Bitte benutzen Sie diese Kennung, um auf die Ressource zu verweisen:
http://dx.doi.org/10.25673/103473
Titel: | Predictive performance of multi-model ensemble forecasts of COVID-19 across European nations |
Autor(en): | Sherratt, Katharine Gruson, Hugo Grah, Rok Johnson, Helen Niehus, Rene Prasse, Bastian Sandmann, Frank Deuschel, Jannik Wolffram, Daniel Abbott, Sam Ullrich, Alexander Gibson, Graham Ray, Evan L. Reich, Nicholas G. Sheldon, Daniel Wang, Yijin Wattanachit, Nutcha Wang, Lijing Trnka, Jan Obozinski, Guillaume Sun, Tao Thanou, Dorina Pottier, Loic Krymova, Ekaterina Meinke, Jan H. Barbarossa, Maria Vittoria ![]() Leithäuser, Neele ![]() Mohring, Jan Schneider, Johanna Wlazło, Jarosław ![]() Fuhrmann, Jan Lange, Berit ![]() Rodiah, Isti ![]() Baccam, Prasith Gurung, Heidi Stage, Steven Suchoski, Bradley Budzinski, Jozef Walraven, Robert Villanueva, Inmaculada Tucek, Vit Smid, Martin Zajíček, Milan Pérez Álvarez, Cesar Reina, Borja Bosse, Nikos I. Meakin, Sophie R. Castro, Lauren Fairchild, Geoffrey Michaud, Isaac Osthus, Dave Alaimo Di Loro, Pierfrancesco Maruotti, Antonello Eclerová, Veronika Kraus, Andrea Kraus, David Pribylova, Lenka Dimitris, Bertsimas Li, Michael Lingzhi ![]() Saksham, Soni Dehning, Jonas Mohr, Sebastian Priesemann, Viola ![]() Redlarski, Grzegorz Bejar Haro, Benjamin ![]() Ardenghi, Giovanni Parolini, Nicola ![]() Ziarelli, Giovanni Bock, Wolfgang ![]() Heyder, Stefan Hotz, Thomas ![]() Singh, David E. Guzman-Merino, Miguel Aznarte, Jose L. Moriña, David Alonso, Sergio ![]() Álvarez, Enric López, Daniel Prats, Clara Burgard, Jan Pablo ![]() Rodloff, Arne Zimmermann, Tom Kuhlmann, Alexander Zibert, Janez Pennoni, Fulvia ![]() Divino, Fabio Català, Marti Lovison, Gianfranco Giudici, Paolo ![]() Tarantino, Barbara Bartolucci, Francesco ![]() Jona Lasinio, Giovanna Mingione, Marco Farcomeni, Alessio ![]() Srivastava, Ajitesh Montero-Manso, Pablo Adiga, Aniruddha Hurt, Benjamin Lewis, Bryan Marathe, Madhav Porebski, Przemyslaw Venkatramanan, Srinivasan Bartczuk, Rafal P. Dreger, Filip Gambin, Anna ![]() Gogolewski, Krzysztof Gruziel-Słomka, Magdalena Krupa, Bartosz Moszyński, Antoni Niedzielewski, Karol Nowosielski, Jedrzej Radwan, Maciej Rakowski, Franciszek Semeniuk, Marcin Szczurek, Ewa ![]() Zieliński, Jakub Kisielewski, Jan Pabjan, Barbara Kirsten, Holger ![]() Kheifetz, Yuri Scholz, Markus Biecek, Przemysław ![]() Bodych, Marcin Filinski, Maciej Idzikowski, Radoslaw Krueger, Tyll Ozanski, Tomasz Bracher, Johannes Funk, Sebastian ![]() |
Erscheinungsdatum: | 2023 |
Art: | Artikel |
Sprache: | Englisch |
Zusammenfassung: | Background: Short-term forecasts of infectious disease burden can contribute to situational awareness and aid capacity planning. Based on best practice in other fields and recent insights in infectious disease epidemiology, one can maximise the predictive performance of such forecasts if multiple models are combined into an ensemble. Here, we report on the performance of ensembles in predicting COVID-19 cases and deaths across Europe between 08 March 2021 and 07 March 2022. Methods: We used open-source tools to develop a public European COVID-19 Forecast Hub. We invited groups globally to contribute weekly forecasts for COVID-19 cases and deaths reported by a standardised source for 32 countries over the next 1–4 weeks. Teams submitted forecasts from March 2021 using standardised quantiles of the predictive distribution. Each week we created an ensemble forecast, where each predictive quantile was calculated as the equally-weighted average (initially the mean and then from 26th July the median) of all individual models’ predictive quantiles. We measured the performance of each model using the relative Weighted Interval Score (WIS), comparing models’ forecast accuracy relative to all other models. We retrospectively explored alternative methods for ensemble forecasts, including weighted averages based on models’ past predictive performance. Results: Over 52 weeks, we collected forecasts from 48 unique models. We evaluated 29 models’ forecast scores in comparison to the ensemble model. We found a weekly ensemble had a consistently strong performance across countries over time. Across all horizons and locations, the ensemble performed better on relative WIS than 83% of participating models’ forecasts of incident cases (with a total N=886 predictions from 23 unique models), and 91% of participating models’ forecasts of deaths (N=763 predictions from 20 models). Across a 1–4 week time horizon, ensemble performance declined with longer forecast periods when forecasting cases, but remained stable over 4 weeks for incident death forecasts. In every forecast across 32 countries, the ensemble outperformed most contributing models when forecasting either cases or deaths, frequently outperforming all of its individual component models. Among several choices of ensemble methods we found that the most influential and best choice was to use a median average of models instead of using the mean, regardless of methods of weighting component forecast models. Conclusions: Our results support the use of combining forecasts from individual models into an ensemble in order to improve predictive performance across epidemiological targets and populations during infectious disease epidemics. Our findings further suggest that median ensemble methods yield better predictive performance more than ones based on means. Our findings also highlight that forecast consumers should place more weight on incident death forecasts than incident case forecasts at forecast horizons greater than 2 weeks. |
URI: | https://opendata.uni-halle.de//handle/1981185920/105425 http://dx.doi.org/10.25673/103473 |
Open-Access: | ![]() |
Nutzungslizenz: | ![]() |
Journal Titel: | eLife |
Verlag: | eLife Sciences Publications |
Verlagsort: | Cambridge |
Band: | 12 |
Originalveröffentlichung: | 10.7554/eLife.81916 |
Seitenanfang: | 1 |
Seitenende: | 23 |
Enthalten in den Sammlungen: | Open Access Publikationen der MLU |
Dateien zu dieser Ressource:
Datei | Beschreibung | Größe | Format | |
---|---|---|---|---|
elife-81916-v2.pdf | 2 MB | Adobe PDF | ![]() Öffnen/Anzeigen |