SUNScholar will be down for routine maintenance from 2018-12-11 10:00 SAST.

ITEM VIEW

Modelling water stress in a Shiraz Vineyard using hyperspectral imaging and machine learning

dc.contributor.authorLoggenberg, Kyleen_ZA
dc.contributor.authorStrever, Alberten_ZA
dc.contributor.authorGreyling, Bernoen_ZA
dc.contributor.authorPoona, Niteshen_ZA
dc.date.accessioned2018-01-31T09:50:41Z
dc.date.available2018-01-31T09:50:41Z
dc.date.issued2018
dc.identifier.citationLoggenberg, K., et al. 2018. Modelling water stress in a Shiraz Vineyard using hyperspectral imaging and machine learning. Remote Sensing, 10(2):202, doi:10.3390/rs10020202
dc.identifier.issn2072-4292 (online)
dc.identifier.otherdoi:10.3390/rs10020202
dc.identifier.urihttp://hdl.handle.net/10019.1/103097
dc.descriptionCITATION: Loggenberg, K., et al. 2018. Modelling water stress in a Shiraz Vineyard using hyperspectral imaging and machine learning. Remote Sensing, 10(2):202, doi:10.3390/rs10020202.
dc.descriptionThe original publication is available at http://www.mdpi.com
dc.descriptionPublication of this article was funded by the Stellenbosch University Open Access Fund.
dc.description.abstractThe detection of water stress in vineyards plays an integral role in the sustainability of high-quality grapes and prevention of devastating crop loses. Hyperspectral remote sensing technologies combined with machine learning provides a practical means for modelling vineyard water stress. In this study, we applied two ensemble learners, i.e., random forest (RF) and extreme gradient boosting (XGBoost), for discriminating stressed and non-stressed Shiraz vines using terrestrial hyperspectral imaging. Additionally, we evaluated the utility of a spectral subset of wavebands, derived using RF mean decrease accuracy (MDA) and XGBoost gain. Our results show that both ensemble learners can effectively analyse the hyperspectral data. When using all wavebands (p = 176), RF produced a test accuracy of 83.3% (KHAT (kappa analysis) = 0.67), and XGBoost a test accuracy of 80.0% (KHAT = 0.6). Using the subset of wavebands (p = 18) produced slight increases in accuracy ranging from 1.7% to 5.5% for both RF and XGBoost. We further investigated the effect of smoothing the spectral data using the Savitzky-Golay filter. The results indicated that the Savitzky-Golay filter reduced model accuracies (ranging from 0.7% to 3.3%). The results demonstrate the feasibility of terrestrial hyperspectral imagery and machine learning to create a semi-automated framework for vineyard water stress modelling.en_ZA
dc.description.urihttp://www.mdpi.com/2072-4292/10/2/202
dc.format.extent14 pages : illustrations
dc.language.isoen_ZAen_ZA
dc.publisherMDPI
dc.subjectHyperspectral imaging -- Remote sensingen_ZA
dc.subjectGeology -- Remote sensingen_ZA
dc.subjectNatural resources -- Remote sensingen_ZA
dc.subjectImage processing -- Digital technologyen_ZA
dc.subjectComputer science -- Remote sensingen_ZA
dc.subjectShiraz Vineyard -- Irrigation -- Agricultureen_ZA
dc.titleModelling water stress in a Shiraz Vineyard using hyperspectral imaging and machine learningen_ZA
dc.typeArticleen_ZA
dc.description.versionPublisher's version
dc.rights.holderAuthors retain copyright


Files in this item

Thumbnail
Thumbnail

This item appears in the following Collection(s)

ITEM VIEW