0000000000459296
AUTHOR
Francois Tavin
Comparison of metrics to remove the influence of geometrical conditions on soil reflectance
The objective of this work is to find the best metric to ignore the variations of soil reflectance induced by the solar-view angles geometry. Differences between spectra measured for the same soil under different observation and illumination configurations can leads to misclassifications. Using ninety two soils of different composition measured under twenty eight solar- view angles geometries, we tested 3 metrics : RMSE, SAM, R2 (the coefficient of determination) and we compared their performances. The best metric seems to be the coefficient of determination with 93 % of good classifications.
Optimization of image parameters using a hyperspectral library application to soil identification and moisture estimation
The growing number of sensors raises questions about the image parameters required for the application, soil identification and moisture estimation. Hyperspectral images are also known to contain highly redundant information. Hence not all the spectral bands are needed for the satisfactory classification of the soil types. Hence, the work was aimed at obtaining these optimal spectral bands for identifying the soil types and to use these spectral bands to estimate the moisture content of the soils using the method proposed by Whiting et.al.
Comparison of Metrics for the Classification of Soils Under Variable Geometrical Conditions Using Hyperspectral Data
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 determinat…
Optimal band selection for future satellite sensor dedicated to soil science
Hyperspectral imaging systems could be used for identifying the different soil types from the satellites. However, detecting the reflectance of the soils in all the wavelengths involves the use of a large number of sensors with high accuracy and also creates a problem in transmitting the data to earth stations for processing. The current sensors can reach a bandwidth of 20 nm and hence, the reflectance obtained using the sensors are the integration of reflectance obtained in each of the wavelength present in the spectral band. Moreover, not all spectral bands contribute equally to classification and hence, identifying the bands necessary to have a good classification is necessary to reduce …
Comparison of metrics for the classification of soils under variable geometrical conditions using hyperspectral data
International audience; no abstract