Support Vector Machine and Artificial Neural Network Models for the Classification of Grapevine Varieties Using a Portable NIR Spectrophotometer

Abstract

The identification of different grapevine varieties, currently attended using visual ampelometry, DNA analysis and very recently, by hyperspectral analysis under laboratory conditions, is an issue of great importance in the wine industry. This work presents support vector machine and artificial neural network’s modelling for grapevine varietal classification from in-field leaf spectroscopy. Modelling was attempted at two scales: site-specific and a global scale. Spectral measurements were obtained on the near-infrared (NIR) spectral range between 1600 to 2400 nm under field conditions in a non-destructive way using a portable spectrophotometer. For the site specific approach, spectra were collected from the adaxial side of 400 individual leaves of 20 grapevine (Vitis vinifera L.) varieties one week after veraison. For the global model, two additional sets of spectra were collected one week before harvest from two different vineyards in another vintage, each one consisting on 48 measurement from individual leaves of six varieties. Several combinations of spectra scatter correction and smoothing filtering were studied. For the training of the models, support vector machines and artificial neural networks were employed using the pre-processed spectra as input and the varieties as the classes of the models. The results from the pre-processing study showed that there was no influence whether using scatter correction or not. Also, a second-degree derivative with a window size of 5 Savitzky-Golay filtering yielded the highest outcomes. For the site-specific model, with 20 classes, the best results from the classifiers thrown an overall score of 87.25% of correctly classified samples. These results were compared under the same conditions with a model trained using partial least squares discriminant analysis, which showed a worse performance in every case. For the global model, a 6-class dataset involving samples from three different vineyards, two years and leaves monitored at post-veraison and harvest was also built up, reaching a 77.08% of correctly classified samples. The outcomes obtained demonstrate the capability of using a reliable method for fast, in-field, non-destructive grapevine varietal classification that could be very useful in viticulture and wine industry, either global or site-specific.

Automated plant identification using artificial neural network and support vector machine

“…The ANN model had a higher AUC value than the SVM model; and with additional comparison of AUC, we found that performance of the ANN model is slightly better than the SVM model. These results are consistent with the study of Gutiérrez et al (2015) where the ANN model performed slightly better than the SVM model in identifying grapevine varieties. This can be taken as an indication that these models can be utilized for these kinds of tasks.…”

Data Mining and NIR Spectroscopy in Viticulture: Applications for Plant Phenotyping under Field Conditions

“…Only very recently, grapevine varietal classification has been attempted by hyperspectral imaging [ 24 ] and an NIR portable spectrophotometer [ 43 ]. In [ 24 ], hyperspectral imaging in the range between 280 nm and 1028 nm was used along with PLS for the classification of 300 leaves from three different varieties (Tempranillo, Grenache and Cabernet Sauvignon), under laboratory conditions.…”

“…The outcomes reached in the present work, even when a large number of varieties was selected for the training, highlights the accuracy shown by data mining techniques for the same goal, particularly when the spectra were collected in the field and in a non-destructive way, different from [ 24 ], where a hyperspectral camera was used indoors under controlled illumination conditions. In [ 43 ], the authors used a portable NIR spectrophotometer of the same range as the one in this work for the acquisition of leaves’ spectra. Artificial neural networks (ANNs) and sequential minimal optimization for the training of SVMs were tested as classification algorithms for the development of two grapevine discrimination models for two different approaches: a site-specific model for 20 varieties (yielding 87.25% of correctly classified samples, using ANNs) and a global model using six varieties from different vineyards and seasons (obtaining 77.08%, again with ANNs).…”

Comparative quantification of chlorophyll and polyphenol levels in grapevine leaves sampled from different geographical locations

“…Grapevine varietal and clone identification were successfully tested using the hyperspectral image of a leaf measured in reflectance mode and proper classifications around 95% were obtained in both cases 11,12 . In the same context, Gutierrez et al (2015) used a portable NIR instrument for in-field grapevine varieties discrimination using the leaves spectra 13 . A total of 20 different grapevine varieties were included in this study and around 85% of correct predictions were obtained.…”