Skip directly to site content Skip directly to page options Skip directly to A-Z link Skip directly to A-Z link Skip directly to A-Z link

Disclaimer: Early release articles are not considered as final versions. Any changes will be reflected in the online version in the month the article is officially released.

Volume 30, Number 9—September 2024
Research Letter

Optimizing Disease Outbreak Forecast Ensembles

Spencer J. FoxComments to Author , Minsu Kim, Lauren Ancel Meyers, Nicholas G. Reich, and Evan L. Ray
Author affiliations: University of Georgia, Athens, Georgia, USA (S.J. Fox); University of Massachusetts Amherst, Amherst, Massachusetts, USA (M. Kim, N.G. Reich, E.L. Ray); University of Texas at Austin, Austin, Texas, USA (L.A. Meyers); Dell Medical School, Austin (L.A. Meyers); Santa Fe Institute, Santa Fe, New Mexico, USA (L.A. Meyers)

Main Article

Figure 2

Summarized ensemble forecast scores from collaborative forecast efforts in study of optimizing disease outbreak forecasting ensembles. Scores correspond to the average forecast performance during testing periods across all dates, locations, and forecast horizons (Appendix Table 1). All scores are standardized by the baseline forecast model for that metric (Y = 1). Scores <1 indicate better accuracy than baseline. A) COVID-19 cases with 15 included models. B) COVID-19 admissions with 17 included models. C) COVID-19 deaths with 19 included models. D) Influenza admissions with 21 included models. D) Influenza-like illness with 23 included models. Solid black lines indicate mean scores; gray shading indicates minimum–maximum range. Horizontal purple dashed line indicates unweighted published ensemble used as standard.

Figure 2. Summarized ensemble forecast scores from collaborative forecast efforts in study of optimizing disease outbreak forecasting ensembles. Scores correspond to the average forecast performance during testing periods across all dates, locations, and forecast horizons (Appendix Table 1). All scores are standardized by the baseline forecast model for that metric (Y = 1). Scores <1 indicate better accuracy than baseline. A) COVID-19 cases with 15 included models. B) COVID-19 admissions with 17 included models. C) COVID-19 deaths with 19 included models. D) Influenza admissions with 21 included models. D) Influenza-like illness with 23 included models. Solid black lines indicate mean scores; gray shading indicates minimum–maximum range. Horizontal purple dashed line indicates unweighted published ensemble used as standard.

Main Article

Page created: August 01, 2024
Page updated: August 14, 2024
Page reviewed: August 14, 2024
The conclusions, findings, and opinions expressed by authors contributing to this journal do not necessarily reflect the official position of the U.S. Department of Health and Human Services, the Public Health Service, the Centers for Disease Control and Prevention, or the authors' affiliated institutions. Use of trade names is for identification only and does not imply endorsement by any of the groups named above.
file_external