20190329
Author :
Tümsavaş Zeynal, Tekin Yücel, Ulusoy Yahya, Mouazen Abdul M
Tümsavaş Zeynal, Tekin Yücel, Ulusoy Yahya, Mouazen Abdul M
Title : Prediction and mapping of soil clay and sand contents using visible and near-infrared spectroscopy
Journal : Biosystems engineering
Comment :
The aim of this research was to examine the potential of visible and near infrared (Vis
-NIR) spectroscopy for the prediction and mapping of sand and clay fractions of soils.
This study demonstrated that soil sand and clay can be successfully measured and mapped using Vis-NIR spectroscopy under both laboratory and on-line scanning conditions.
A partial least squares (PLS) regression with leave-one-out cross-validation analysis was carried out using the calibration set, and the resulting model prediction ability was tested using the prediction set.
Models developed were used to predict sand and clay content using laboratory spectra and spectra collected on-line from the field. Results showed an “excellent” laboratory prediction performance for both sand (regression coefficient R2 = 0.90, root mean square error of prediction (RMSEP) = 2.91% and ratio of prediction deviation (RPD) = 3.25 in cross-validation; R2 = 0.81, RMSEP = 3.84% and RPD = 2.33 in the prediction set) and clay (R2 = 0.91, RMSEP = 2.67% and RPD = 3.51 in cross validation; R2 = 0.85, RMSEP = 3.40% and RPD = 2.66 in the prediction set). On-line predictions were less accurate than the laboratory results, although the online predictions were still very good (RPD = 2.25-2.31).
Comment :
The aim of this research was to examine the potential of visible and near infrared (Vis
-NIR) spectroscopy for the prediction and mapping of sand and clay fractions of soils.
This study demonstrated that soil sand and clay can be successfully measured and mapped using Vis-NIR spectroscopy under both laboratory and on-line scanning conditions.
A partial least squares (PLS) regression with leave-one-out cross-validation analysis was carried out using the calibration set, and the resulting model prediction ability was tested using the prediction set.
Models developed were used to predict sand and clay content using laboratory spectra and spectra collected on-line from the field. Results showed an “excellent” laboratory prediction performance for both sand (regression coefficient R2 = 0.90, root mean square error of prediction (RMSEP) = 2.91% and ratio of prediction deviation (RPD) = 3.25 in cross-validation; R2 = 0.81, RMSEP = 3.84% and RPD = 2.33 in the prediction set) and clay (R2 = 0.91, RMSEP = 2.67% and RPD = 3.51 in cross validation; R2 = 0.85, RMSEP = 3.40% and RPD = 2.66 in the prediction set). On-line predictions were less accurate than the laboratory results, although the online predictions were still very good (RPD = 2.25-2.31).
댓글
댓글 쓰기