Previsões
ID
Idioma
Nome do modelo
Repositório
Descrição
LSTM model for Infodengue Sprint
Predictions for 2025 in AM using the comb_att_n architecture
Model 1 - Weekly and yearly (iid) components
This upload represents the epidemic prediction for unseen data from the period of 2024-06-16 to 2025-10-05 in the state CE. 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
2024/25 forecast for three-way interaction model (CE)
Model 1 - Weekly and yearly (iid) components
This upload represents the epidemic prediction for unseen data from the period of 2024-06-16 to 2025-10-05 in the state RR.
Model 1 - Weekly and yearly (iid) components
This upload represents the epidemic prediction for unseen data from the period of 2024-06-16 to 2025-10-05 in the state AM.
Model 2 - Weekly and yearly (rw1) components
This upload represents the epidemic prediction for unseen data from the period of 2024-06-16 to 2025-10-05 in the state MG.
Model 1 - Weekly and yearly (iid) components
This upload represents the epidemic prediction for unseen data from the period of 2024-06-16 to 2025-10-05 in the state GO. 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 2025 in RN using the baseline architecture
LSTM model for Infodengue Sprint
Predictions for 2025 in PE using the baseline architecture
Model 1 - Weekly and yearly (iid) components
This upload represents the epidemic prediction for unseen data from the period of 2024-06-16 to 2025-10-05 in the state AM. 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 2025 in PA using the comb_att_n architecture
LSTM model for Infodengue Sprint
Predictions for 2025 in AL using the baseline architecture
Temp-SPI Interaction Model
2024/25 forecast for three-way interaction model (AC)
Prophet model with PCA and vaiance threshold
predict for 2025 of the Prophet model in GO
LSTM model for Infodengue Sprint
Predictions for 2025 in PI using the baseline architecture
LSTM model for Infodengue Sprint
Predictions for 2024 in RJ using the baseline architecture
Model 1 - Weekly and yearly (iid) components
This upload represents the epidemic prediction for validation test 2 in the state RJ.
infodengue_sprint_24_25_hybrid_CNN_LSTM_ensemble_model
infodengue_sprint_24_25_hybrid_CNN_LSTM_ensemble_model Prediction on RJ_info_dengue_test_2
LSTM model for Infodengue Sprint
Predictions for 2024 in RJ using the baseline architecture
Model 2 - Weekly and yearly (rw1) components
This upload represents the epidemic prediction for validation test 2 in the state RJ.
Model 1 - Weekly and yearly (iid) components
This upload represents the epidemic prediction for validation test 2 in the state AL.
LSTM model for Infodengue Sprint
Predictions for 2024 in AL using the baseline architecture
infodengue_sprint_24_25_hybrid_CNN_LSTM_ensemble_model
infodengue_sprint_24_25_hybrid_CNN_LSTM_ensemble_model Prediction on AL_info_dengue_test_2
Model 2 - Weekly and yearly (rw1) components
This upload represents the epidemic prediction for validation test 2 in the state AL.
LSTM model for Infodengue Sprint
Predictions for 2024 in MT using the att architecture
LSTM model for Infodengue Sprint
Predictions for 2024 in PA using the baseline architecture
700 previsões
https://api.mosqlimate.org/api/registry/predictions/?page=8&per_page=30&
Página 8 de 24