Teams from anywhere in the world are invited to submit forecasts once a week for one or more of the countries. Take a look at the submission instructions and get in touch with any questions.

Teams

Model name Affiliation Methods Complete metadata
BIOCOMSC-Gompertz BIOCOMSC Empirical model based on cases and deaths dynamics. Metadata
bisop-seirfilter Centre for Modelling of Biological and Social Processes please see https://www.medrxiv.org/content/10.1101/2021.02.16.21251834v1 Metadata
bisop-seirfilterlite Centre for Modelling of Biological and Social Processes A simple stochastic SEIR state space model Metadata
CovidMetrics-epiBATS University of Cologne Covid Metrics Forecasts are based on TBATS - models (DeLivera, Hyndman and Snyder (2011)) and are updated daily for each German state. Metadata
DSMPG-bayes Priesemann Group, MPI-DS Bayesian inference of SIR-dynamics Metadata
ECDC-hosp_model ECDC Modelling Team mechanistic estimation of hospitalisations using age disaggregated data of weekly cases, vaccination, and case hospitalisation rates Metadata
epiforecasts-arimareg epiforecasts A regression model forecasting admissions from 1-week-lagged cases, with ARIMA errors. Fit to weekly data. Metadata
epiforecasts-caseconv epiforecasts A convolution of cases and a delay distribution fit to weekly data. Metadata
epiforecasts-EpiExpert_direct Epiforecasts / London School of Hygiene and Tropical Medicine Mean ensemble of human predictions Metadata
epiforecasts-EpiExpert_Rt Epiforecasts / London School of Hygiene and Tropical Medicine Mean ensemble of human predictions of Rt which get mapped to cases and deaths using a renewal equation Metadata
epiforecasts-EpiExpert Epiforecasts / London School of Hygiene and Tropical Medicine Mean ensemble of human predictions Metadata
epiforecasts-EpiNow2 Epiforecasts / London School of Hygiene and Tropical Medicine Semi-mechanistic estimation of the time-varying reproduction number for latent infections mapped to reported cases/deaths. Metadata
epiforecasts-tsensemble epiforecasts A mean ensemble of three autoregressive time series models (ARIMA, ETS and “naive” - future admissions are equal to the last observed week, with expanding uncertainty). Metadata
epiMOX-SUIHTER epiMOX Compartmental model SUIHTER Metadata
EuroCOVIDhub-baseline European COVID-19 Forecast Hub An baseline model against which other models can be evaluated Metadata
EuroCOVIDhub-ensemble European COVID-19 Forecast Hub An ensemble, or model average, of submitted forecasts to the European COVID-19 Forecast Hub. Metadata
FIAS_FZJ-Epi1Ger Frankfurt Institute for Advanced Studies & Forschungszentrum Jülich An extended SEIR model with additional compartments for undetected cases Metadata
HZI-AgeExtendedSEIR Helmholtz Zentrum fuer Infektionsforschung Deterministic SEIR type model Metadata
ICM-agentModel ICM / University of Warsaw Agent-based model Metadata
IEM_Health-CovidProject IEM Health SEIR model projections for daily incident confirmed COVID cases and deaths by using AI to fit actual cases observed. Metadata
ILM-EKF ILM Extended Kalman filter based on reproduction equation Metadata
Imperial-DeCa Imperial College London Uses both cases and deaths to estimate an observed CFR. Projections are based on the estimated CFR. Metadata
Imperial-RtI0 Imperial College London Jointly estimates initial incidence and reproduction number Metadata
Imperial-sbkp Imperial College London Optimises the window over which reproduction number is assumed to be constant. Metadata
itwm-dSEIR Fraunhofer Institute for Industrial Mathematics ITWM cohort based, integral equation Metadata
ITWW-county_repro ITWW Forecasts of county level incidence based on regional reproduction numbers. Metadata
Karlen-pypm Karlen Working Group Discrete-time difference equations with long periods of constant transmission rate Metadata
KITmetricslab-bivar_branching KITmetricslab Delta-variant and other cases are modelled as independent branching processes, with weekly growth  rates following random walks. Forecasts for 3 and 4 wk are likely unreliable. Metadata
LANL-GrowthRate Los Alamos National Labs This model makes predictions about the future, unconditional on particular intervention strategies. Statistical dynamical growth model accounting for population susceptibility. Metadata
