Abstract
The performance of a support vector regression (SVR) model with a Gaussian radial basis kernel to predict anthocyanin concentration, pH index and sugar content in whole grape berries, using spectroscopic measurements obtained in reflectance mode, was evaluated. Each sample contained a small number of whole berries and the spectrum of each sample was collected during ripening using hyperspectral imaging in the range of 380–1028 nm. Touriga Franca (TF) variety samples were collected for the 2012–2015 vintages, and Touriga Nacional (TN) and Tinta Barroca (TB) variety samples were collected for the 2013 vintage. These TF vintages were independently used to train, validate and test the SVR methodology; different combinations of TF vintages were used to train and test each model to assess the performance differences under wider and more variable datasets; the varieties that were not employed in the model training and validation (TB and TN) were used to test the generalization ability of the SVR approach. Each case was tested using an external independent set (with data not included in the model training or validation steps). The best R2 results obtained with varieties and vintages not employed in the model’s training step were 0.89, 0.81 and 0.90, with RMSE values of 35.6 mg·L−1, 0.25 and 3.19 °Brix, for anthocyanin concentration, pH index and sugar content, respectively. The present results indicate a good overall performance for all cases, improving the state-of-the-art results for external test sets, and suggesting that a robust model, with a generalization capacity over different varieties and harvest years may be obtainable without further training, which makes this a very competitive approach when compared to the models from other authors, since it makes the problem significantly simpler and more cost-effective.
Highlights
As increases in computational power and processing capability continue, the introduction of new technologies into the most diverse industry segments is expanding, viticulture and the whole wine industry being no exception
For each dataset the training and validation were conducted with 10-fold cross-validation for the Touriga Franca (TF) 2012 samples, and with five-fold cross-validation for the remaining vintages
A hyperspectral imaging technique was combined with a machine learning algorithm to compose a framework capable of estimating oenological parameters with different varieties and vintages of wine grape berries
Summary
As increases in computational power and processing capability continue, the introduction of new technologies into the most diverse industry segments is expanding, viticulture and the whole wine industry being no exception. With producers and companies demanding cheaper and faster ways to produce higher-quality wine from their vineyards, together with the massive increases in information available to the market, the search for a competitive advantage is increasing. One such advantage can be found in the development of new methodologies to reduce the cost of gathering information about grapes in an environmentally-friendly and timely manner, allowing winemakers to obtain more frequent insights into their wine grapes, to enable harvesting them at the optimal point of maturity and selecting them according to certain quality features. A possible reason for the extensive use of that range, in addition to the good results obtained, may be related to the fact that equipment operating at larger wavelengths tends to be significantly more expensive
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
