DeepGLEAM: A hybrid mechanistic and deep learning model for COVID-19 forecasting
This work addresses forecasting challenges for public health officials during the COVID-19 pandemic, but it is incremental as it builds on existing models.
The authors tackled COVID-19 mortality forecasting by developing DeepGLEAM, a hybrid model that combines a mechanistic simulation model with deep learning to learn correction terms, resulting in improved performance with integrated uncertainty quantification methods.
We introduce DeepGLEAM, a hybrid model for COVID-19 forecasting. DeepGLEAM combines a mechanistic stochastic simulation model GLEAM with deep learning. It uses deep learning to learn the correction terms from GLEAM, which leads to improved performance. We further integrate various uncertainty quantification methods to generate confidence intervals. We demonstrate DeepGLEAM on real-world COVID-19 mortality forecasting tasks.