Novel Optimization Methods for Wine Processing

We are developing an optimization method for wine processing based on historical winery data and artificial neural networks (ANNs). This method will allow winemakers to fully use the information collected in their wineries over the years in order to produce a final product which has the qualities that they desire, even as grape characteristics vary from year to year. To date, we have established that ANNs can be used successfully to correlate wine processing inputs with chemical and sensory properties of the finished wine. In particular, we have been able to predict primary and malolactic fermentation kinetics based solely on grape characteristics and intended processing. This result will likely have application to prediction of sluggish and stuck fermentations. In addition, we have been able to predict how the color of Cabernet Sauvignon wines that we have made are a function of the processing completed. Increasing fermentation temperature and enzyme addition were found to increase color intensity, while increasing skin contact time (extended maceration) was found to decrease color intensity. We are currently conducting more experiments to clarify these relationships, and thereby maximize color extraction. Using chemical and sensory data from Sauvignon Blanc wines made in our winery, a sample optimization has demonstrated that the method developed predicts different optimal processing conditions for different “target” wines given grapes at a fixed maturity level. We are now in the process of extending this optimization method to actual winery data.