We are grateful to all contributing teams for their work and encourage new teams to submit forecasts once a week for one or more EU/EEA countries. Modelling results are directly used by ECDC and brought to public health professionals to support situational awareness and planning. We also invite contributing teams to take part in planned research papers. Check the “Join in” section to learn how to submit your models.
Dutch Natl Inst Publ Hlth Envir (RIVM)
RIVM
Syndromic indicators Models
Kalman Filter dlm
A dynamic linear model with the local trend and the first and second derivative terms, using a Kalman filter implemented in R-package dlm with log(x+1) transformation of the time series.
European Centre for Disease Prevention and Control
ECDC
COVID-19 Models
ARIMA model with seasonality
Compartmental model (H)
Compartmental model (HC)
Using historical data patterns with highest similarity to current data to foreast the future values
Contributors
Detailed description
Model consists of 1) taking 'm' latest data points, 2) find 'n' closest neighbours from all historical data using L2-norm, 3) use the next data time point from each historical data points, 4) use data from point 3 to fit a log-normal distribution , 5) use the log-normal distirbution to estimate the quantiles/distribution, 6) return to step 3 but use two data points ahead for estimations of horizon 2, etc for horizon 3 and 4, 7) find optimal values of 'n' and 'm for a given country, using past 4 weeks of forecasts.Data inputs
ECDC ERVISS Syndromic indicators Models
ARIMA model with seasonality
Historical simplex pattern
Using historical data patterns with highest similarity to current data to foreast the future values
Contributors
Detailed description
Model consists of 1) taking 'm' latest data points, 2) find 'n' closest neighbours from all historical data using L2-norm, 3) use the next data time point from each historical data points, 4) use data from point 3 to fit a log-normal distribution , 5) use the log-normal distirbution to estimate the quantiles/distribution, 6) return to step 3 but use two data points ahead for estimations of horizon 2, etc for horizon 3 and 4, 7) find optimal values of 'n' and 'm for a given country, using past 4 weeks of forecasts.Data inputs
Historical ILIARIRates data as provided by RespiCast and ECDCFjordhest
fjordhest
Syndromic indicators Models
fjordhest-ensemble
An inverse-WIS weighted ensemble of 3 component models - an exponential trend smoothing (ETS) model, a quantile AR model, and a baseline model of random walk with drift.
Contributors
Detailed description
Quantile autoregression model uses quantgen R package, and is similar to CMU-Timeseries model from 2022/23 FluSight season. Random walk and ETS models use fable R package. To build an ensemble, the quantile distributions of the component models are weighted (location- and target-specific) by the mean of inverse-WIS scores over the last 3 weeks that could be evaluated. The estimates are solely the responsibility of the contributors and do not represent, nor are endorsed by, the Norwegian Institute of Public Health.Citation/s
Tibshirani R, Brooks L (2020). quantgen: Tools for generalized quantile modeling; https://github.com/cmu-delphi/flu-hosp-forecast/; O'Hara-Wild M, Hyndman R, Wang E (2022). fable: Forecasting Models for Tidy Time Series. R package version 0.3.2.Data inputs
ECDC ERVISSLicense
CC-BY_SA-4.0ISI Foundation
ISI
COVID-19 Models
CovBcast
A stochastic, age-structured compartmental model that explicitly integrates behavioral changes through a new compartment of susceptible individuals who are risk averse.
CovidABCaster
LSTFlu
RespiCompass Adaptive Ensemble2
SEIR_BRW
Syndromic indicators Models
FluABCaster
FluBcast
A stochastic, age-structured compartmental model that explicitly integrates behavioral changes through a new compartment of susceptible individuals who are risk averse.
GLEAM
LSTFlu
RespiCompass Adaptive Ensemble2
ItaLuxColab
ItaLuxColab
COVID-19 Models
Epidemic projections by SIRS+EKF
Region-wise stochastic SIRS model with automatic data integration by the extended Kalman filter (EKF) and adaptive hyperparameter estimation (gitlab.com/uniluxembourg/lcsb/systems-control/epinetekf)
Syndromic indicators Models
Epidemic projections by SIRS+EKF
Region-wise stochastic SIRS model with automatic data integration by the extended Kalman filter (EKF) and adaptive hyperparameter estimation (gitlab.com/uniluxembourg/lcsb/systems-control/epinetekf)
Epidemic projections by networked SIRS+EKF
Stochastic networked SIRS model with automatic data integration by the extended Kalman filter (EKF) and adaptive hyperparameter estimation (gitlab.com/uniluxembourg/lcsb/systems-control/epinetekf)
MRC Centre for Global Imfectious Disease Analysis
MRC_GIDA
Syndromic indicators Models
CATBoost
NBEATS
NHiTS
Notre Dame Perkins Lab
NotreDame
Syndromic indicators Models
Rt co-circulation
Smoothed ILI historic data used to estimate the Rt using the EpiEstim package in R. Rt then predicted into the future by a GAM model with smoothed COVID and Influenza data as predictors
Queen Mary University of London
QMUL
Syndromic indicators Models
ARIMA Model
SEIR Agumented Model
RespiCast
respicast
COVID-19 Models
Hub Ensemble
Quantile Baseline
A simple baseline model that samples future target changes from historical increments.
Contributors
Detailed description
The baseline model consistently predicts as median value the last data point within the calibration period, while its confidence intervals are estimated on past data increments. Similar baseline models have become a standard neutral benchmark providing a simple reference for all models in the context of collaborative forecasting hubs, see Cramer et al. "Evaluation of individual and ensemble probabilistic forecasts of COVID-19 mortality in the United States", 2022 and Sherratt et al. "Predictive performance of multi-model ensemble forecasts of COVID-19 across European nations", 2023.License
CC-BY-4.0 Syndromic indicators Models
Hub Ensemble
Quantile Baseline
The baseline model consistently predicts as median value the last data point within the calibration period, while its confidence intervals are estimated on past data increments. Similar baseline models have become a standard neutral benchmark providing a simple reference for all models in the context of collaborative forecasting hubs.
Contributors
Detailed description
The baseline model consistently predicts as median value the last data point within the calibration period, while its confidence intervals are estimated on past data increments. Similar baseline models have become a standard neutral benchmark providing a simple reference for all models in the context of collaborative forecasting hubs, see Cramer et al. "Evaluation of individual and ensemble probabilistic forecasts of COVID-19 mortality in the United States", 2022 and Sherratt et al. "Predictive performance of multi-model ensemble forecasts of COVID-19 across European nations", 2023.License
CC-BY-4.0Safinea
safinea
COVID-19 Models
CovidCast
Syndromic indicators Models