Constraint-Aware Physics-Informed Neural Networks for SEIR Reaction-Diffusion Epidemic Models with Vital Dynamics

TL;DR

This paper introduces a constraint-aware physics-informed neural network framework for simulating and estimating parameters in spatial SEIR epidemic models, ensuring epidemiological constraints and stability.

Contribution

It develops a novel PINN approach that incorporates epidemiological constraints and boundary conditions for reaction-diffusion epidemic models with sparse data.

Findings

Accurately reconstructs spatiotemporal epidemic dynamics.

Reliable parameter estimation even with sparse or noisy data.

Ensures positivity, boundedness, and stability in simulations.

Abstract

Reaction-diffusion epidemic models with vital dynamics are an important framework for describing the spatial and temporal spread of infectious diseases. In this work, we present a constraint-aware, physics-informed neural network (PINN) approach to an SEIR reaction-diffusion system with homogeneous Neumann boundary conditions. Due to the scarcity of spatial epidemiological datasets, we generate synthetic benchmark data using structure-preserving implicit-explicit nonstandard finite difference (NSFD) schemes that ensure positivity, boundedness, and numerical stability. The PINN framework integrates PDE residuals, observational data, boundary conditions, and epidemiological constraints within a unified optimization procedure. Specifically, the loss function incorporates the non-negativity of compartment populations and the admissibility of epidemiological parameters. We apply the method to forward simulation and inverse parameter estimation in one- and two-dimensional settings. Numerical experiments demonstrate the framework's ability to accurately reconstruct spatiotemporal epidemic dynamics and reliably identify parameters, even when data is sparse or noisy. These results underscore the potential of constraint-aware PINNs as a robust, data-driven methodology for spatial epidemic modeling.