6533b86cfe1ef96bd12c8aac
RESEARCH PRODUCT
Comparison of Metrics for the Classification of Soils Under Variable Geometrical Conditions Using Hyperspectral Data
Audrey RomanPierre GoutonFrédéric BaretWeidong LiuFrancois TavinSandrine Mathieusubject
Coefficient of determination010504 meteorology & atmospheric sciencesMean squared error0211 other engineering and technologiesSOIL IDENTIFICATION02 engineering and technologySolid modeling01 natural sciencesSpectral lineCLASSIFICATION[SPI]Engineering Sciences [physics]HYPERSPECTRALSurface roughnessElectrical and Electronic EngineeringComputingMilieux_MISCELLANEOUS021101 geological & geomatics engineering0105 earth and related environmental sciencesMathematicsRemote sensingHyperspectral imagingSoil classificationGeotechnical Engineering and Engineering GeologySOLAR-VIEW ANGLESoil waterSPECTRAL LIBRARYDISTANCE METRIC[SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processingdescription
International audience; The objective of this letter is to find a distance metric between reflectance spectra that is not sensitive to the variations on the soil reflectance induced by the geometry of solar-view angles. This is motivated by the fact that differences between spectra measured for the same soil under different observation and illumination configurations can lead to misclassifications. Using 26 soils of different compositions simulated with Hapke’s model and 92 soils of different compositions measured under 28 solarview angle geometries in laboratory conditions, we tested three metrics, namely, root-mean-square error, spectral angle mapper, and R2 (the coefficient of determination), and we compared their efficiency. The best results are obtained with the coefficient of determination with 93% of good classifications
| year | journal | country | edition | language |
|---|---|---|---|---|
| 2008-10-01 |