Neural network surrogates for action potentials
Chaos: An Interdisciplinary Journal of Nonlinear Science · 01.05.2026 · 36 (5)
DOI: 10.1063/5.0322725 ↗Kurz gefasst
Fachartikel in der Zeitschrift Chaos: An Interdisciplinary Journal of Nonlinear Science, online erschienen am 15.05.2026. Verfasst von Yan Barbosa Werneck und 3 weiteren Autor:innen. Beteiligte Einrichtung: Computational Modeling Graduate Program, Federal University of Juiz de Fora, Juiz de Fora, Brazil. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 31 Literaturangaben. Gefördert von: Fundação de Amparo à Pesquisa do Estado de Minas Gerais, Coordenação de Aperfeiçoamento de Pessoal de Nível Superior, Ciência sem Fronteiras.
Abstract (Originalsprache)
In this study, we investigate neural network surrogate models for excitable dynamics using the FitzHugh–Nagumo system as a canonical reduced model of cardiac and neuronal action potentials. We compare three classes of architectures—data-driven feedforward networks, physics-informed neural networks (PINNs), and recurrent neural networks (RNNs)—and assess their ability to reproduce the temporal evolution of action potentials. Our evaluation emphasizes stability, long-horizon error accumulation, and fidelity to both the qualitative and quantitative features of the underlying dynamical system. We find that purely data-driven feedforward surrogates can provide accurate and stable approximations in data-rich regimes, offering fast inference and direct access to the solution at arbitrary time points. In contrast, recurrent architectures exhibit substantial error growth over long time horizons, highlighting persistent challenges in learning stable excitable dynamics. PINNs are most beneficial in data-scarce settings, where physics-based regularization improves identifiability and reduces extrapolation error. We further show that parameter regimes near bifurcations are particularly difficult to learn; incorporating physics-informed loss terms can partially alleviate these failures, though not eliminate them. For simple configurations, the proposed surrogates achieve speedups of up to 1.7× over conventional numerical solvers while remaining fully differentiable. However, for more complex and highly parameterized problems, classical differential-equation solvers remain more robust and accurate than the neural surrogate approaches considered here.
Autor:innen und Institutionen
- Computational Modeling Graduate Program, Federal University of Juiz de Fora, Juiz de Fora, Brazil.
- Department of Computer Science, Federal University of Juiz de Fora, Juiz de Fora, Brazil.
- Department of Computer Science, Federal University of São João del-Rei, São João del-Rei, Brazil.
ORCID-Profile: Yan Barbosa Werneck, Bernardo M Rocha, Rafael Sachetto Oliveira, Rodrigo W Dos Santos
Förderung
- Fundação de Amparo à Pesquisa do Estado de Minas Gerais
- Coordenação de Aperfeiçoamento de Pessoal de Nível Superior
- Ciência sem Fronteiras
- Financiadora de Estudos e Projetos
Zitieren
APA
Barbosa Werneck, Y., Rocha, B. M., Sachetto Oliveira, R., & Dos Santos, R. W. (2026). Neural network surrogates for action potentials. Chaos: An Interdisciplinary Journal of Nonlinear Science, 36(5). https://doi.org/10.1063/5.0322725
Vancouver
Barbosa Werneck Y, Rocha BM, Sachetto Oliveira R, Dos Santos RW. Neural network surrogates for action potentials. Chaos: An Interdisciplinary Journal of Nonlinear Science. 2026;36(5). doi:10.1063/5.0322725
BibTeX
@article{BarbosaWerneck2026,
author = {Barbosa Werneck, Yan and Rocha, Bernardo M and Sachetto Oliveira, Rafael and Dos Santos, Rodrigo W},
title = {Neural network surrogates for action potentials},
journal = {Chaos: An Interdisciplinary Journal of Nonlinear Science},
year = {2026},
volume = {36},
number = {5},
doi = {10.1063/5.0322725}
}
EUVIMED