COVID-19 Forecasts: Deaths

Reported and forecasted new and total COVID-19 deaths as of May 2, 2022.

Interpretation of Forecasts of New and Total Deaths

• This week’s national ensemble predicts that the number of newly reported COVID-19 deaths will likely increase over the next 4 weeks, with 1,600 to 4,600 new deaths likely reported in the week ending May 28, 2022. The national ensemble predicts that a total of 1,000,000 to 1,007,000 COVID-19 deaths will be reported by this date.
• The state- and territory-level ensemble forecasts predict that over the next 4 weeks, the trends in numbers of future reported deaths are uncertain or predicted to remain stable in all states and territories.
• Ensemble forecasts combine diverse independent team forecasts into one forecast. While they have been among the most reliable forecasts in performance over time, even the ensemble forecasts have not reliably predicted rapid changes in the trends of reported cases, hospitalizations, and deaths. They should not be relied upon for making decisions about the possibility or timing of rapid changes in trends.

National Forecast

Download full-sized imageimage icon

• The figures show the number of new (top row) and total (bottom row) COVID-19 deaths reported in the United States each week from February 26 through April 30 and forecasted over the next 4 weeks, through May 28.
• This week, 20 modeling groups contributed a forecast that was eligible for inclusion in the new or total deaths ensemble forecasts for at least one jurisdiction.
• Models make various assumptions about the levels of social distancing and other interventions, which may not reflect recent changes in behavior. See model descriptions below for details on the assumptions and methods used to produce the forecasts.

Download national forecast data excel icon[XLS – 17 KB]

State Forecasts

State-level forecasts show the predicted number of new COVID-19 deaths for the next 4 weeks by state. Each state forecast figure uses a different scale due to differences in the number of COVID-19 deaths between states and only forecasts meeting a set of ensemble inclusion criteria are shown. Further details are available here: https://covid19forecasthub.org/doc/ensemble/external icon. Plots of the state-level ensemble forecast and the underlying data can be downloaded below.

Download state forecasts pdf icon[PDF – 1 MB]

Download forecast data excel icon[CSV – 577 KB]

Additional forecast data and information about submitting forecasts are available at the COVID-19 Forecast Hubexternal icon.

Forecast Inclusion, Evaluation, and Assumptions

Forecasts are listed when they meet a set of submission and data quality requirements and a subset are included in the ensemble. Further details are available here: https://covid19forecasthub.org/doc/ensembleexternal icon.

Ensemble and specific team forecast performance is evaluated using a variety of metrics, including the assessment of prediction interval coverage. This assessment is available at https://delphi.cmu.edu/forecast-eval/external icon.

The forecasts make different assumptions about social distancing measures. Additional individual model details are available here: https://github.com/cdcepi/COVID-19-Forecasts/blob/master/COVID-19_Forecast_Model_Descriptions.md.external icon Details on the ensemble’s accuracy in short-term predictions and its usefulness as a real-time tool to help guide policy and planning can be found here: Ensemble Forecasts of Coronavirus Disease 2019 (COVID-19) in the U.S.external icon

Intervention assumptions fall into multiple categories:

• These modeling groups make assumptions about how levels of social distancing will change in the future:
  • Columbia Universityexternal icon (Model: Columbia)
  • Massachusetts Institute of Technology, Operations Research Centerexternal icon (Model: MIT-ORC)
  • Predictive Science Inc.external icon (Model: PSI)
  • University of California, Los Angelesexternal icon (Model: UCLA)

• These modeling groups assume that existing social distancing measures will continue through the projected 4-week time period:
  • AIpertexternal icon (Model: AIpert)
  • Bob Paganoexternal icon (Model: BPagano)
  • Georgia Institute of Technology, College of Computingexternal icon (Model: GT-DeepCOVID)
  • Hong Kong University of Science and Technologyexternal icon (Model: DNN)
  • Johns Hopkins University Applied Physics Labexternal icon (Model: JHU-APL)
  • Johns Hopkins University, Infectious Disease Dynamics Labexternal icon (Model: JHU-IDD)
  • Lehigh University Computational Uncertainty Labexternal icon (Model: LUcompUncertLab-VAR_3streams)
  • Massachusetts Institute of Technology, Cassandraexternal icon (Model: MIT-Cassandra)
  • Massachusetts Institute of Technology, Institute for Data, Systems, and Societyexternal icon (Model: MIT-ISOLAT)
  • Massachusetts Institute of Technology, Laboratory of Computational Physiologyexternal icon (Model: MIT-LCP)
  • Northeastern University, Laboratory for the Modeling of Biological and Socio-technical Systemsexternal icon (Model: MOBS)
  • Qi-Jun Hongexternal icon (Model: QJHong)
  • Robert Walravenexternal icon (Model: ESG)
  • Steve McConnellexternal icon (Model: CovidComplete)
  • University of California, San Diego and Northeastern Universityexternal icon (Model: UCSD-NEU)
  • University of Southern Californiaexternal icon (Model: USC)

¹ The full range of the prediction intervals is not visible for all state plots. Please see the forecast data for the full range of state-specific prediction intervals.