sjSDM

Scalable Joint Species Distribution Modeling

Last update: 17 June 2023

Copyright license: GNU General Public License, version 3.0

Software version identifier: 1.0.4, 1.0.0, 1.0.1, 1.0.2, 1.0.3, 1.0.5

Description

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.

Cites work

A new joint species distribution model for faster and more accurate inference of species associations from big community data

This page was built for software: sjSDM