FINN: Forest Informed Neural Networks

A hybrid dynamic forest (gap) model (FINN) that can be configured as a fully mechanistic, process-based model, like classic forest gap models, or with its demographic processes (growth, mortality, regeneration) replaced by deep neural networks (DNNs), or any combination of the two. Provides functions to define a model and its mechanistic or empirical components, calibrate it to forest inventory data, and interpret the calibrated processes. FINN is implemented with the 'torch' package, which supplies GPU support and the automatic differentiation used to calibrate the model by stochastic gradient descent; no knowledge of 'torch' is required. The hybrid modeling approach is described in Pichler and Käber (2026) <doi:10.1111/2041-210x.70347>.

Version: 0.2.0
Depends: R (≥ 4.1.0)
Imports: abind, cli, stats, utils, data.table, coro, Rcpp, torch, ggplot2, glue, grid
LinkingTo: Rcpp
Suggests: testthat (≥ 3.0.0), knitr, rmarkdown
Published: 2026-11-19
DOI: 10.32614/CRAN.package.FINN
Author: Maximilian Pichler ORCID iD [aut], Yannek Käber ORCID iD [aut, cre]
Maintainer: Yannek Käber <y.kaeber at posteo.de>
BugReports: https://github.com/FINNverse/FINN/issues
License: GPL (≥ 3)
URL: https://github.com/FINNverse/FINN, https://finnverse.github.io/FINN/
NeedsCompilation: yes
Citation: FINN citation info
Materials: README, NEWS
CRAN checks: FINN results

Documentation:

Reference manual: FINN.html , FINN.pdf
Vignettes: Introduction to FINN (source)
Parameterising FINN from Ellenberg indicator values (source)
Preparing your data for FINN (source)
Fitting FINN to forest inventory data (Oregon, US FIA) (source)
Mortality: a binomial response and a neural-network process (source)

Downloads:

Package source: FINN_0.2.0.tar.gz
Windows binaries: r-devel: FINN_0.1.0.zip, r-release: FINN_0.1.0.zip, r-oldrel: FINN_0.2.0.zip
macOS binaries: r-release (arm64): FINN_0.2.0.tgz, r-oldrel (arm64): FINN_0.2.0.tgz, r-release (x86_64): FINN_0.2.0.tgz, r-oldrel (x86_64): FINN_0.2.0.tgz
Old sources: FINN archive

Linking:

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