Community

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.
Contributors
Fuminari Miura
Don Klinkenberg
Jantien Backer
Jan van de Kassteele
Jacco Wallinga

Data inputs
Surveillance data from the RespiCast platform.

European Centre for Disease Prevention and Control
ECDC
COVID-19 Models
ARIMA model with seasonality
A simple ARIMA model with seasonality
Contributors
ECDC Mathematical Modelling Team

Data inputs
ECDC ERVISS

Compartmental model (H)
An SIRS-type model with seasonality fitted to hospitalisations
Contributors
ECDC Mathematical Modelling Team

Data inputs
ECDC ERVISS

Compartmental model (HC)
An SIRS-type model with seasonality fitted to hospitalisations and cases
Contributors
ECDC Mathematical Modelling Team

Data inputs
ECDC ERVISS

Historical simplex pattern
Using historical data patterns with highest similarity to current data to foreast the future values
Contributors
ECDC Mathematical Modelling Team

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
A simple ARIMA model with seasonality
Contributors
ECDC Mathematical Modelling Team

Data inputs
ECDC ERVISS

Historical simplex pattern
Using historical data patterns with highest similarity to current data to foreast the future values
Contributors
ECDC Mathematical Modelling team

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 ECDC

Fjordhest
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
Sasi Kandula
Birgitte De Blasio

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 ERVISS

License
CC-BY_SA-4.0

ISI 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.
Contributors
Stefania Fiandrino

Data inputs
ECDC ERVISS, FluID WHO, UN World Population, contact matrices from Mistry et al. (2021), Prem et al (2017)

License
CC-BY-4.0

CovidABCaster
A stochastic, age structured compartmental model calibrated via Approximate Bayesian Computation techniques.
Contributors
Nicolo Gozzi

Data inputs
ECDC ERVISS, FluID WHO, UN World Population Prospects, contact matrices from Mistry et al. (2021), Prem et al (2017)

License
CC-BY-4.0

LSTFlu
Bidirectional Long Short Term Memory model trained over 10 years of ILI surveillance data from Italy.
Contributors
Mattia Mazzoli

Data inputs
ECDC ERVISS.

License
CC-BY-4.0

RespiCompass Adaptive Ensemble2
An adaptive ensemble of multiple models contributing to RespiCompass scenario projections for COVID-19.
Contributors
Stefania Fiandrino
Nicolo Gozzi

Data inputs
ECDC ERVISS and RespiCompass projections for COVID-19

License
CC-BY-4.0

SEIR_BRW
SEIR Beta Random Walks is a stochastic compartmental model with random variations in the transmission rate, that provides short-term incidence forecasts.
Contributors
Valeria Marras

Data inputs
ECDC ERVISS

License
CC-BY-4.0

Syndromic indicators Models
FluABCaster
A stochastic, age structured compartmental model calibrated via Approximate Bayesian Computation techniques.
Contributors
Nicolò Gozzi

Data inputs
ECDC ERVISS, FluID WHO, UN World Population Prospects, contact matrices from Mistry et al. (2021), Prem et al (2017)

License
CC-BY-4.0

FluBcast
A stochastic, age-structured compartmental model that explicitly integrates behavioral changes through a new compartment of susceptible individuals who are risk averse.
Contributors
Stefania Fiandrino

Data inputs
ECDC ERVISS, FluID WHO, UN World Population, contact matrices from Mistry et al. (2021), Prem et al (2017)

License
CC-BY-4.0

GLEAM
A stochastic, age-structured compartmental model based on a metapopulation approach that uses real-world data on populations and human mobility to simulate epidemic spreading on a global scale.
Contributors
Luca Rossi

Data inputs
ECDC ERVISS, FluID WHO

License
CC-BY-4.0

LSTFlu
Bidirectional Long Short Term Memory model trained over 10 years of ILI surveillance data from Italy.
Contributors
Mattia Mazzoli

Data inputs
ECDC ERVISS.

