@article{fdi:010086017,
  title = {{U}sing {PRISMA} hyperspectral satellite imagery and {GIS} approaches for soil fertility mapping ({F}erti{M}ap) in {N}orthern {M}orocco},
  author = {{G}asmi, {A}. and {G}omez, {C}{\'e}cile and {C}hehbouni, {A}bdelghani and {D}hiba, {D}. and {E}l {G}harous, {M}.},
  editor = {},
  language = {{ENG}},
  abstract = {{Q}uickly and correctly mapping soil nutrients significantly impact accurate fertilization, food security, soil productivity, and sustainable agricultural development. {W}e evaluated the potential of the new {PRISMA} hyperspectral sensor for mapping soil organic matter ({SOM}), available soil phosphorus ({P}2{O}5), and potassium ({K}2{O}) content over a cultivated area in {K}houribga, northern {M}orocco. {T}hese soil nutrients were estimated using (i) the random forest ({RF}) algorithm based on feature selection methods, including feature subset evaluation and feature ranking methods belonging to three categories (i.e., filter, wrapper, and embedded techniques), and (ii) 107 soil samples taken from the study area. {T}he results show that the {RF}-embedded method produced better predictive accuracy compared with the filter and wrapper methods. {T}he model for {SOM} showed moderate accuracy ({R}-val(2) = 0.5, {RMSEP} = 0.43%, and {RPIQ} = 2.02), whereas that for soil {P}2{O}5 and {K}2{O} exhibited low efficiency ({R}-val(2) = 0.26 and 0.36, {RMSEP} = 51.07 and 182.31 ppm, {RPIQ} = 0.65 and 1.16, respectively). {T}he interpolation of {RF}-residuals by ordinary kriging ({OK}) methods reached the highest predictive results for {SOM} ({R}-val(2) = 0.69, {RMSEP} = 0.34%, and {RPIQ} = 2.56), soil {P}2{O}5 ({R}-val(2) = 0.44, {RMSEP} = 44.10 ppm, and {RPIQ} = 0.75), and soil {K}2{O} ({R}-val(2) = 0.51, {RMSEP} = 159.29 ppm, and {RPIQ} = 1.34), representing the best fitting ability between the hyperspectral data and soil nutrients. {T}he result maps provide a spatially continuous surface mapping of the soil landscape, conforming to the pedological substratum. {F}inally, the hyperspectral remote sensing imagery can provide a new way for modeling and mapping soil fertility, as well as the ability to diagnose nutrient deficiencies.},
  keywords = {{PRISMA} ; hyperspectral image ; feature selection ; random forest ; {GIS} ; approaches ; soil fertility mapping ; {MAROC} ; {KHOURIBGA}},
  booktitle = {},
  journal = {{R}emote {S}ensing},
  volume = {14},
  numero = {16},
  pages = {4080 [22 ]},
  year = {2022},
  DOI = {10.3390/rs14164080},
  URL = {https://www.documentation.ird.fr/hor/fdi:010086017},
}