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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Su, Yiqi, Lee, Ray, Cui, Jiaming, Ramakrishnan, Naren
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914309003542528
author Su, Yiqi
Lee, Ray
Cui, Jiaming
Ramakrishnan, Naren
author_facet Su, Yiqi
Lee, Ray
Cui, Jiaming
Ramakrishnan, Naren
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2602_06323
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle How (Not) to Hybridize Neural and Mechanistic Models for Epidemiological Forecasting
Su, Yiqi
Lee, Ray
Cui, Jiaming
Ramakrishnan, Naren
Machine Learning
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.
title How (Not) to Hybridize Neural and Mechanistic Models for Epidemiological Forecasting
topic Machine Learning
url https://arxiv.org/abs/2602.06323