During the COVID-19 pandemic, forecasting COVID-19 trends to support planning and response was a priority for scientists and decision makers alike. In the United States, COVID-19 forecasting was coordinated by a large group of universities, companies, and government entities led by the Centers for Disease Control and Prevention and the US COVID-19 Forecast Hub (https://covid19forecasthub.org). We evaluated approximately 9.7 million forecasts of weekly state-level COVID-19 cases for predictions 1-4 weeks into the future submitted by 24 teams from August 2020 to December 2021. We assessed coverage of central prediction intervals and weighted interval scores (WIS), adjusting for missing forecasts relative to a baseline forecast, and used a Gaussian generalized estimating equation (GEE) model to evaluate differences in skill across epidemic phases that were defined by the effective reproduction number. Overall, we found high variation in skill across individual models, with ensemble-based forecasts outperforming other approaches. Forecast skill relative to the baseline was generally higher for larger jurisdictions (e.g., states compared to counties). Over time, forecasts generally performed worst in periods of rapid changes in reported cases (either in increasing or decreasing epidemic phases) with 95% prediction interval coverage dropping below 50% during the growth phases of the winter 2020, Delta, and Omicron waves. Ideally, case forecasts could serve as a leading indicator of changes in transmission dynamics. However, while most COVID-19 case forecasts outperformed a naïve baseline model, even the most accurate case forecasts were unreliable in key phases. Further research could improve forecasts of leading indicators, like COVID-19 cases, by leveraging additional real-time data, addressing performance across phases, improving the characterization of forecast confidence, and ensuring that forecasts were coherent across spatial scales. In the meantime, it is critical for forecast users to appreciate current limitations and use a broad set of indicators to inform pandemic-related decision making.

Timely, high-resolution forecasts of infectious disease incidence are useful for policy makers in deciding intervention measures and estimating healthcare resource burden. In this paper, we consider the task of forecasting COVID-19 confirmed cases at the county level for the United States. 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. We present a forecasting pipeline which incorporates probabilistic forecasts from multiple statistical, machine learning and mechanistic methods through a Bayesian ensembling scheme, and has been operational for nearly 6 months serving local, state and federal policymakers in the United States. While showing that the Bayesian ensemble is at least as good as the individual methods, we also show that each individual method contributes significantly for different spatial regions and time points. We compare our model's performance with other similar models being integrated into CDC-initiated COVID-19 Forecast Hub, and show better performance at longer forecast horizons. Finally, we also describe how such forecasts are used to increase lead time for training mechanistic scenario projections. Our work demonstrates that such a real-time high resolution forecasting pipeline can be developed by integrating multiple methods within a performance-based ensemble to support pandemic response.

The COVID-19 pandemic brought to the forefront an unprecedented need for experts, as well as citizens, to visualize spatio-temporal disease surveillance data. Web application dashboards were quickly developed to fill t his g ap, b ut a ll of these dashboards supported a particular niche view of the pandemic (ie, current status or specific r egions). I n t his paper, we describe our work developing our COVID-19 Surveillance Dashboard, which offers a unique view of the pandemic while also allowing users to focus on the details that interest them. From the beginning, our goal was to provide a simple visual tool for comparing, organizing, and tracking near-real-time surveillance data as the pandemic progresses. In developing this dashboard, we also identified 6 key metrics which we propose as a standard for the design and evaluation of real-time epidemic science dashboards. Our dashboard was one of the first released to the public, and continues to be actively visited. Our own group uses it to support federal, state and local public health authorities, and it is used by individuals worldwide to track the evolution of the COVID-19 pandemic, build their own dashboards, and support their organizations as they plan their responses to the pandemic.