the nonlinear term of the ROM, where the vector terms of the expansion are given by neural networks depending on the ROM solution, and the coefficients are given by an interpolation of some “optimal” coefficients. Because NEIM is based on a greedy strategy, we are able to provide a basic error analysis to investigate its performance. NEIM has the advantages of being easy to implement in models with automatic differentiation, of being a nonlinear projection of the ROM nonlinearity, of being efficient for both nonlocal and local nonlinearities, and of relying solely on data and not the explicit form of the ROM nonlinearity. We demonstrate the effectiveness of the methodology on solution-dependent and solution-independent nonlinearities, a nonlinear elliptic problem, and a nonlinear parabolic model of liquid crystals. Code availability: https://github.com/maxhirsch/NEIM . Reproducibility of computational results. This paper has been awarded the “SIAM Reproducibility Badge: Code and data available” as recognition that the authors have followed reproducibility principles valued by SISC and the scientific computing community. Code and data that allow readers to reproduce the results in this paper are available at https://github.com/maxhirsch/NEIM and in the supplementary materials ( NEIM-main.zip [2.10MB]). [Formula: see text]
Förderung
- National Science Foundation Graduate Research Fellowship Program
- ThinkSwiss Research Scholarship
- INdAM-GNCS
- PNRR
- European Union’s NextGenerationEU
- École Polytechnique Fédérale de Lausanne Excellence Research Scholarship
Zitieren
APA
Hirsch, M., Pichi, F., & Hesthaven, J. S. (2025). Neural Empirical Interpolation Method for Nonlinear Model Reduction. SIAM Journal on Scientific Computing, 47(6), C1264-C1293. https://doi.org/10.1137/24m1681434
Vancouver
Hirsch M, Pichi F, Hesthaven JS. Neural Empirical Interpolation Method for Nonlinear Model Reduction. SIAM Journal on Scientific Computing. 2025;47(6):C1264-C1293. doi:10.1137/24m1681434
BibTeX
@article{Hirsch2025,
author = {Hirsch, Max and Pichi, Federico and Hesthaven, Jan S.},
title = {Neural Empirical Interpolation Method for Nonlinear Model Reduction},
journal = {SIAM Journal on Scientific Computing},
year = {2025},
volume = {47},
number = {6},
pages = {C1264--C1293},
doi = {10.1137/24m1681434}
}
EUVIMED