Physics-informed deep learning for infectious disease forecasting

2025-01-16

AI Summary

To address data scarcity, poor interpretability, and challenges in multi-metric joint modeling for infectious disease forecasting, this paper proposes a physics-informed neural network (PINN) framework integrating mechanistic and data-driven approaches. Methodologically, SEIR-type dynamical equations are embedded into the loss function, and—novelly—a covariant quantum network is introduced to model heterogeneous covariates such as human mobility and vaccination coverage; further, a state-space formulation enables joint prediction of multiple outcomes (cases, deaths, hospitalizations). This work presents the first systematic empirical validation of PINNs on state-level COVID-19 data. On California data, our framework achieves higher accuracy than purely data-driven models and naive baselines, matches the performance of sophisticated GISST models, yet features greater structural simplicity, enhanced interpretability, and markedly improved generalization under limited-data regimes.

Technology Category

• Machine Learning: Calibration & Uncertainty Quantification
• Reasoning under Uncertainty: Relational Probabilistic Models
• Search and Optimization: Metareasoning and Metaheuristics

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Accurate forecasting of contagious illnesses has become increasingly important to public health policymaking, and better prediction could prevent the loss of millions of lives. To better prepare for future pandemics, it is essential to improve forecasting methods and capabilities. In this work, we propose a new infectious disease forecasting model based on physics-informed neural networks (PINNs), an emerging area of scientific machine learning. The proposed PINN model incorporates dynamical systems representations of disease transmission into the loss function, thereby assimilating epidemiological theory and data using neural networks (NNs). Our approach is designed to prevent model overfitting, which often occurs when training deep learning models with observation data alone. In addition, we employ an additional sub-network to account for mobility, vaccination, and other covariates that influence the transmission rate, a key parameter in the compartment model. To demonstrate the capability of the proposed model, we examine the performance of the model using state-level COVID-19 data in California. Our simulation results show that predictions of PINN model on the number of cases, deaths, and hospitalizations are consistent with existing benchmarks. In particular, the PINN model outperforms the basic NN model and naive baseline forecast. We also show that the performance of the PINN model is comparable to a sophisticated Gaussian infection state space with time dependence (GISST) forecasting model that integrates the compartment model with a data observation model and a regression model for inferring parameters in the compartment model. Nonetheless, the PINN model offers a simpler structure and is easier to implement. Our results show that the proposed forecaster could potentially serve as a new computational tool to enhance the current capacity of infectious disease forecasting.

Problem

• Infectious Disease Prediction
• Public Health Decision Making
• Pandemic Preparedness

Innovation

• Physics-Informed Neural Networks (PINN)
• Epidemic Prediction
• External Factors Integration