Seq2Seq Surrogates of Epidemic Models to Facilitate Bayesian Inference

TL;DR

This paper demonstrates that deep seq2seq models can serve as fast, accurate surrogates for complex epidemic models, enabling efficient Bayesian inference and policy exploration.

Contribution

The authors introduce a novel seq2seq surrogate modeling approach for epidemic models, significantly reducing computational costs while maintaining accuracy.

Findings

Seq2seq surrogates replicate complex epidemic dynamics accurately.

Surrogates enable predictions thousands of times faster than traditional models.

Facilitates robust Bayesian inference for epidemic analysis.

Abstract

Epidemic models are powerful tools in understanding infectious disease. However, as they increase in size and complexity, they can quickly become computationally intractable. Recent progress in modelling methodology has shown that surrogate models can be used to emulate complex epidemic models with a high-dimensional parameter space. We show that deep sequence-to-sequence (seq2seq) models can serve as accurate surrogates for complex epidemic models with sequence based model parameters, effectively replicating seasonal and long-term transmission dynamics. Once trained, our surrogate can predict scenarios a several thousand times faster than the original model, making them ideal for policy exploration. We demonstrate that replacing a traditional epidemic model with a learned simulator facilitates robust Bayesian inference.