Epi$^2$-Net: Advancing Epidemic Dynamics Forecasting with Physics-Inspired Neural Networks

2025-08-04

AI Summary

Contemporary epidemiological forecasting models exhibit a dichotomy: mechanistic models suffer from rigid structural assumptions, while data-driven approaches lack epidemiological constraints. To bridge this gap, we propose “Neural Epidemic Propagation,” the first framework that deeply integrates explicit physical priors—such as transmission dynamics and spatial coupling—with neural representations. Methodologically, we design a physics-informed deep learning architecture that combines neural ordinary differential equations (ODEs) to model continuous-time disease evolution, graph neural networks (GNNs) to encode inter-regional transmission topology, and a physics-constrained loss function to enforce model consistency with epidemiological principles. Extensive experiments on multiple real-world epidemic datasets demonstrate that our approach significantly outperforms state-of-the-art baselines in both prediction accuracy and robustness. Crucially, it achieves a synergistic balance between mechanistic interpretability and data adaptability, offering reliable, actionable insights for public health decision-making.

Technology Category

• Machine Learning: Deep Neural Architectures and Foundation Models
• Search and Optimization: Learning to Search
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Social Networks and Social Media: Influence propagation, information diffusion, and the prediction on networks
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Advancing epidemic dynamics forecasting is vital for targeted interventions and safeguarding public health. Current approaches mainly fall into two categories: mechanism-based and data-driven models. Mechanism-based models are constrained by predefined compartmental structures and oversimplified system assumptions, limiting their ability to model complex real-world dynamics, while data-driven models focus solely on intrinsic data dependencies without physical or epidemiological constraints, risking biased or misleading representations. Although recent studies have attempted to integrate epidemiological knowledge into neural architectures, most of them fail to reconcile explicit physical priors with neural representations. To overcome these obstacles, we introduce Epi$^2$-Net, a Epidemic Forecasting Framework built upon Physics-Inspired Neural Networks. Specifically, we propose reconceptualizing epidemic transmission from the physical transport perspective, introducing the concept of neural epidemic transport. Further, we present a physic-inspired deep learning framework, and integrate physical constraints with neural modules to model spatio-temporal patterns of epidemic dynamics. Experiments on real-world datasets have demonstrated that Epi$^2$-Net outperforms state-of-the-art methods in epidemic forecasting, providing a promising solution for future epidemic containment. The code is available at: https://anonymous.4open.science/r/Epi-2-Net-48CE.

Problem

• Overcoming limitations of mechanism-based and data-driven epidemic models
• Integrating physical constraints with neural networks for accurate forecasting
• Improving spatio-temporal epidemic dynamics prediction with physics-inspired AI

Innovation

• Physics-inspired neural networks for epidemic forecasting
• Neural epidemic transport concept introduced
• Physical constraints integrated with neural modules