sjSDM: Scalable Joint Species Distribution Modeling

A scalable method to estimate joint Species Distribution Models (jSDMs) for big community datasets based on a Monte Carlo approximation of the joint likelihood. The numerical approximation is based on 'PyTorch' and 'reticulate', and can be run on CPUs and GPUs alike. The method is described in Pichler & Hartig (2021) <doi:10.1111/2041-210X.13687>. The package contains various extensions, including support for different response families, ability to account for spatial autocorrelation, and deep neural networks instead of the linear predictor in jSDMs.

Version: 1.0.5
Depends: R (≥ 3.0)
Imports: reticulate, stats, mvtnorm, utils, rstudioapi, abind, graphics, grDevices, Metrics, parallel, mgcv, cli, crayon, ggplot2, checkmate, mathjaxr, ggtern
Suggests: testthat, knitr, rmarkdown
Published: 2023-06-17
DOI: 10.32614/CRAN.package.sjSDM
Author: Maximilian Pichler ORCID iD [aut, cre], Florian Hartig ORCID iD [aut], Wang Cai [ctb]
Maintainer: Maximilian Pichler <maximilian.pichler at>
License: GPL-3
NeedsCompilation: no
Citation: sjSDM citation info
Materials: README NEWS
In views: Environmetrics
CRAN checks: sjSDM results


Reference manual: sjSDM.pdf
Vignettes: sjSDM: Help with the installation of dependencies
Getting started with sjSDM: a scalable joint Species Distribution Model


Package source: sjSDM_1.0.5.tar.gz
Windows binaries: r-devel:, r-release:, r-oldrel:
macOS binaries: r-release (arm64): sjSDM_1.0.5.tgz, r-oldrel (arm64): sjSDM_1.0.5.tgz, r-release (x86_64): sjSDM_1.0.5.tgz, r-oldrel (x86_64): sjSDM_1.0.5.tgz
Old sources: sjSDM archive


Please use the canonical form to link to this page.