IDExtremes - R package

BSC Group: Earth Sciences Software
IDExtremes is an R package designed to predict the probability of outbreaks using observed and forecast hydrometeorological indicators. Its flexible design allows users to input both observed (long-lag) and forecast (short-lag) hydrometeorological indicators, such as drought and flood indicators, and output the probability of an outbreak of a given climate-sensitive disease (e.g., dengue, malaria, or leptospirosis) several months in advance.
Software Author: 

Giovenale Moirano, Chloe Fletcher, Martin Lotto, Daniela Lührsen, Raúl Capellán, Rachel Lowe

License: 

GPL License (Version 2.0)

Primary tabs

The tool is based on a Bayesian statistical modeling framework and provides functionalities for performing exploratory analysis, fitting spatiotemporal models, testing and validating the predictive ability of the models, and forecasting the probability of a disease outbreak. Additionally, the tool includes functions to visuaise outputs for all modeling steps and final predictions.
 
Dependencies
The package is written in R (R version ≥ 4.2.0) and uses the following R packages: INLA, dplyr, ggplot2, grDevices, rlang, tidyr.
 
Functioning
The package can be used in any R environment and other programming languages if R is supported. All the functions will comprise a workflow of data processing, with parallelization and multi-core operation options. The jobs can be submitted to HPCs to be processed in parallel. The package also provides several model post-processing functions to validate model forecasts and select the models with the best predictive performance.
 
Development
The technology is being developed as part of the IDExtremes project (June 2023 - May 2027). The first two years are dedicated to developing a suite of functions and the R package with all associated documentation. The last two years will be used to test and validate the R package within several relevant environments of our partner agencies. Future users from our partner organisations will participate in the beta testing phase. At the end of the project, the sustainability of the operational R package will be evaluated using the CHAOSS framework.