Modeling COVID-19 Dynamics in German States Using Physics-Informed Neural Networks

2025-10-08

AI Summary

This study addresses the challenge of jointly inferring time-varying transmission and recovery parameters—and thereby the effective reproduction number $R_t$—from noisy, regional COVID-19 case data across Germany’s 16 federal states. Method: We propose a multi-region, time-varying SIR modeling framework grounded in physics-informed neural networks (PINNs), which seamlessly integrates ODE-based epidemiological constraints with data-driven fitting—without requiring strong prior assumptions on parameter forms. To our knowledge, this is the first systematic application of PINNs to long-term (2020–2023), fine-grained, cross-regional COVID-19 dynamics modeling. Contribution/Results: Our approach reveals pronounced spatiotemporal heterogeneity in transmission and recovery rates across states, with dynamics closely aligned to vaccination coverage milestones and public health intervention timings. It establishes a scalable, physics-informed learning paradigm for parameter identifiability analysis under data noise and enables quantitative attribution of policy impacts in complex infectious disease systems.

Technology Category

• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Reasoning under Uncertainty: Relational Probabilistic Models
• Intelligent Robots: State Estimation

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• User Modeling, Personalization and Recommendation: Psychology-informed user models and recommender systems
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

The COVID-19 pandemic has highlighted the need for quantitative modeling and analysis to understand real-world disease dynamics. In particular, post hoc analyses using compartmental models offer valuable insights into the effectiveness of public health interventions, such as vaccination strategies and containment policies. However, such compartmental models like SIR (Susceptible-Infectious-Recovered) often face limitations in directly incorporating noisy observational data. In this work, we employ Physics-Informed Neural Networks (PINNs) to solve the inverse problem of the SIR model using infection data from the Robert Koch Institute (RKI). Our main contribution is a fine-grained, spatio-temporal analysis of COVID-19 dynamics across all German federal states over a three-year period. We estimate state-specific transmission and recovery parameters and time-varying reproduction number (R_t) to track the pandemic progression. The results highlight strong variations in transmission behavior across regions, revealing correlations with vaccination uptake and temporal patterns associated with major pandemic phases. Our findings demonstrate the utility of PINNs in localized, long-term epidemiological modeling.

Problem

• Modeling COVID-19 transmission dynamics across German states
• Estimating state-specific epidemiological parameters from noisy data
• Analyzing regional variations in pandemic progression and interventions

Innovation

• Physics-Informed Neural Networks solve SIR inverse problem
• Estimate state-specific transmission and recovery parameters
• Track time-varying reproduction number across German states