Supervised latent-variable regression for high-dimensional predictors such as soil reflectance spectra. The model uses an encoder-decoder neural network with a stochastic Gaussian latent representation regularized by a Kullback-Leibler term, and a supervised prediction head trained jointly with the reconstruction objective. The implementation interfaces R with a 'Python' deep-learning backend and provides utilities for training, tuning, and prediction.
| Version: | 0.1.9 |
| Depends: | R (≥ 3.5.0) |
| Imports: | reticulate, stats |
| Suggests: | knitr, rmarkdown, prospectr, pls |
| Published: | 2026-03-17 |
| DOI: | 10.32614/CRAN.package.soilVAE (may not be active yet) |
| Author: | Hugo Rodrigues [aut, cre] |
| Maintainer: | Hugo Rodrigues <rodrigues.machado.hugo at gmail.com> |
| BugReports: | https://github.com/HugoMachadoRodrigues/soilVAE/issues |
| License: | MIT + file LICENSE |
| URL: | https://hugomachadorodrigues.github.io/soilVAE/, https://github.com/HugoMachadoRodrigues/soilVAE/ |
| NeedsCompilation: | no |
| SystemRequirements: | Python (>= 3.9); TensorFlow (>= 2.13); Keras (>= 3) |
| Citation: | soilVAE citation info |
| Materials: | README, NEWS |
| CRAN checks: | soilVAE results |
| Reference manual: | soilVAE.html , soilVAE.pdf |
| Vignettes: |
soilVAE vignettes (source) soilVAE Workflow (source, R code) |
| Package source: | soilVAE_0.1.9.tar.gz |
| Windows binaries: | r-devel: not available, r-release: soilVAE_0.1.9.zip, r-oldrel: soilVAE_0.1.9.zip |
| macOS binaries: | r-release (arm64): not available, r-oldrel (arm64): soilVAE_0.1.9.tgz, r-release (x86_64): not available, r-oldrel (x86_64): not available |
Please use the canonical form https://CRAN.R-project.org/package=soilVAE to link to this page.