deepspat: Deep Compositional Spatial Models

Deep compositional spatial models are standard spatial covariance models coupled with an injective warping function of the spatial domain. The warping function is constructed through a composition of multiple elemental injective functions in a deep-learning framework. The package implements two cases for the univariate setting; first, when these warping functions are known up to some weights that need to be estimated, and, second, when the weights in each layer are random. In the multivariate setting only the former case is available. Estimation and inference is done using 'tensorflow', which makes use of graphics processing units. For more details see Zammit-Mangion et al. (2022) <doi:10.1080/01621459.2021.1887741>, Vu et al. (2022) <doi:10.5705/ss.202020.0156>, and Vu et al. (2023) <doi:10.1016/j.spasta.2023.100742>.

Version:	0.3.0
Imports:	data.table, dplyr, Matrix, methods, reticulate, keras, tensorflow, tfprobability, evd, SpatialExtremes, fields
Published:	2025-11-12
DOI:	10.32614/CRAN.package.deepspat (may not be active yet)
Author:	Andrew Zammit-Mangion [aut], Quan Vu [aut, cre], Xuanjie Shao [aut]
Maintainer:	Quan Vu <quanvustats at gmail.com>
License:	Apache License 2.0
NeedsCompilation:	no
SystemRequirements:	TensorFlow (https://www.tensorflow.org/),
Materials:	README, NEWS
CRAN checks:	deepspat results

Documentation:

Reference manual:

deepspat.html , deepspat.pdf

Downloads:

Package source:	deepspat_0.3.0.tar.gz
Windows binaries:	r-devel: deepspat_0.3.0.zip, r-release: not available, r-oldrel: not available
macOS binaries:	r-release (arm64): deepspat_0.3.0.tgz, r-oldrel (arm64): deepspat_0.3.0.tgz, r-release (x86_64): deepspat_0.3.0.tgz, r-oldrel (x86_64): deepspat_0.3.0.tgz

Linking:

Please use the canonical form https://CRAN.R-project.org/package=deepspat to link to this page.