Predictions
ID
Lang
Model name
Repository
Description
LSTM model for Infodengue Sprint
Predictions for 2024 in DF using the att_3 architecture
Model 1 - Weekly and yearly (iid) components
The model is founded on a structural decomposition designed for modeling counting series, employing a Poisson distribution. The log intensity is defined by the sum of weekly and yearly components, where the first one is defined as a AR(1) process and the last one is assumed to be iid.
Model 1 - Weekly and yearly (iid) components
The model is founded on a structural decomposition designed for modeling counting series, employing a Poisson distribution. The log intensity is defined by the sum of weekly and yearly components, where the first one is defined as a AR(1) process and the last one is assumed to be iid.
Temp-SPI Interaction Model
Validation test 1 for three-way interaction model (RO)
Model 2 - Weekly and yearly (rw1) components
The model is founded on a structural decomposition designed for modeling counting series, employing a Poisson distribution. The log intensity is defined by the sum of weekly and yearly components, where the first one is defined as a AR(1) process and the last one is assumed to be iid.
Model 1 - Weekly and yearly (iid) components
The model is founded on a structural decomposition designed for modeling counting series, employing a Poisson distribution. The log intensity is defined by the sum of weekly and yearly components, where the first one is defined as a AR(1) process and the last one is assumed to be iid.
Model 2 - Weekly and yearly (rw1) components
The model is founded on a structural decomposition designed for modeling counting series, employing a Poisson distribution. The log intensity is defined by the sum of weekly and yearly components, where the first one is defined as a AR(1) process and the last one follows a RW(1) process.
LNCC-CLiDENGO-2025-1
Validation test 3 for UF=RN (LNCC-CLiDENGO model)
Temp-SPI Interaction Model
Validation test 1 for three-way interaction model (AC)
LaCiD/UFRN
Dengue predictions for RS using Validation Test 2
Random Forest model with uncertainty computed with conformal prediction
Forecast de novos casos para o geocode 2704302 entre 2022-01-01 e 2023-01-01 usando apenas os dados de todos as cidades clusterizadas com 2704302 como input
LSTM model for Infodengue Sprint
Predictions for 2023 in MA using the baseline architecture
Deep learning model using BI-LSTM Layers
Forecast de novos casos para o geocode 2111300 entre 2022-01-01 e 2023-01-01 usando apenas os dados do geocode 2111300
Random Forest model with uncertainty computed with conformal prediction
Forecast de novos casos para o geocode 2211001 entre 2022-01-01 e 2023-01-01 usando apenas os dados de todos as cidades clusterizadas com 2211001 como input
Model 1 - Weekly and yearly (iid) components
The model is founded on a structural decomposition designed for modeling counting series, employing a Poisson distribution. The log intensity is defined by the sum of weekly and yearly components, where the first one is defined as a AR(1) process and the last one is assumed to be iid.
LSTM model for Infodengue Sprint
Predictions for 2024 in RO using the comb_att_n architecture
Model 1 - Weekly and yearly (iid) components
The model is founded on a structural decomposition designed for modeling counting series, employing a Poisson distribution. The log intensity is defined by the sum of weekly and yearly components, where the first one is defined as a AR(1) process and the last one is assumed to be iid.
Model 1 - Weekly and yearly (iid) components
The model is founded on a structural decomposition designed for modeling counting series, employing a Poisson distribution. The log intensity is defined by the sum of weekly and yearly components, where the first one is defined as a AR(1) process and the last one is assumed to be iid.
LSTM model for Infodengue Sprint
Predictions for 2024 in RS using the baseline architecture
Model 1 - Weekly and yearly (iid) components
The model is founded on a structural decomposition designed for modeling counting series, employing a Poisson distribution. The log intensity is defined by the sum of weekly and yearly components, where the first one is defined as a AR(1) process and the last one is assumed to be iid.
Model 2 - Weekly and yearly (rw1) components
The model is founded on a structural decomposition designed for modeling counting series, employing a Poisson distribution. The log intensity is defined by the sum of weekly and yearly components, where the first one is defined as a AR(1) process and the last one follows a RW(1) process.
Temp-SPI Interaction Model
Validation test 1 for three-way interaction model (DF)
Random Forest model with uncertainty computed with conformal prediction
Forecast de novos casos para o geocode 2304400 entre 2022-01-01 e 2023-01-01 usando apenas os dados de todos as cidades clusterizadas com 2304400 como input
Model 1 - Weekly and yearly (iid) components
The model is founded on a structural decomposition designed for modeling counting series, employing a Poisson distribution. The log intensity is defined by the sum of weekly and yearly components, where the first one is defined as a AR(1) process and the last one is assumed to be iid.
Temp-SPI Interaction Model
Validation test 1 for three-way interaction model (PB)
UERJ-SARIMAX-2025-2
Validation test 1 for UF=AP (UERJ-SARIMAX-2025-2)
LaCiD/UFRN
Dengue predictions for RR using Validation Test 2
Deep learning model using BI-LSTM Layers
Forecast de novos casos para o geocode 2408102 entre 2022-01-01 e 2023-01-01 usando apenas os dados do geocode e das cidades clusterizadas com ele
LSTM-RF model
LSTM-RF predictions for Mosqlimate Sprint 2025
2595 predictions
https://api.mosqlimate.org/api/registry/predictions/?page=59&per_page=30&
Page 59 of 87
