@article{fdi:010086379,
  title = {{S}pectral assessment of soil properties in semi-arid tropical regions of southern {K}arnataka {P}lateau},
  author = {{L}alitha, {M}. and {D}harumarajan, {S}. and {G}omez, {C}{\'e}cile and {H}egde, {R}. and {K}oyal, {A}. and {K}handal, {S}. and {S}hashikumar, {B}. {N}. and {P}arvathy, {S}.},
  editor = {},
  language = {{ENG}},
  abstract = {{T}he present study assessed the visible and short wave infrared ({VNIR}-{SWIR}) laboratory spectroscopy coupled random forest regression ({RF}) technique for predicting soil properties in the southern {K}arnataka {P}lateau, {I}ndia. {T}he spectral data acquired for about 228 profile samples were used to predict key soil properties. {T}he {RF} model fits well for the spectral prediction of clay ({R}-2 = 0.65), sand ({R}-2 = 0.60), cation exchange capacity ({R}-2 = 0.74), field capacity ({R}-2 = 0.65) and permanent wilting point ({R}-2 = 0.72). {W}herein soil organic carbon was poorly predicted with an {R}-2 of 0.22 and {RPD} of 1.2 due to its lower content and narrow range (0.8 to 20 g kg(-1)). {T}he spectral assessment by {PCA} showed that the first (50%) and third (34%) components had high spectral variation and significantly correlated with soil properties such as p{H}, {CEC}, clay, {FC}, and {PWP} related to wavelengths indicating clay minerals and iron oxides. {H}owever, the second component had less spectral variation (13%) that is related to wavelengths indicating various organic components and correlated well with {SOC}. {T}hus, the {VNIR}-{SWIR} spectroscopy could be a suitable supplementary method for rapidly predicting soil properties related to clay minerals and iron oxides.},
  keywords = {{S}oil survey ; laboratory {VNIR}-{SWIR} spectroscopy ; soil properties ; random ; forest regression ; semiarid tropical ; {INDE} ; {ZONE} {TROPICALE} ; {ZONE} {SEMIARIDE} ; {KARNATAKA} {PLATEAU}},
  booktitle = {},
  journal = {{A}rchives of {A}gronomy and {S}oil {S}cience},
  volume = {[{E}arly access]},
  numero = {},
  pages = {[25 ]},
  ISSN = {0365-0340},
  year = {2022},
  DOI = {10.1080/03650340.2022.2134565},
  URL = {https://www.documentation.ird.fr/hor/fdi:010086379},
}