A new grape yield prediction tool will be created using advanced modeling methods, including machine learning, in combination with large pre-existing vineyard and weather data sets. The premise is that the independent factors that affect yields are well known, but the ways in which they interact overall to determine yields are not well understood. The reason for the knowledge gap is that modeling interactions among multiple variables requires advanced statistical methods not previously utilized in grape yield prediction tools.
Yields are influenced by weather up to 18 months prior to harvest and by crop load and vegetative growth of the previous season. As a result, yields vary substantially from year-to-year because of compounding weather effects, with costly unpredictability. The general ways in which weather affects individual components of yield, such as the initiation of inflorescences and flowering, are known. However, a model incorporating the multiple factors affecting yield does not exist.
This project will use machine learning to create an accurate and easy to use yield prediction tool for use by Australian grape growers.
For more information on the project contact email@example.com