License
CC-BY-4.0

RespiCompass Adaptive Ensemble2
An adaptive ensemble of multiple models contributing to RespiCompass scenario projections for ILI.
Contributors
Stefania Fiandrino
Nicolò Gozzi

Data inputs
ECDC ERVISS and RespiCompass projections for ILI

License
CC-BY-4.0

SEIR_BRW
SEIR Beta Random Walks is a stochastic compartmental model with random variations in the transmission rate, that provides short-term incidence forecasts.
Contributors
Valeria Marras

Data inputs
ECDC ERVISS

License
CC-BY-4.0

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)
Contributors
Atte Aalto
Daniele Proverbio
Giulia Giordano
Jorge Goncalves

Data inputs
ECDC ERVISS

License
CC-BY-4.0

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)
Contributors
Atte Aalto
Daniele Proverbio
Giulia Giordano
Jorge Goncalves

Data inputs
ECDC ERVISS and FluID (as provided in flu-forecast-hub)

License
CC-BY-4.0

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)
Contributors
Atte Aalto
Daniele Proverbio
Giulia Giordano
Jorge Goncalves

Data inputs
ECDC ERVISS and FluID (as provided in flu-forecast-hub)

License
CC-BY-4.0

MRC Centre for Global Imfectious Disease Analysis
MRC_GIDA
Syndromic indicators Models
CATBoost
Categorical Boosting model
Contributors
Rhys Earl
Marc Baguelin
Edwin Van Leeuwen
Jamie Lopez-Bernal
Neil Ferguson

Data inputs
ECDC ERVISS

NBEATS
Neural Basis Expansion Analysis for Time Series
Contributors
Rhys Earl
Marc Baguelin
Edwin Van Leeuwen
Jamie Lopez-Bernal
Neil Ferguson

Data inputs
ECDC ERVISS

NHiTS
Neural Hierarchical Interpolation for Time Series
Contributors
Rhys Earl
Marc Baguelin
Edwin Van Leeuwen
Jamie Lopez-Bernal
Neil Ferguson

Data inputs
ECDC ERVISS

Prophet
Facebook Prophet forecasting model
Contributors
Rhys Earl
Marc Baguelin
Edwin Van Leeuwen
Jamie Lopez-Bernal
Neil Ferguson

Data inputs
ECDC ERVISS

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
Contributors
Alex Perkins
Kelsey Shaw

Data inputs
Syndromic data from Respicast Github and COVID and Influenza non-sentinel detection data from ERVISS

Queen Mary University of London
QMUL
Syndromic indicators Models
ARIMA Model
AutoRegressive Integrated Moving Average (ARIMA) model for analyzing time series
Contributors
Nicola Perra
Yuhan Li

Data inputs
ECDC ERVISS

License
CC-BY-4.0

SEIR Agumented Model
An SEIR compartmental model augmented by incorporating ARIMA model predictions for improved forecast selection
Contributors
Nicola Perra
Yuhan Li

Data inputs
ECDC ERVISS

License
CC-BY-4.0

SEIR Model
An SEIR compartmental model using biased wampe for selecting predictions
Contributors
Nicola Perra
Yuhan Li

Data inputs
ECDC ERVISS

License
CC-BY-4.0

RespiCast
respicast
COVID-19 Models
Hub Ensemble
An Ensemble model that computes the median across different models' quantiles.
Contributors
RespiCast Team

License
CC-BY-4.0

Quantile Baseline
A simple baseline model that samples future target changes from historical increments.
Contributors
RespiCast Team

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
An Ensemble model that computes the median across different models' quantiles.
Contributors
RespiCast Team

License
CC-BY-4.0

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
RespiCast Team

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

Safinea
safinea
COVID-19 Models
CovidCast
An SIRS-type model, with seasonality, fitted to hospital admissions
Contributors
Helen Johnson

Data inputs
ECDC ERVISS

License
CC-BY-4.0

Syndromic indicators Models
SS_KF_syndromic
A state-space model with respiratory disease as a hidden states and separate observation processes for ILI and ARI reporting. Smoothed with unscented Kalman Filter, poisson process
Contributors
Helen Johnson

Data inputs
ECDC ERVISS

License
CC-BY-4.0