Package: sjSDM 1.0.7

Maximilian Pichler

sjSDM: Scalable Joint Species Distribution Modeling

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 and the option to fit responses using deep neural networks instead of a standard linear predictor. 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 'PyTorch' and 'reticulate', which can be run on CPUs or GPUs.

Authors:Maximilian Pichler [aut, cre], Florian Hartig [aut], Wang Cai [ctb]

sjSDM_1.0.7.tar.gz
sjSDM_1.0.7.zip(r-4.7)sjSDM_1.0.7.zip(r-4.6)sjSDM_1.0.7.zip(r-4.5)
sjSDM_1.0.7.tgz(r-4.6-any)sjSDM_1.0.7.tgz(r-4.5-any)
sjSDM_1.0.7.tar.gz(r-4.7-any)sjSDM_1.0.7.tar.gz(r-4.6-any)
sjSDM_1.0.7.tgz(r-4.6-emscripten)
manual.pdf |manual.html✨
DESCRIPTION |NEWS
card.svg |card.png
sjSDM/json (API)

# Install 'sjSDM' in R:

install.packages('sjSDM', repos = c('https://theoreticalecology.r-universe.dev', 'https://cloud.r-project.org'))

Bug tracker:https://github.com/theoreticalecology/s-jsdm/issues

Datasets:

butterflies - Butterflies
eucalypts - Eucalypts

On CRAN:

deep-learning gpu-acceleration machine-learning species-distribution-modelling species-interactions

7.87 score 78 stars 105 scripts 271 downloads 26 exports 67 dependencies

Last updated from:855e785863. Checks:9 OK. Indexed: yes.

Target	Result	Time
linux-devel-x86_64	OK	230
source / vignettes	OK	309
linux-release-x86_64	OK	239
macos-release-arm64	OK	240
macos-oldrel-arm64	OK	278
windows-devel	OK	340
windows-release	OK	295
windows-oldrel	OK	236
wasm-release	OK	144

Exports:AccSGD AdaBound Adamax bioticStruct DNN generateSpatialEV getCor getCov getSe getWeights install_diagnostic install_sjSDM internalStructure is_torch_available linear madgrad plotAssemblyEffects RMSprop Rsquared setWeights SGD simulate_SDM sjSDM sjSDM_cv sjSDM.tune sjSDMControl

Dependencies:abind backports base64enc beeswarm bslib cachem checkmate cli codetools commonmark cpp11 crayon digest doParallel farver fastmap fontawesome foreach fs ggplot2 glue gridExtra gtable here htmltools httpuv isoband iterators jquerylib jsonlite labeling later lattice lifecycle magrittr mathjaxr Matrix memoise Metrics mgcv mime mvtnorm nlme otel plyr png promises qgam R6 rappdirs RColorBrewer Rcpp RcppTOML reticulate rlang rprojroot rstudioapi S7 sass scales shiny sourcetools vctrs viridis viridisLite withr xtable

sjSDM: Getting started with sjSDM - a scalable joint Species Distribution Model

Rendered fromsjSDM_Introduction.Rmdusingknitr::rmarkdown

Last update: 2025-09-17
Started: 2023-03-30

Help page	Topics
AccSGD	AccSGD
AdaBound	AdaBound
Adamax	Adamax
Anova / Variation partitioning	anova.sjSDM
biotic structure	bioticStruct
butterflies	butterflies
check module	check_module
check model check model and rebuild if necessary	checkModel
Return coefficients from a fitted sjSDM model	coef.sjSDM
DiffGrad	DiffGrad
Non-linear model (deep neural network) of environmental responses	DNN
eucalypts	eucalypts
Generate spatial eigenvectors	generateSpatialEV
getCor	getCor getCor.sjSDM
getCov	getCov getCov.sjSDM
getImportance	getImportance
Post hoc calculation of standard errors	getSe
Get weights	getWeights getWeights.sjSDM
Importance of environmental, spatial and association components	importance
install diagnostic	install_diagnostic
Install sjSDM and its dependencies	install_sjSDM
Installation help	sjSDM-package installation_help
Plot internal metacommunity structure	internalStructure
is_torch_available	is_torch_available
Linear model of environmental response	linear
Extract negative-log-Likelihood from a fitted sjSDM model	logLik.sjSDM
madgrad	madgrad
new_image function	new_image
Coefficients plot	plot.sjSDM
Plot elastic net tuning	plot.sjSDM_cv
Training history	plot.sjSDM.DNN
Plot anova results	plot.sjSDManova
Plot importance	plot.sjSDMimportance
Plot internal structure	plot.sjSDMinternalStructure
Plot predictors of assembly processes	plotAssemblyEffects
Internal coefficients plot	plotsjSDMcoef
Predict from a fitted sjSDM model	predict.sjSDM
Print a bioticStruct object	print.bioticStruct
Print a DNN object	print.DNN
Print a linear object	print.linear
Print a fitted sjSDM model	print.sjSDM
Print a fitted sjSDM_cv model	print.sjSDM_cv
Print sjSDM anova object	print.sjSDManova
Print importance	print.sjSDMimportance
Print internal structure object	print.sjSDMinternalStructure
Residuals for a sjSDM model	residuals.sjSDM
RMSprop	RMSprop
R-squared	Rsquared
Set weights	setWeights setWeights.sjSDM
SGD	SGD
Simulate joint Species Distribution Models	simulate_SDM
Generates simulations from sjSDM model	simulate.sjSDM
Fitting scalable joint Species Distribution Models (sjSDM)	sjSDM sjSDM.tune
Cross validation of elastic net tuning	sjSDM_cv
sjSDM control object	sjSDMControl
Return summary of a fitted sjSDM model	summary.sjSDM
Return summary of a fitted sjSDM_cv model	summary.sjSDM_cv
Summary table of sjSDM anova	summary.sjSDManova
Update and re-fit a model call	update.sjSDM

Package: sjSDM 1.0.7

sjSDM: Scalable Joint Species Distribution Modeling

Citation

Development and contributors

Readme and manuals

Help Manual

Usage by other packages (reverse dependencies)