https://finnverse.r-universe.devRecent package updates in finnverseR-universehttps://github.com/finnverse.pnghttps://finnverse.r-universe.devTue, 22 Sep 2026 12:24:15 GMTy.kaeber@posteo.de (Yannek Käber)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>.https://github.com/r-universe/finnverse/actions/runs/35748827162Tue, 22 Sep 2026 12:24:15 GMTFINN0.2.0failurehttps://finnverse.r-universe.devhttps://github.com/finnverse/finnD-Fit_to_FIA.RmdD-Fit_to_FIA.htmlFitting FINN to forest inventory data (Oregon, US FIA)2026-07-14 12:26:062026-09-22 12:24:14A-Introduction_to_FINN.RmdA-Introduction_to_FINN.htmlIntroduction to FINN2026-07-14 12:26:062026-08-11 06:27:37E-Mortality.RmdE-Mortality.htmlMortality: a binomial response and a neural-network process2026-07-14 16:18:352026-09-22 12:24:14B-Succession_demo.RmdB-Succession_demo.htmlParameterising FINN from Ellenberg indicator values2026-07-14 12:26:062026-07-28 10:20:34C-Data_preparation.RmdC-Data_preparation.htmlPreparing your data for FINN2026-07-14 12:26:062026-07-28 10:20:34