All Models Are Useful: Bayesian Ensembling for Robust High-Resolution COVID-19 Forecasting
Speaker: Aniruddha Adiga, Research Scientist within the Network Systems Science and Advanced Computing division at the University of Virginia's Biocomplexity Institute
Abstract: Timely, high-resolution forecasts of infectious disease incidence are useful for policymakers in deciding intervention measures and estimating healthcare resource burden. Although multiple methods have been explored for this task, their performance has varied across space and time due to noisy data and the inherent dynamic nature of the pandemic. In this talk, we discuss our efforts towards forecasting COVID-19 confirmed cases which have continued to serve local, state, and multinational health agencies for over a year. We present a forecasting pipeline that incorporates probabilistic forecasts from multiple statistical, machine-learning, and mechanistic methods through a Bayesian ensembling scheme and can produce forecasts at different resolutions: county, state, and national level. In terms of forecast evaluation, while showing that the Bayesian ensemble is at least as good as the individual methods, we also show that each individual method contributes significantly to different spatial regions and time points. We compare our model's performance with other similar models being integrated into the CDC-initiated COVID-19 Forecast Hub. In addition, we have developed a public-access interactive dashboard for visualizing and evaluating our model forecasts and will discuss some of its functionalities.
Bio: Aniruddha Adiga is a Research Scientist at the NSSAC Division of the Biocomplexity Institute and Initiative, UVA. He completed his Ph.D. from the Department of Electrical Engineering, Indian Institute of Science (IISc), Bangalore, India, and has held the position of Postdoctoral fellow at IISC, North Carolina State University, and UVA. His research areas include signal processing, machine learning, data mining, forecasting, and big data analysis. At NSSAC, his primary focus has been the analysis and development of forecasting systems for epidemiological signals such as influenza-like illness and COVID-19 using auxiliary data sources.