@article{fdi:010094310,
  title = {{P}redicting soil nutrient classes using {V}is-{NIR} spectroscopy to support sustainable farming decisions},
  author = {{K}usuma, {C}. {G}. and {D}harumarajan, {S}. and {V}asundhara, {R}. and {G}omez, {C}{\'e}cile and {M}anjunatha, {M}. {H}. and {H}egde, {R}.},
  editor = {},
  language = {{ENG}},
  abstract = {{E}fficient nutrient management is crucial for sustainable agriculture and ecosystem health. {T}raditional approaches to nutrient recommendations often rely on soil nutrient classes rather than specific numerical values. {V}isible-{N}ear-{I}nfrared ({V}is-{NIR}) spectroscopy offers a rapid, nondestructive method for predicting soil properties. {T}his study explores the use of {V}is-{NIR} spectroscopy to classify soil nutrient levels for improved agricultural decision-making. {A} dataset of 216 soil samples, collected from diverse land uses in the {G}ummlapalli subwatershed, {K}arnataka, {I}ndia, was analyzed for 11 soil properties, including p{H}, soil organic carbon ({SOC}), macronutrients ({N}, {P}2{O}5, {K}2{O}, {S}), and micronutrients ({B}, {C}u, {F}e, {M}n, {Z}n). {T}he {P}artial {L}east {S}quares {R}egression ({PLSR}) model, enhanced with {S}avitzky-{G}olay ({SG}) smoothing and {S}tandard {N}ormal {V}ariate ({SNV}) transformation, showed variable prediction performance ({R}2: 0.04 for {K}2{O} to 0.70 for p{H}). {T}wo approaches for nutrient classification were evaluated: (1) indirect classification based on predicted soil properties and (2) direct classification using {P}artial {L}east {S}quares {D}iscriminant {A}nalysis ({PLS}-{DA}). {T}o address class imbalance during classification, the {S}ynthetic {M}inority {O}ver-sampling {T}echnique ({SMOTE}) was employed. {D}irect classification outperformed the indirect approach, achieving higher overall accuracy ({OA}) for key properties, including p{H} (0.72), {SOC} (0.61), {P}2{O}5 (0.84), {K}2{O} (0.50), and {C}u (0.96). {T}hese results underscore the reliability of direct classification for assessing soil nutrient classes. {T}his study highlights the potential of {V}is-{NIR} spectroscopy as a robust tool for soil nutrient classification, enabling precise fertilizer recommendations, supporting sustainable farming practices, and promoting ecosystem sustainability.},
  keywords = {classification ; fertilizer recommendations ; prediction ; preprocessing ; soil property ; spectral data ; {INDE}},
  booktitle = {},
  journal = {{L}and {D}egradation and {D}evelopment},
  volume = {[{E}arly access]},
  numero = {},
  pages = {[11 p.]},
  ISSN = {1085-3278},
  year = {2025},
  DOI = {10.1002/ldr.70007},
  URL = {https://www.documentation.ird.fr/hor/fdi:010094310},
}