Premium
Genetic algorithm‐based partial least squares regression for estimating legume content in a grass‐legume mixture using field hyperspectral measurements
Author(s) -
Kawamura Kensuke,
Watanabe Nariyasu,
Sakanoue Seiichi,
Lee HyoJin,
Lim Jihyun,
Yoshitoshi Rena
Publication year - 2013
Publication title -
grassland science
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.388
H-Index - 19
eISSN - 1744-697X
pISSN - 1744-6961
DOI - 10.1111/grs.12026
Subject(s) - partial least squares regression , hyperspectral imaging , coefficient of determination , canopy , mathematics , linear regression , regression analysis , standard error , mean squared error , regression , statistics , remote sensing , botany , biology , geography
This study investigated the ability of a field hyperspectral radiometer (400–2350 nm) and genetic algorithm‐based partial least squares ( GA ‐ PLS ) regression to estimate legume content in a mixed sown pasture in H okkaido, J apan. Canopy reflectance data and plant samples were obtained from 50 selected sites in the spring ( M ay) and summer (July) of 2007 ( n = 100). The predictive accuracy of GA ‐ PLS was compared with that of multiple linear regression ( MLR ) and of standard full‐spectrum PLS ( FS ‐ PLS ) for the spring and summer datasets. Overall, the highest coefficient of determination ( R 2 ) and the lowest root mean squared error of cross validation ( RMSECV ) values were obtained in the GA ‐ PLS models for both datasets ( R 2 = 0.72–0.86, RMSECV = 4.10–5.73%). Selected hyperspectral wavebands in the GA ‐ PLS models did not perfectly match wavelengths identified previously using MLR , but in most cases, they were within 20 nm of previously known wavelength regions.