EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Ensemble forecasts of COVID-19 activity to support Australia’s pandemic response: 2020–22

Robert Moss iD, Ruarai J Tobin iD, Mitchell O'Hara-Wild iD, Adeshina I Adekunle, Dennis Liu, Tobin South, Dylan J Morris, Gerard E Ryan iD, Tianxiao Hao, Aarathy Babu, Katharine L Senior iD, James G Wood und 7 weitere

PLOS Computational Biology · 2026

DOI: 10.1371/journal.pcbi.1014199 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS Computational Biology, 2026. Verfasst von Robert Moss und 18 weiteren Autor:innen. Beteiligte Einrichtung: Melbourne School of Population and Global Health, The University of Melbourne, Melbourne, Victoria, Australia. Hauptthemen laut MEDLINE: Forecasting, COVID-19, Ensemble Learning. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 53 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Department of Health and Aged Care, Australian Government, National Health and Medical Research Council.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

During the COVID-19 pandemic, many countries used real-time data analyses, predictive modelling, and COVID-19 case forecasts, to incorporate emerging evidence into their decisions. In Australia, national and jurisdictional public health responses were informed by weekly ensemble forecasts of daily COVID-19 case counts for each of Australia’s eight states and territories, produced by a consortium of researchers under contract with the Australian Government. As members of this consortium, who produced these forecasts at each week, we now retrospectively evaluate approximately 100,000 predictions for daily case counts 1–28 days into the future, generated between July 2020 and December 2022, and report here (a) how the ensemble forecasts supported public health responses; (b) how well the ensemble forecast performed, relative to the forecasts produced by each contributing team; and (c) how we refined our reporting and visualisations to ensure that outputs were interpreted appropriately. Similar to COVID-19 forecasting studies in other countries, we found that the ensemble forecast consistently out-performed the individual model forecasts, and that performance was lowest when there were rapid changes in the epidemiology, such as periods around epidemic peaks. Our consortium’s internal peer-review process allowed us to explain how features of each ensemble forecast related to the design of the individual models, and this helped enable public health stakeholders to interpret the forecasts appropriately. Ultimately, our forecasts provided information that supported public health responses during periods of different policy goals, and over a wide range of epidemic scenarios.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

ForecastingCOVID-19Ensemble LearningHumansAustraliaPandemicsSARS-CoV-2Computational BiologyPublic HealthRetrospective StudiesPredictive Learning Models

Autor:innen und Institutionen

  • Melbourne School of Population and Global Health, The University of Melbourne, Melbourne, Victoria, Australia.
  • Department of Econometrics and Business Statistics, Monash University, Melbourne, Victoria, Australia.
  • Defence Science and Technology Group, Melbourne, Victoria, Australia.
  • School of Computer and Mathematical Sciences, The University of Adelaide, Adelaide, South Australia, Australia.
  • The Kids Research Institute Australia, Perth, Western Australia, Australia.
  • School of Population Health, University of New South Wales, Sydney, New South Wales, Australia.

ORCID-Profile: Robert Moss, Ruarai J Tobin, Mitchell O'Hara-Wild, Gerard E Ryan, Katharine L Senior

Förderung

  • Department of Health and Aged Care, Australian Government
  • National Health and Medical Research Council

Zitieren

APA

Moss, R., Tobin, R. J., O'Hara-Wild, M., Adekunle, A. I., Liu, D., South, T., Morris, D. J., Ryan, G. E., Hao, T., Babu, A., Senior, K. L., Wood, J. G., Golding, N., Ross, J. V., Dawson, P., Hyndman, R. J., Price, D. J., McCaw, J. M., & Shearer, F. M. (2026). Ensemble forecasts of COVID-19 activity to support Australia’s pandemic response: 2020–22. PLOS Computational Biology. https://doi.org/10.1371/journal.pcbi.1014199

Vancouver

Moss R, Tobin RJ, O'Hara-Wild M, Adekunle AI, Liu D, South T, et al. Ensemble forecasts of COVID-19 activity to support Australia’s pandemic response: 2020–22. PLOS Computational Biology. 2026. doi:10.1371/journal.pcbi.1014199

BibTeX
@article{Moss2026,
  author = {Moss, Robert and Tobin, Ruarai J and O'Hara-Wild, Mitchell and Adekunle, Adeshina I and Liu, Dennis and South, Tobin and Morris, Dylan J and Ryan, Gerard E and Hao, Tianxiao and Babu, Aarathy and Senior, Katharine L and Wood, James G and Golding, Nick and Ross, Joshua V and Dawson, Peter and Hyndman, Rob J and Price, David J and McCaw, James M and Shearer, Freya M},
  title = {Ensemble forecasts of COVID-19 activity to support Australia’s pandemic response: 2020–22},
  journal = {PLOS Computational Biology},
  year = {2026},
  doi = {10.1371/journal.pcbi.1014199}
}
Kostenlos starten →