Comparison between artificial neural network and partial least squares for on-line visible and near infrared spectroscopy measurement of soil organic carbon, pH and clay content

Simple item page
dc.contributor.authorKuang, Boyan
dc.contributor.authorMouazen, Abdul M.
dc.contributor.buuauthorTekin, Yucel
dc.contributor.departmentUludağ Üniversitesi/Teknik Bilimler Meslek Yüksekokulu.tr_TR
dc.contributor.researcheridJ-3560-2012tr_TR
dc.contributor.scopusid15064756600tr_TR
dc.date.accessioned2022-06-09T07:37:22Z
dc.date.available2022-06-09T07:37:22Z
dc.date.issued2015-03
dc.description.abstractSoil organic carbon (OC), pH and clay content (CC) can be measured with on-line visible and near infrared spectroscopy (vis-NIRS), whose calibration method may considerably affect the measurement accuracy. The aim of this study was to compare artificial neural network (ANN) and partial least squares regression (PLSR) for the calibration of a visible and near infrared (vis-NIR) spectrophotometer for the on-line measurement of OC, pH and CC in two fields in a Danish farm. An on-line sensor platform equipped with a mobile, fiber type, vis-NIR spectrophotometer (AgroSpec from tec5 Technology for Spectroscopy, Germany), with a measurement range of 305-2200 nm was used to acquire soil spectra in diffuse reflectance mode. Both ANN and PLSR calibration models of OC, pH and CC were validated with independent validation sets. Comparison and full-point maps were developed using ArcGIS software (ESRI, USA). Results of the on-line independent validation showed that ANN outperformed PLSR in both fields. For example, residual prediction deviation (RPD) values for on-line independent validation in Field 1 were improved from 1.93 to 2.28, for OC, from 2.08 to 2.31 for pH and from 1.98 to 2.15 for CC, after ANN analyses as compared to PLSR, whereas root mean square error (RMSEP) values decreased from 1.48 to 1.25%, for OC, from 0.13 to 0.12 for pH and from 1.05 to 0.96% for CC. The comparison maps showed better spatial similarities between laboratory and ANN predicted maps (higher kappa values), as compared to PLSR predicted maps. In most cases, more detailed full-point maps were developed with ANN, although the size of spots with high concentration of PLSR maps matches the measured maps better. Therefore, it was recommended to adopt the ANN for on-line prediction of DC, pH and CC.en_US
dc.description.sponsorshipICT-AGRI under the European Commission's ERA-NET schemeen_US
dc.description.sponsorshipDepartment for Environment, Food & Rural Affairs (DEFRA) (IF0208)en_US
dc.identifier.citationKuang, B. vd. (2015). "Comparison between artificial neural network and partial least squares for on-line visible and near infrared spectroscopy measurement of soil organic carbon, pH and clay content". Soil and Tillage Research, 146(Part B), 243-252.en_US
dc.identifier.endpage252tr_TR
dc.identifier.issn0167-1987
dc.identifier.issuePart Ben_US
dc.identifier.scopus2-s2.0-84910601185tr_TR
dc.identifier.startpage243tr_TR
dc.identifier.urihttps://doi.org/10.1016/j.still.2014.11.002
dc.identifier.urihttps://www.sciencedirect.com/science/article/pii/S0167198714002475
dc.identifier.urihttp://hdl.handle.net/11452/26997
dc.identifier.volume146tr_TR
dc.identifier.wos000347499100013tr_TR
dc.indexed.scopusScopusen_US
dc.indexed.wosSCIEen_US
dc.language.isoenen_US
dc.publisherElsevieren_US
dc.relation.collaborationYurt dışıtr_TR
dc.relation.journalSoil and Tillage Researchen_US
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergitr_TR
dc.relation.tubitak1120471tr_TR
dc.rightsinfo:eu-repo/semantics/closedAccessen_US
dc.subjectANNen_US
dc.subjectSoilen_US
dc.subjectSpectroscopyen_US
dc.subjectVisible and near infrareden_US
dc.subjectMoisture-contenten_US
dc.subjectPredictionen_US
dc.subjectSensoren_US
dc.subjectCalibrationen_US
dc.subjectAgreementen_US
dc.subjectAccuracyen_US
dc.subjectSpikingen_US
dc.subjectModelsen_US
dc.subjectMatteren_US
dc.subjectScaleen_US
dc.subjectAgricultureen_US
dc.subjectNetherlandsen_US
dc.subjectCalibrationen_US
dc.subjectCarbonen_US
dc.subjectInfrared devicesen_US
dc.subjectLeast squares approximationsen_US
dc.subjectMean square erroren_US
dc.subjectMeteorological instrumentsen_US
dc.subjectNear infrared spectroscopyen_US
dc.subjectNeural networksen_US
dc.subjectOrganic carbonen_US
dc.subjectSocial networking (online)en_US
dc.subjectSoilsen_US
dc.subjectSpectrophotometersen_US
dc.subjectSpectroscopyen_US
dc.subjectMeasurement accuracyen_US
dc.subjectOn-line measurementen_US
dc.subjectPartial least square (PLS)en_US
dc.subjectPartial least squares regressions (PLSR)en_US
dc.subjectRoot mean square errorsen_US
dc.subjectVisible and near infrareden_US
dc.subjectVisible and near-infrared spectroscopyen_US
dc.subjectSoil surveysen_US
dc.subjectArtificial neural networken_US
dc.subjectCalibrationen_US
dc.subjectClay soilen_US
dc.subjectComparative studyen_US
dc.subjectConcentration (composition)en_US
dc.subjectLeast squares methoden_US
dc.subjectMappingen_US
dc.subjectMethodologyen_US
dc.subjectNear infrareden_US
dc.subjectpHen_US
dc.subjectSoil analysisen_US
dc.subjectSoil organic matteren_US
dc.subject.scopusSoil Color; Near-Infrared Spectroscopy; Hyperspectralen_US
dc.subject.wosSoil scienceen_US
dc.titleComparison between artificial neural network and partial least squares for on-line visible and near infrared spectroscopy measurement of soil organic carbon, pH and clay contenten_US
dc.typeArticle
dc.wos.quartileQ1en_US

Files

License bundle
Now showing 1 - 1 of 1
Name:
license.txt
Size:
1.71 KB
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections

Web of Science
Scopus