To develop an intuitive smartphone-based decision support tool to inform berry volume and predict an optimal harvest window according to preferred wine style, for large-scale vineyard management.
The project will build on experience gained through project CSU 1501 ‘Developing a phone-based imaging tool to inform on fruit volume and potential optimal harvest time for optimal grape harvesting’. The tool uses machine learning methods to assess fruit volume in red and white varieties, based on images captured using a smartphone. In addition, the relationship between colour evolution and flavour development is used to assist in determining a grape harvesting window appropriate to desired wine styles.
The utility of the existing app will be expanded to facilitate the management of multiple sites or blocks. This will include the ability to monitor and record data specific to varieties and multiple locations (vineyards and blocks/parcels), improved machine learning analytics and imaging methods that are specific to different cultivars, and GPS tagging and time stamping of individual vine images.
The second phase of the project is the development of a decision support tool (to be called ‘SmartWine’) to allow the large-scale capture, storage and analysis of data from the app and other instruments or measurements (e.g. spectrophotometers, images, Brix), to improve the accuracy of fruit volume estimates and the identification of an optimal harvest window. The collected data, including vineyard practices, are intended to provide a tool for decision making in later years, as the database accumulated from multiple vineyard sites grows.
‘SmartWine’ will assist in making accurate harvesting date predictions and recommendations to grapegrowers and winemakers.