Multivariate Space-Time Weather Generator • MSTWeatherGen

Overview

{MSTWeatherGen} Multivariate and Space-Time stochastic Weather Generator R package is designed for the simulation of multivariate spatio-temporal meteorological variables. It provides tools for estimating the model parameters and generating synthetic weather data that can be used for a variety of applications, including climate research, agricultural or hydrological modeling.

For more details on the methodology, see the publication:

Obakrim, S. et al. “A multivariate and space-time stochastic weather generator using a latent Gaussian framework,” Stochastic Environmental Research and Risk Assessment, 2025. doi:10.1007/s00477-024-02897-8

Installation

You can install MSTWeatherGen from GitHub as follows:

# install.packages("remotes")
remotes::install_github("Chair-Geolearning/MSTWeatherGen")

The main branch (default branch) is stable.

Download a special release :

Development

Active all unit tests set “R_TEST_ALL” global variable to TRUE.

Disable vignette building (that can take to much time) use : --no-build-vignettes at build and --ignore-vignettes at check.

Getting Started

To learn how to use the MSTWeatherGen package, please refer to the detailed vignette available here.

Funding

This work was made possible thanks to the Geolearning Chair funded by Andra, BNP-Paribas, CCR and the SCOR Foundation for Science. A preliminary version was supported by funding from the French National Research Agency (ANR) as part of the BEYOND project (Contract No. 20-PCPA-0002).

Chair Geolearning