LeipzigIMISE-SECIR Universitaet Leipzig IMISE/GenStat SECIR type model Metadata
MIMUW-StochSEIR Faculty of Mathematics, Informatics, and Mechanics, University of Warsaw Extended SEIR model Metadata
MIT_CovidAnalytics-DELPHI CovidAnalytics at MIT This model makes predictions for future cases based on a heavily modified SEIR model taking into account underdetection and government intervention. Current interventions are assumed to continue. Metadata
MOCOS-agent1 MOCOS group Agent-based microsimulation model Metadata
MUNI_DMS-SEIAR Department of Mathematics and Statistics Masaryk University Team SEIAR model with A compartment of absent unobserved infected estimated from hospital data with incorporated mobility data dependence; optimized to the compartment of all exposed (unobserved included) Metadata
MUNI-ARIMA Masaryk University Seasonal ARIMA model with outlier detection fitted to transformed daily series. Weekly forecasts are obtained by aggregating bootstrap daily forecast paths. Metadata
PL_GRedlarski-DistrictsSum Grzegorz Redlarski Modified SIR method, applied to all districts. Forecasts for districts are summed up. Metadata
RobertWalraven-ESG Robert Walraven Multiple skewed gaussian distribution peaks fit to raw data Metadata
SDSC_ISG-TrendModel Swiss Data Science Center / University of Geneva The Trend Model predicts daily cases and deaths using linear extrapolation on the linear or log scale of the underlying trend estimated by a robust LOESS seasonal-trend decomposition model. Metadata
Statgroup19-richards Statgroup19 Richards’ curve based generalized growth model Metadata
Statgroup19-spatialrichards Statgroup19 Richards’ curve based generalized growth model taking into account spatial dependence Metadata
UB-BSLCoV UB Bayesian synthetic likelihood estimation for underreported non-stationary time series Metadata
UMass-MechBayes UMass-Amherst Bayesian compartmental model with observations on cumulative case counts and cumulative deaths. Model is fit independently to each state. Model includes observation noise and a case detection rate. Metadata
UMass-SemiMech UMass-Amherst Bayesian semi-compartmental model with observations on incident case counts and incident deaths. Model is fit independently to each state. Model includes observation noise and a case detection rate. Metadata
UNED-PreCoV2 UNED Bayesian time series models with ARIMA noise and fixed transfer functions for each input. Metadata
UNIPV-BayesINGARCHX UNIPV Periscope Working Group Bayesian estimation of time-dependent models with time-varying coefficients to predict COVID-19 positive counts. Metadata
UpgUmibUsi-MultiBayes UNIPG_UNIMIB_USI_UNINSUBRIA Bayesian Dirichlet-Multinomial models for counts of patients in mutually exclusive and exhaustive categories such as hospitalized in regular wards and in intensive care units, deceased and recovered Metadata
USC-SIkJalpha University of Southern California A heterogeneous infection rate model with human mobility for epidemic modeling. Our model adapts to changing trends and provide predictions of confirmed cases and deaths. Metadata
USyd-OneModelMan University of Sydney Forecast Lab A single autoregressive model fit jointly to all European time series, adding time series from the top regions across the world. A high-dimensional manifold embedding is used capture the process. Metadata
UVA-Ensemble University of Virginia, Biocomplexity COVID-19 Response Team An ensemble of multiple methods such as auto-regressive (AR)models with exogenous variables, Long short-term memory (lSTM) models,Kalman filter and PatchSim (an SEIR model). Metadata

Presentations

The ECDC hosts weekly calls which any forecasting team is welcome to join. Each week a different team is invited to present and discuss forecasting methods. Slides and extra content provided by the teams can be accessed below:

06/10/2021 UpgUmibUsi MultiBayes

22/09/2021 epiforecasts EpiNow2

07/09/2021 Hub forecast review

06/07/2021 Karlen pypm

22/06/2021 FIAS_FZJ Epi1Ger

08/06/2021 epiforecasts EpiExpert

25/05/2021 SEIAR MUNI

18/05/2021 Imperial

11/05/2021 ICM agentmodel

20/04/2021 MOCOS agent1

13/04/2021 UNED PreCoV2

30/03/2021 DSMPG bayes

23/03/2021 UNIPV BayesINGARCH

09/03/2021 Evaluation of interval forecasts

02/03/2021 The European Covid19 Forecast Hub