National and subnational short-term forecasting of COVID-19 in Germany and Poland during early 2021.
Johannes BracherDaniel WolfframJannik DeuschelKonstantin GörgenJakob L KettererAlexander UllrichSam AbbottMaria Vittoria BarbarossaDimitris BertsimasSangeeta N BhatiaMarcin BodychNikos I BosseJan Pablo BurgardLauren A CastroGeoffrey FairchildJochen FiedlerJan FuhrmannSebastian FunkAnna GambinKrzysztof GogolewskiStefan HeyderThomas HotzYuri KheifetzHolger KirstenTyll KruegerEkaterina KrymovaNeele LeithäuserMichael Lingzhi LiJan H MeinkeBłażej MiasojedowIsaac J MichaudJan MohringPierre NouvelletJedrzej M NowosielskiTomasz OzanskiMaciej RadwanFranciszek RakowskiMarkus ScholzSaksham SoniAjitesh SrivastavaTilmann GneitingMelanie SchienlePublished in: Communications medicine (2022)
Multi-model approaches can help to improve the performance of epidemiological forecasts. However, while death numbers can be predicted with some success based on current case and hospitalization data, predictability of case numbers remains low beyond quite short time horizons. Additional data sources including sequencing and mobility data, which were not extensively used in the present study, may help to improve performance.