# ------------------------------------------------
# CITATION.cff file created with {cffr} R package
# See also: https://docs.ropensci.org/cffr/
# ------------------------------------------------
 
cff-version: 1.2.0
message: 'To cite package "soilcnn" in publications use:'
type: software
license: MIT
title: 'soilcnn: Convolutional Neural Networks for Digital Soil Mapping'
version: 0.1.0
abstract: 'A framework, built on ''torch'', for mapping a soil property from point
  observations and a stack of aligned rasters with a convolutional network that reads
  the neighbourhood of each point. It extracts the patches; resamples by spatial blocks
  or by k-fold nearest neighbour distance matching, after Linnenbrink et al. (2024)
  <https://doi.org/10.5194/gmd-17-5897-2024>; tunes and selects under a noise floor
  and the one-standard-error rule; refits the selected configuration under several
  seeds; and predicts median, mean and interval maps over rasters of any extent. The
  map''s centre is the ensemble median over seeds; the mean corrects its back-transformation
  by smearing, after Duan (1983) <https://doi.org/10.1080/01621459.1983.10478017>.
  The intervals are conformal, calibrated three ways and each checked on the test
  set: on the cross-validated residuals; on a calibration set held out of every fold,
  as split conformal, after Lei et al. (2018) <https://doi.org/10.1080/01621459.2017.1307116>;
  or with every fold''s model at each pixel, as CV+, after Barber et al. (2021) <https://doi.org/10.1214/20-AOS1965>
  -- with points, or whole groups of them, weighing alike, after Dunn et al. (2023)
  <https://doi.org/10.1080/01621459.2022.2060112>. The area of applicability of Meyer
  and Pebesma (2021) <https://doi.org/10.1111/2041-210X.13650> is mapped beside them.
  What a model learned is read by permutation, by SHAP values from expected gradients,
  after Erion et al. (2021) <https://doi.org/10.1038/s42256-021-00343-w>, by SAGE,
  after Covert et al. (2020) <https://doi.org/10.48550/arXiv.2004.00668>, by accumulated
  local effects, after Apley and Zhu (2020) <https://doi.org/10.1111/rssb.12377>,
  and by refits without each variable. Random forest and multilayer perceptron baselines
  run under the same folds.'
authors:
- family-names: Moquedace
  given-names: Cássio Marques
  email: cassiomoquedace@gmail.com
- family-names: Baldi
  given-names: Clara Glória Oliveira
preferred-citation:
  type: manual
  title: 'soilcnn: Convolutional Neural Networks for Digital Soil Mapping'
  authors:
  - family-names: Moquedace
    given-names: Cássio Marques
    email: cassiomoquedace@gmail.com
  - family-names: Baldi
    given-names: Clara Glória Oliveira
  year: '2026'
  notes: R package version 0.1.0
  url: https://github.com/moquedace/soilcnn
repository: https://cran.r-universe.dev
repository-code: https://github.com/moquedace/soilcnn
commit: 2379c381d2cc1dea08270023c35fab0d5565455e
url: https://moquedace.github.io/soilcnn/
date-released: '2026-10-21'
contact:
- family-names: Moquedace
  given-names: Cássio Marques
  email: cassiomoquedace@gmail.com