A Koopman-PINN Framework for Epidemic Models: Parameter Inference and Forecasting
We propose a Koopman-enhanced physics-informed neural network (K-PINN) framework for parameter inference and forecasting in nonlinear epidemic models. This method combines Koopman operator theory and physics-informed learning. It maps epidemic states into a latent observable space where the dynamics evolve approximately linearly while satisfying the governing epidemic equations through automatic differentiation. This integration improves interpretability, parameter identifiability, and long-term predictive stability. We apply the proposed framework to a normalized SEIRSD epidemic model and evaluate it using synthetic monkeypox (Mpox) data and real-world datasets from Germany, Morocco, and Sweden for the SARS-CoV-2 virus. Synthetic trajectories are generated using a structure-preserving, nonstandard finite difference scheme to ensure reliable training data. Numerical results demonstrate that K-PINN achieves more accurate parameter estimation, trajectory reconstruction, and long-term forecasting than classical PINNs and Koopman-EDMD approaches. These results suggest that K-PINN is an effective machine learning framework for epidemic modeling that can be extended to more complex systems.
Authors
- Matthias Ehrhardt (ORCID: https://orcid.org/0000-0003-2561-8854)
- Moulay Rchid Sidi Ammi (ORCID: https://orcid.org/0000-0002-4488-9070)
- Achraf Zinihi (ORCID: https://orcid.org/0009-0001-3245-2779)
Institutions
- University of Wuppertal (DE)
- Université Moulay Ismail de Meknes (MA)
Publication Details
- Journal
- Numerical Mathematics Theory Methods and Applications
- Published
- 2026-11-17
- DOI
- https://doi.org/10.4208/nmtma.oa-2026-0094
- Primary Topic
- Model Reduction and Neural Networks
- Type
- article
- Field-Weighted Citation Impact
- 0.00