Package: sjSDM
Type: Package
Title: Scalable Joint Species Distribution Modeling
Version: 1.1.0
Authors@R: 
    c(person(given = "Maximilian",
             family = "Pichler",
             role = c("aut", "cre"),
             email = "maximilian.pichler@biologie.uni-regensburg.de",
             comment = c(ORCID = "0000-0003-2252-8327")),
      person(given = "Florian",
             family = "Hartig",
             role = "aut",
             email = "florian.hartig@biologie.uni-regensburg.de",
             comment = c(ORCID = "0000-0002-6255-9059")),
      person(given = "Wang",
             family = "Cai",
             role = "ctb",
             email = "caiwang0503@163.com"))
Description: A scalable and fast method for estimating joint Species
        Distribution Models (jSDMs) for big community data, including
        eDNA data. The package estimates a full (i.e. non-latent) jSDM
        with different response distributions (including the
        traditional multivariate probit model). The package allows to
        perform variation partitioning (VP) / ANOVA on the fitted
        models to separate the contribution of environmental, spatial,
        and biotic associations. In addition, the total R-squared can
        be further partitioned per species and site to reveal the
        internal metacommunity structure, see Leibold et al.,
        <doi:10.1111/oik.08618>. The internal structure can then be
        regressed against environmental and spatial distinctiveness,
        richness, and traits to analyze metacommunity assembly
        processes.  The package includes support for accounting for
        spatial autocorrelation, for grouping-factor random effects in
        the environmental formula, and for deep neural networks, which
        can replace the linear predictor or sit beside it as one block
        of a formula that also holds interpretable linear terms. As
        described in Pichler & Hartig (2021)
        <doi:10.1111/2041-210X.13687>, scalability is achieved by using
        a Monte Carlo approximation of the joint likelihood implemented
        via 'torch', which can be run on CPUs or GPUs.
License: GPL-3
Encoding: UTF-8
LazyData: true
Depends: R (>= 4.1.0)
Imports: torch, reformulas, stats, mvtnorm, utils, rstudioapi, abind,
        graphics, grDevices, Metrics, parallel, mgcv, cli, crayon,
        ggplot2, checkmate, mathjaxr, beeswarm, qgam, scales, viridis
Suggests: testthat, knitr, rmarkdown, fields
URL: https://github.com/TheoreticalEcology/s-jSDM/
BugReports: https://github.com/TheoreticalEcology/s-jSDM/issues
Roxygen: list(old_usage = FALSE, markdown = TRUE)
VignetteBuilder: knitr
RdMacros: mathjaxr
Config/roxygen2/version: 8.1.0
Config/pak/sysreqs: cmake make libuv1-dev zlib1g-dev
Repository: https://theoreticalecology.r-universe.dev
Date/Publication: 2026-10-17 10:06:09 UTC
RemoteUrl: https://github.com/theoreticalecology/s-jsdm
RemoteRef: HEAD
RemoteSha: 54a545277d89ea954f3dd26e2d152638e1b48d99
RemoteSubdir: sjSDM
NeedsCompilation: no
Packaged: 2026-10-17 11:13:58 UTC; root
Author: Maximilian Pichler [aut, cre] (ORCID:
    <https://orcid.org/0000-0003-2252-8327>),
  Florian Hartig [aut] (ORCID: <https://orcid.org/0000-0002-6255-9059>),
  Wang Cai [ctb]
Maintainer: Maximilian Pichler <maximilian.pichler@biologie.uni-regensburg.de>