Abstract
The high quality of Port wine is the result of a sequence of winemaking operations, such as harvesting, maceration, fermentation, extraction and aging. These stages require proper monitoring and control, in order to consistently achieve the desired wine properties. The present work focuses on the harvesting stage, where the sugar content of grapes plays a key role as one of the critical maturity parameters. Our approach makes use of hyperspectral imaging technology to rapidly extract information from wine grape berries; the collected spectra are fed to machine learning algorithms that produce estimates of the sugar level. A consistent predictive capability is important for establishing the harvest date, as well as to select the best grapes to produce specific high-quality wines. We compared four different machine learning methods (including deep learning), assessing their generalization capacity for different vintages and varieties not included in the training process. Ridge regression, partial least squares, neural networks and convolutional neural networks were the methods considered to conduct this comparison. The results show that the estimated models can successfully predict the sugar content from hyperspectral data, with the convolutional neural network outperforming the other methods.
Highlights
We aimed to evaluate and compare the prediction performance of RR, PLS, neural networks (NN) and 1D Convolutional neural networks (CNN) models using the independent test set created with different vintages of Touriga Franca (TF)
We propose an approach that lays the groundwork for the development of an on-the-fly non-invasive sensing methodology for predicting and monitoring the key enological parameters of Port wine grape berries that are essential for their ripeness assessment
These results reveal that the proposed 1D CNN architecture can be successfully applied to estimate sugar content of wine grape berries, achieving a better performance rate when compared with the other three methods of ridge regression, partial least squares and neural networks
Summary
Produced from grapes of excellent quality that grow in the Douro region, Port wine is known for its renowned quality, being one of the most famous Portuguese fortified wines worldwide. We consider one well-known representative of Port wines, the. Dow’s Port wine (from Symington Family Estates, the industrial partner collaborating with the present research project). This wine is mainly produced from grape varieties harvested in the vineyard of Quinta do Bomfim, often consisting of Tawny Ports, twenty, thirty and forty-year-old wine, aged in oak cask. It is important to keep in mind, that the high quality of these wines starts at the vineyards, where it is crucial to monitor the components and properties of the grapes that will be used as raw material for the winemaking process
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
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.
