How (Not) to Hybridize Neural and Mechanistic Models for Epidemiological Forecasting

2026-02-06

AI Summary

This work proposes a novel approach to explicitly model time-varying epidemic dynamics, addressing the limited predictive performance of conventional neuro-mechanistic hybrid models under partial observability and non-stationary transmission dynamics. By decomposing infection time series into trend, seasonal, and residual components at multiple scales, the method treats these as interpretable control signals for a controlled neural ordinary differential equation (ODE) coupled with a mechanistic epidemiological model. This enables joint inference and forecasting of time-varying transmission, recovery, and waning immunity rates without requiring auxiliary covariates. Evaluated across diverse epidemic scenarios, the approach significantly outperforms strong baselines, reducing long-term prediction RMSE by 15–35%, decreasing peak timing errors by 1–3 weeks, lowering peak magnitude bias by up to 30%, and simultaneously enhancing model robustness and interpretability.

Technology Category

• Search and Optimization: Mixed Discrete/Continuous Search
• Reasoning under Uncertainty: Relational Probabilistic Models
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization

Abstract

Epidemiological forecasting from surveillance data is a hard problem and hybridizing mechanistic compartmental models with neural models is a natural direction. The mechanistic structure helps keep trajectories epidemiologically plausible, while neural components can capture non-stationary, data-adaptive effects. In practice, however, many seemingly straightforward couplings fail under partial observability and continually shifting transmission dynamics driven by behavior, waning immunity, seasonality, and interventions. We catalog these failure modes and show that robust performance requires making non-stationarity explicit: we extract multi-scale structure from the observed infection series and use it as an interpretable control signal for a controlled neural ODE coupled to an epidemiological model. Concretely, we decompose infections into trend, seasonal, and residual components and use these signals to drive continuous-time latent dynamics while jointly forecasting and inferring time-varying transmission, recovery, and immunity-loss rates. Across seasonal and non-seasonal settings, including early outbreaks and multi-wave regimes, our approach reduces long-horizon RMSE by 15-35%, improves peak timing error by 1-3 weeks, and lowers peak magnitude bias by up to 30% relative to strong time-series, neural ODE, and hybrid baselines, without relying on auxiliary covariates.

Problem

• epidemiological forecasting
• hybrid modeling
• partial observability
• non-stationary dynamics
• transmission dynamics

Innovation

• controlled neural ODE
• non-stationarity modeling
• multi-scale decomposition
• hybrid epidemiological forecasting
• time-varying transmission dynamics