Machine learning based prediction of soil total nitrogen, organic carbon and moisture content by using VIS-NIR spectroscopy

Show simple item record

dc.contributor.author Morellos, Antonios
dc.contributor.author Pantazi, Xanthoula-Eirini
dc.contributor.author Moshou, Dimitrios
dc.contributor.author Alexandridis, Thomas
dc.contributor.author Whetton, Rebecca
dc.contributor.author Tziotzios, Georgios
dc.contributor.author Wiebensohn, Jens
dc.contributor.author Bill, Ralf
dc.contributor.author Mouazen, Abdul Mounem
dc.date.accessioned 2016-07-06T16:10:58Z
dc.date.available 2016-07-06T16:10:58Z
dc.date.issued 2016-05-24
dc.identifier.citation Antonios Morellos, Xanthoula-Eirini Pantazi, Dimitrios Moshou, Thomas Alexandridis, Rebecca Whetton, Georgios Tziotzios, Jens Wiebensohn, Ralf Bill, Abdul M. Mouazen, Machine learning based prediction of soil total nitrogen, organic carbon and moisture content by using VIS-NIR spectroscopy, Biosystems Engineering, Volume 152, December 2016, pp104-116 en_UK
dc.identifier.issn 1537-5110
dc.identifier.uri http://dx.doi.org/10.1016/j.biosystemseng.2016.04.018
dc.identifier.uri http://dspace.lib.cranfield.ac.uk/handle/1826/10106
dc.description.abstract It is widely known that the visible and near infrared (VIS-NIR) spectroscopy has the potential of estimating soil total nitrogen (TN), organic carbon (OC) and moisture content (MC) due to the direct spectral responses these properties have in the near infrared (NIR) region. However, improving the prediction accuracy requires advanced modelling techniques, particularly when measurement is planned for fresh (wet and un-processed) soil samples. The aim of this work is to compare the predictive performance of two linear multivariate and two machine learning methods for TN, OC and MC. The two multivariate methods investigated included principal component regression (PCR) and partial least squares regression (PLSR), whereas the machine learning methods included least squares support vector machines (LS-SVM), and Cubist. A mobile, fibre type, VIS-NIR spectrophotometer was utilised to collect soil spectra (305–2200 nm) in diffuse reflectance mode from 140 wet soil samples collected from one field in Germany. The results indicate that machine learning methods are capable of tackling non-linear problems in the dataset. LS-SVMs and the Cubist method out-performed the linear multivariate methods for the prediction of all three soil properties studied. LS-SVM provided the best prediction for MC (root mean square error of prediction (RMSEP) = 0.457% and residual prediction deviation (RPD) = 2.24) and OC (RMSEP = 0.062% and RPD = 2.20), whereas the Cubist method provided the best prediction for TN (RMSEP = 0.071 and RPD = 1.96). en_UK
dc.language.iso en en_UK
dc.publisher Elsevier en_UK
dc.rights Attribution-NonCommercial-NoDerivatives 4.0 International en_UK
dc.rights.uri http://creativecommons.org/licenses/by-nc-nd/4.0/
dc.subject VIS-NIR spectroscopy en_UK
dc.subject Data mining en_UK
dc.subject Chemometrics en_UK
dc.subject Soil properties en_UK
dc.title Machine learning based prediction of soil total nitrogen, organic carbon and moisture content by using VIS-NIR spectroscopy en_UK
dc.type Article en_UK


Files in this item

This item appears in the following Collection(s)

Show simple item record

Attribution-NonCommercial-NoDerivatives 4.0 International Except where otherwise noted, this item's license is described as Attribution-NonCommercial-NoDerivatives 4.0 International

Search CERES


Browse

My Account

Statistics