Estimate Epidemiological Parameters given Partial Observations based on Algebraically Observable PINNs
This work addresses parameter estimation in epidemiology with incomplete data, but it appears incremental as it adapts an existing PINN framework with algebraic observability.
The study tackled the problem of estimating epidemiological parameters using physics-informed neural networks (PINNs) when only partial and noisy trajectory data are available, by introducing algebraically observable PINNs, and demonstrated its validity in parameter estimation and prediction of unobserved variables through numerical experiments.
In this study, we considered the problem of estimating epidemiological parameters based on physics-informed neural networks (PINNs). In practice, not all trajectory data corresponding to the population estimated by epidemic models can be obtained, and some observed trajectories are noisy. Learning PINNs to estimate unknown epidemiological parameters using such partial observations is challenging. Accordingly, we introduce the concept of algebraic observability into PINNs. The validity of the proposed PINN, named as an algebraically observable PINNs, in terms of estimation parameters and prediction of unobserved variables, is demonstrated through numerical experiments.