Incorporating Deep Learning Into System Dynamics: Amortized Bayesian Inference for Scalable Likelihood‐Free Parameter Estimation

Abstract

Estimating parameters and their credible intervals for complex system dynamics models is challenging but critical to continu-ous model improvement and reliable communication with an increasing fraction of audiences. The purpose of this study is tointegrate Amortized Bayesian Inference (ABI) methods with system dynamics. Utilizing Neural Posterior Estimation (NPE), wetrain neural networks using synthetic data (pairs of ground truth parameters and outcome time series) to estimate parameters ofsystem dynamics models. We apply this method to two example models: a simple Random Walk model and a moderately complexSEIRb model. We show that the trained neural networks can output the posterior for parameters instantly given new unseentime series data. Our analysis highlights the potential of ABI to facilitate a principled, scalable, and likelihood-free inferenceworkflow that enhance the integration of models of complex systems with data. Accompanying code streamlines application todiverse system dynamics models.