Comparative analysis of learning and meta-learning algorithms for creating models for predicting the probable alcohol level during the ripening of grape berries

• Published in: Computers and electronics in agriculture 2012, Vol.80, p.54-62
• Main Authors: Fernandez Martinez, Roberto, Lostado Lorza, Ruben, Fernandez Ceniceros, Julio, Martinez-de-Pison Ascacibar, F. Javier
• Format: Article
• Language: English
• Subjects: Agronomy. Soil science and plant productions; Alcohols; Algorithms; Bagging algorithm; Berries; Biological and medical sciences; climate; decision support systems; Design engineering; experts; Feature selection; Fundamental and applied biological sciences. Psychology; Grape sugar concentration; Grapes; Learning; Learning and meta-learning algorithms; Mathematical analysis; Mathematical models; meteorological parameters; prediction; Probable alcohol level; ripening; sugars; vines; vineyards; wines
• ISSN: 0168-1699; 1872-7107
• DOI: 10.1016/j.compag.2011.10.009

The changes occurring in the dynamics of sugar concentration in grape berries are fairly significant during maturation, whereby they are commonly used as a marker of their development. In view of the importance this parameter has for wine producers, this paper designs several models for predicting the must’s probable alcohol level using both meteorological variables and those specific to the vineyard. Presentation is made of a comparative analysis of learning and meta-learning algorithms for the selection of variables and the design of useful predictive models for estimating this level. The models are designed according to data gathered at different locations within the Rioja Qualified Designation of Origin (DOC Rioja, Spain) under different climate conditions, as well as involving different grape varieties. The models designed in this study provide very good results, and following their validation by experts, they have been proven to make a major contribution to decision-making in vine growing. Finally, considering the indices of analysis studied, it has been observed that the ensemble-type model based on the Bagging algorithm with REPTree decision trees records the best results, with a root mean squared error (RMSE) of 8.1% and a correlation of 84.9%.