@article{fdi:010075127,
  title = {{H}ow far can the uncertainty on a {D}igital {S}oil {M}ap be known ? : a numerical experiment using pseudo values of clay content obtained from {V}is-{SWIR} hyperspectral imagery},
  author = {{L}agacherie, {P}. and {A}rrouays, {D}. and {B}ourennane, {H}. and {G}omez, {C}{\'e}cile and {M}artin, {M}. and {S}aby, {N}. {P}. {A}.},
  editor = {},
  language = {{ENG}},
  abstract = {{D}igital {S}oil {M}ap uncertainty is usually evaluated from a set of independent soil observations that are used to determine various uncertainty indicators. {H}owever, the number and locations of the sites that constitute these evaluations may impact the value of these indicators. {I}n this paper, a numerical experiment on uncertainty indicators was performed using the pseudo values of topsoil clay content obtained from an airborne hyperspectral image in the {C}ap {B}on region ({T}unisia). {T}hese pseudo values form a soil pattern with a large extent (46% of 300 km(2)), high resolution (5 m) and good accuracy ({R}-val(2) = 0.75) while being free of visible artefacts and pedologically plausible. {T}herefore, the dataset was considered a fair representation of reality while providing a quasi-unlimited choice of sites. {T}he numerical experiment considered three {Q}uantile {R}egression {F}orests as examples of {DSM} models by using inputs from relief soil covariates and geographical locations that were calibrated from 200, 2000 and 100,000 individuals respectively (low, medium and high quality models). {T}heir uncertainty indicators were first evaluated by calculating four uncertainty indicators ({ME}, {MSE}, {SSMSE} and {PICP}) from a large independent validation set of 100,000 sites. {T}hese uncertainty indicators were then computed from independent evaluation sets of different sizes (from 50 to 500 sites) and from different locations (500 evaluation sets of each size). {T}he independent evaluation sets were selected following a stratified random sampling using compact geographical strata. {T}he numerical experiment showed that the values of the uncertainty indicators were highly variable across numbers and locations of sites. {T}he largest variations were observed for evaluation sets with fewer than 100 sites, but non-negligible variations remained for larger evaluation datasets. {T}his result suggested that evaluations from independent sets convey a non-negligible error on the uncertainty indicators, which increases as the number of sites decrease. {E}valuations of {DSM} models from independent evaluation sets should be interpreted with care and uncertainty on validation results should be systematically estimated. {F}or that, numerical experiments for benchmarking {DSM} models on known soil patterns across the world would be a valuable complement to the analytical expressions for the uncertainty indicators and the many {DSM} applications for which these analytical expressions are not valid. {T}his would serve also to improve the sampling techniques for the calibration and evaluation datasets to reduce the error when estimating the uncertainty of a {DSM} product.},
  keywords = {{S}oil mapping ; {U}ncertainty ; {H}yperspectral imagery ; {R}andom forest ; {S}ampling ; {TUNISIE} ; {CAP} {BON}},
  booktitle = {},
  journal = {{G}eoderma},
  volume = {337},
  numero = {},
  pages = {1320--1328},
  ISSN = {0016-7061},
  year = {2019},
  DOI = {10.1016/j.geoderma.2018.08.024},
  URL = {https://www.documentation.ird.fr/hor/fdi:010075127},
}