Design-Based Residual-Correction Forests for Digital Soil Mapping R package GeoVersa version 0.3.0 Implements DB-TARF (Design-Based Targeted Adaptive Residual Forest) for large-scale digital soil and ecological mapping evaluated under the design-based paradigm of Wadoux et al. (2021) <doi:10.1016/j.ecolmodel.2021.109692>. A random forest is augmented by a cross-fitted, out-of-fold-selected residual correction (residual forests, ordinary kriging, recalibration), together with design-based conformal prediction intervals. Software Imports: ranger, caret, stats, withr Suggests: Cubist, gstat, sp, nnet, testthat (>= 3.0.0) Hugo Rodrigues <rodrigues.machado.hugo@gmail.com> Comprehensive R Archive Network (CRAN) Hugo Rodrigues [aut, cre] MIT + file LICENSE (https://CRAN.R-project.org/package=GeoVersa/LICENSE) 2026-07-06 application/tgz https://CRAN.R-project.org/package=GeoVersa doi:10.32614/CRAN.package.GeoVersa