Models
ID
Lang
Name
Uploaded at
Description
infodengue_sprint_24_25_hybrid_CNN_LSTM_ensemble_model
2024-09-09
2024_info_dengue_model_hybrid_CNN_LSTM_ensemble_RMSE_Penalties_final_ex_state_CE.ipynb
Model 2 - Weekly and yearly (rw1) components
2024-08-15
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.
Model 1 - Weekly and yearly (iid) components
2024-08-15
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.
BB-M
2024-08-19
Bayesian baseline random effects model
Temp-SPI Interaction Model
2024-08-14
Hierarchical Bayesian mixed model with three-way interaction between temperature, long-lag SPI and short-lag SPI
LSTM model with PCA and vaiance threshold
2024-08-15
using LSTM combined with PCA and vaiance threshold
Prophet model with PCA and vaiance threshold
2024-08-15
using Prophet model combined with PCA and vaiance threshold
LSTM model for Infodengue Sprint
2024-08-08
The models used to forecast the dengue cases in the 2024/2025. It's considered different architectures and set of predictors to predict the 52 weeks in different states
Univariate neural prophet model
2023-12-04
In this repo, it's implemented a neural prophet model that based only on the times series of cases compute the cases in the next four weeks.
Example of Univariate neural prophet model
2023-12-06
In this repo, it's implemented a neural prophet model that based only on the times series of cases compute the cases in the next four weeks.
Deep learning model using BI-LSTM Layers
2023-11-27
In this repo, in the path /models/neuralnetworks it's implemented a deep learning model with three lstm layers (the first one is bidirectional) interspersed with dropout layers and a dense layer in the output. This model computes the number of new cases in the next four weeks based on the last four weeks of data (cases and climate variables). The confidence interval of the predictions is computed using dropout and making multiple predictions to compute the ci of them.
Random Forest model with uncertainty computed with conformal prediction
2023-11-27
In this repo, in the path /models/gbt it's implemented a random forest regressor model that based on the last four weeks of data (cases and climate variables), compute the cases in the fourth week ahead. The predictions for multiple times are obtained in a rolling window fashion, i.e., the historical data window is moved forward one week at a time, predicting the next fourth week at each step. The confidence interval of the predictions are computed using the conformal prediction.
Baseline weekly model
2024-07-08
Model that train a lstm model that predict the cases in a week based in the epiweek value and the cases in the same week in the last two years
test model
2024-05-28
This example model is based on the X methodoly, uses as input the Y variables to predict Z.
LSTM model
2024-05-10
In this repo, it's implemented a LSTM model that forecast the cases in the next four weeks and it used to gen probabilist forecasts according to a MEM baseline.
18 models
https://api.mosqlimate.org/api/registry/models/?page=1&per_page=50&
Page 1 of 1