Simulation-based inference for rapid Bayesian parameter estimation in epidemiological models: a comparison with MCMC

2026-06-25

AI Summary

This study addresses the computational burden of traditional Markov chain Monte Carlo (MCMC) methods in Bayesian calibration of high-dimensional, nonlinear epidemiological models, which hinders near real-time analysis. For the first time, simulation-based inference (SBI) is applied to multi-stage, long-window Bayesian inference in a complex SECIR model, leveraging neural posterior estimation to efficiently calibrate parameters against German ICU data from the 2020 COVID-19 pandemic. Comprehensive evaluation via Wasserstein distance, Kullback–Leibler divergence, and posterior predictive checks demonstrates that SBI achieves comparable posterior accuracy while drastically improving computational efficiency: it completes a 31-day calibration window in 60–70 seconds (versus ~1000 seconds for MCMC) and reconstructs a 201-day trajectory in 157 seconds (compared to over 19,000 seconds with MCMC), thereby enabling near real-time epidemic analysis.

Abstract

Mechanistic epidemiological models are widely used to support infectious disease forecasting and public-health decision making. Bayesian calibration of such models is commonly performed using Markov chain Monte Carlo (MCMC), which can become computationally expensive for high-dimensional nonlinear systems and repeated near-real-time analyses. Here, we investigate simulation-based inference (SBI) using neural posterior estimation as a scalable alternative for Bayesian calibration of a mechanistic SECIR epidemiological model using COVID-19 intensive care unit (ICU) occupancy data from Germany during 2020. We compared SBI and MCMC across multiple epidemic phases using both 31-day inference windows and a substantially more challenging 201-day reconstruction problem involving multiple transmission change points. Posterior agreement was evaluated quantitatively using Wasserstein distances and Kullback-Leibler divergences together with posterior predictive checks. Across the 31-day windows, SBI recovered posterior distributions in strong agreement with MCMC while accurately reproducing observed ICU trajectories. In the 201-day setting, SBI preserved the dominant posterior structure despite increased uncertainty. SBI, by combining CPU and GPU resources, substantially reduced computational runtime compared with MCMC, which was restricted to running on CPUs. Whereas MCMC required approximately 1000 seconds for the 31-day inference problems, SBI achieved comparable posterior and predictive performance in approximately 60-70 seconds on a single GPU. For the 201-day inference problem, SBI required an average of 157 seconds, while the MCMC runs took over 19,000 seconds. Our results demonstrate that SBI provides a rapid and computationally efficient framework for Bayesian calibration of mechanistic epidemiological models, supporting repeated near-real-time inference and rapid outbreak analysis.

Problem

• Bayesian calibration
• epidemiological models
• computational efficiency
• real-time inference
• parameter estimation

Innovation

• simulation-based inference
• neural posterior estimation
• Bayesian calibration
• epidemiological modeling
• computational efficiency