Accurate Calibration of Agent-based Epidemiological Models with Neural Network Surrogates
This work addresses the challenge of providing reliable disease dynamics insights and forecasts for major metropolitan areas in the United States, representing an incremental improvement in calibration techniques.
The researchers tackled the problem of calibrating complex agent-based epidemiological models to observed data by developing a neural network surrogate model and a novel posterior estimation method, achieving more accurate parameter estimates and enabling joint fitting of global parameters across regions.
Calibrating complex epidemiological models to observed data is a crucial step to provide both insights into the current disease dynamics, i.e.\ by estimating a reproductive number, as well as to provide reliable forecasts and scenario explorations. Here we present a new approach to calibrate an agent-based model -- EpiCast -- using a large set of simulation ensembles for different major metropolitan areas of the United States. In particular, we propose: a new neural network based surrogate model able to simultaneously emulate all different locations; and a novel posterior estimation that provides not only more accurate posterior estimates of all parameters but enables the joint fitting of global parameters across regions.