@article{fdi:010076571,
  title = {{S}oil texture estimation using radar and optical data from {S}entinel-1 and {S}entinel-2},
  author = {{B}ousbih, {S}. and {Z}ribi, {M}. and {P}elletier, {C}. and {G}orrab, {A}. and {L}ili-{C}habaane, {Z}. and {B}aghdadi, {N}. and {B}en {A}issa, {N}. and {M}ougenot, {B}ernard},
  editor = {},
  language = {{ENG}},
  abstract = {{T}his paper discusses the combined use of remotely sensed optical and radar data for the estimation and mapping of soil texture. {T}he study is based on {S}entinel-1 ({S}-1) and {S}entinel-2 ({S}-2) data acquired between {J}uly and early {D}ecember 2017, on a semi-arid area about 3000 km(2) in central {T}unisia. {I}n addition to satellite acquisitions, texture measurement samples were taken in several agricultural fields, characterized by a large range of clay contents (between 13% and 60%). {F}or the period between {J}uly and {A}ugust, various optical indicators of clay content {S}hort-{W}ave {I}nfrared ({SWIR}) bands and soil indices) were tested over bare soils. {S}atellite moisture products, derived from combined {S}-1 and {S}-2 data, were also tested as an indicator of soil texture. {A}lgorithms based on the support vector machine ({SVM}) and random forest ({RF}) methods are proposed for the classification and mapping of clay content and a three-fold cross-validation is used to evaluate both approaches. {T}he classifications with the best performance are achieved using the soil moisture indicator derived from combined {S}-1 and {S}-2 data, with overall accuracy ({OA}) of 63% and 65% for the {SVM} and {RF} classifications, respectively.},
  keywords = {{S}entinel-1 ; {S}entinel-2 ; {S}oil {M}oisture ; {T}exture ; {C}lay ; {SVM} ; {R}andom {F}orest ; {TUNISIE} ; {ATLAS} ; {KAIROUAN} {PLAINE}},
  booktitle = {},
  journal = {{R}emote {S}ensing},
  volume = {11},
  numero = {13},
  pages = {art. 1520 [20p.]},
  ISSN = {2072-4292},
  year = {2019},
  DOI = {10.3390/rs11131520},
  URL = {https://www.documentation.ird.fr/hor/fdi:010076571},
}