机制流行病学模型广泛用于支持传染病预测和公共卫生决策。此类模型的贝叶斯校准通常使用马尔可夫链蒙特卡罗 (MCMC), 进行，对于高维非线性系统和重复的近实时分析来说，计算成本可能会很高。在这里,，我们使用神经后验估计作为机械 SECIR 流行病学模型的贝叶斯校准的可扩展替代方案，使用 2020 年德国的 COVID-19 重症监护病房 (ICU) 占用数据来研究基于模拟的推理 (SBI)。我们使用 31 天的推理窗口和更具挑战性的涉及多重传播的 201 天重建问题，比较了多个流行阶段的 SBI 和 MCMC改变点。使用 Wasserstein 距离和 Kullback-Leibler 散度以及后验预测检查来定量评估后验一致性。在 31 天的窗口中，, SBI 恢复了后验分布，与 MCMC 非常一致，同时准确地再现了观察到的 ICU 轨迹。在 201 天的设置中，尽管不确定性增加，, SBI 仍保留了主要的后部结构。与仅限在 CPU 上运行的 MCMC, 相比，SBI, 通过结合 CPU 和 GPU 资源, 大大减少了计算运行时间。而 MCMC 需要大约 1000 秒才能解决 31 天的推理问题, SBI 在单个 GPU 上大约 60-70 秒内实现了类似的后验和预测性能。对于 201 天的推理问题, SBI 平均需要 157 秒,，而 MCMC 运行需要超过 19,000 秒。我们的结果表明，SBI 为机械流行病学模型, 的贝叶斯校准提供了一个快速且计算高效的框架，支持重复的近实时推理和快速爆发分析。

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.

科目:人工智能(cs.AI)

Subjects: Artificial Intelligence (cs.AI)