Data Mining Techniques for Modelling the Influence of Daily Extreme Weather Conditions on Grapevine, Wine Quality and Perennial Crop Yield

摘要

The influences of daily weather extremes, such as maximum/ minimum temperatures, humidity, and precipitation, are observable in perennial crop phenology that in turn determines the annual crop yield in quality and quantity. In viticulture, grapevine phenology determines the quality of vintage produced from the grapes apart from the best effects by winemaker. Following a brief review of current literature in this research domain, the paper describes a data mining approach being developed to data association modelling to depict dependency relationships between daily weather extremes, grapevine phenology and yield indicators using data from a vineyard in northern New Zealand and daily weather extremes logged at a nearby meteorology station. An artificial neural network algorithm was used to classify the data associations and the chi-square test was used to establish the degree of dependence between the related variable values. The initial results of the approach to daily maximum weather conditions show potential.