Work

Estimate Epidemiological Parameters given Partial Observations based on Algebraically Observable PINNs

Year: 2024

Type: preprint

Abstract: 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.

Source: arXiv (Cornell University)

DOI: 10.48550/arxiv.2407.12598

Author: Komatsu, Mizuka

Institution: Kobe University

Language: English

Topic: Model Reduction and Neural Networks

Subfield: Statistical and Nonlinear Physics

Field: Physics and Astronomy

Domain: Physical Sciences

Open Access status: green

Funders: Japan Society for the Promotion of Science, ACT-X

Awards: Basic research on interpretability and causality in modeling time-dependent phenomena, Coordinating Deep Learning and Algebraic Methods for State Space Modeling

OpenAlex ID: W4403750805

Cites:

Cited by:

Related to: 10