deepspat0.3.1 package

Deep Compositional Spatial Models

AFF_1D

Affine transformation on a 1D domain

AFF_2D

Affine transformation on a 2D domain

AWU

Axial Warping Unit

bisquares1D

Bisquare functions on a 1D domain

bisquares2D

Bisquare functions on a 2D domain

deepspat_bivar_GP

Deep bivariate compositional spatial model for Gaussian processes

deepspat_GP

Deep compositional spatial model for Gaussian processes

deepspat_MSP

Deep compositional spatial model for max-stable processes

deepspat_nn_GP

Deep compositional spatial model (with nearest neighbors) for Gaussian...

deepspat_nn_ST_GP

Deep compositional spatio-temporal model (with nearest neighbors) for ...

deepspat_rPP

Deep compositional spatial model for r-Pareto processes

deepspat_trivar_GP

Deep trivariate compositional spatial model for Gaussian processes

deepspat

Deep compositional spatial models

init_learn_rates

Initialise learning rates

initvars

Initialise weights and parameters

LFT

LFT (Möbius transformation)

predict.deepspat_bivar_GP

Deep bivariate compositional spatial model

predict.deepspat_GP

Deep compositional spatial model

predict.deepspat_nn_GP

Deep compositional spatial model (with nearest neighbors)

predict.deepspat_nn_ST_GP

Deep compositional spatio-temporal model (with nearest neighbors)

predict.deepspat_trivar_GP

Deep trivariate compositional spatial model

predict.deepspat

Deep compositional spatial model

RBF_block

Radial Basis Function Warpings

set_deepspat_seed

Set TensorFlow seed

sim_data

Generate simulation data for testing

summary.deepspat_MSP

Deep compositional spatial model for max-stable processes

summary.deepspat_rPP

Deep compositional spatial model for r-Pareto processes

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>, Vu et al. (2023) <doi:10.1016/j.spasta.2023.100742>, and Shao et al. (2025) <doi:10.48550/arXiv.2505.12548>.

  • Maintainer: Quan Vu
  • License: Apache License 2.0
  • Last published: 2025-11-25