Comparison of Multivariate Regression models for the calibration of a portable VIS-NIR spectrophotometer.
Soil Total Nitrogen (TN), Organic Carbon (OC) and moisture content (MC) can be measured with on-line visible and near infrared spectroscopy (VIS-NIRS). Their calibration method may considerably affect the measurement accuracy.
MSc thesis abstract (submitted 23 June 2015):
The aim of this study was to compare four multivariate regression methods for their predictive effectiveness on these soil variables for the calibration of a
visible and near infrared (VIS-NIR) spectrophotometer for the on-line measurement of TN in a German field. A mobile, fiber type,
VIS-NIR spectrophotometer (AgroSpec from tec5 Technology for Spectroscopy, Germany) mounted in an on-line sensor platform,
comprising of measurement range of 305–2200 nm was utilized so as to obtain soil spectra in diffuse reflectance mode. The four
methods that were compared were Principal Component Regression (PCR), Partial Least Squares Regression (PLSR), Least – Squares Support Vector Machines and Cubist. The results showed that machine learning methods such as LS-SVMs and Cubist method.
Student: Antonios Morellos
Supervisor: Rob Schouten