Physics-Informed Neural Networks for Parameter Estimation in Epidemic Models with Noisy and Limited Data

Abstract Estimating epidemiological parameters from noisy and limited surveillance data is a critical challenge in mathematical epidemiology and outbreak response. This study presents a rigorous comparative benchmark evaluating Physics-Informed Neural Networks (PINNs), which embed an SIR compartmental model into the neural learning objective via automatic differentiation, against classical Non-linear Least Squares (NLS) calibration with numerical Runge-Kutta integration. Both approaches are tested on synthetic epidemic data across observation counts of \(\:{N}_{t}=10\) and \(\:{N}_{t}=30\) and Gaussian noise levels from 1% to 20% over multiple stochastic realizations. Results show that for fully observed, correctly specified compartmental models, classical Least Squares recovers parameters more accurately and reliably in preliminary runs, achieving median transmission rate errors below 5% (0.089%–4.160%) and 100% compliance in capturing the basic reproduction number (\(\:{R}_{0}\)) within a 10% clinical tolerance margin. In contrast, preliminary PINNs yield median transmission errors of 7.76% to 34.21% alongside a systematic negative parameter bias (up to \(\:-30.43\text{\%}\)) caused by optimization stiffness and gradient scale imbalances between data and physical residual losses. However, extended training experiments (10,000–20,000 iterations) demonstrate that PINN errors reduce asymptotically below 2% to 5%, confirming that early limitations stem from optimization stalling rather than representational incapacity. Classical calibration remains the optimal baseline for fully observed low-dimensional systems, while PINNs offer significant scientific potential for partially observed states and non-parametric functional dynamics.

Authors

Institutions

Publication Details

Journal
Research Square
Published
2026-11-16
DOI
https://doi.org/10.21203/rs.3.rs-11717815/v1
Primary Topic
Model Reduction and Neural Networks
Type
preprint
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
preprint

Physics-Informed Neural Networks for Parameter Estimation in Epidemic Models with Noisy and Limited Data

Zainab Adisa, Isaac Adeyemi, Damilare Bamidele, Omolabake Ademola et al.
1 links
Research Square
Model Reduction and Neural Networks
preprint

Physics-Informed Neural Networks for Parameter Estimation in Epidemic Models with Noisy and Limited Data

Zainab Adisa, Isaac Adeyemi, Damilare Bamidele, Omolabake Ademola, Toluwanimi Akinmade
preprint en

Abstract

Abstract Estimating epidemiological parameters from noisy and limited surveillance data is a critical challenge in mathematical epidemiology and outbreak response. This study presents a rigorous comparative benchmark evaluating Physics-Informed Neural Networks (PINNs), which embed an SIR compartmental model into the neural learning objective via automatic differentiation, against classical Non-linear Least Squares (NLS) calibration with numerical Runge-Kutta integration. Both approaches are tested on synthetic epidemic data across observation counts of \(\:{N}_{t}=10\) and \(\:{N}_{t}=30\) and Gaussian noise levels from 1% to 20% over multiple stochastic realizations. Results show that for fully observed, correctly specified compartmental models, classical Least Squares recovers parameters more accurately and reliably in preliminary runs, achieving median transmission rate errors below 5% (0.089%–4.160%) and 100% compliance in capturing the basic reproduction number (\(\:{R}_{0}\)) within a 10% clinical tolerance margin. In contrast, preliminary PINNs yield median transmission errors of 7.76% to 34.21% alongside a systematic negative parameter bias (up to \(\:-30.43\text{\%}\)) caused by optimization stiffness and gradient scale imbalances between data and physical residual losses. However, extended training experiments (10,000–20,000 iterations) demonstrate that PINN errors reduce asymptotically below 2% to 5%, confirming that early limitations stem from optimization stalling rather than representational incapacity. Classical calibration remains the optimal baseline for fully observed low-dimensional systems, while PINNs offer significant scientific potential for partially observed states and non-parametric functional dynamics.

Research Square
Mountain Top University (NG), Ladoke Akintola University of Technology (NG)
Good health and well-being
Model Reduction and Neural Networks
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon