Several studies have focused on comparisons between Support Vector Regression (SVR)and Artificial Neural Networks (ANNs). However, few have involved domains with massivelylarge data sets. This research led to a methodology for reducing the number of SVR trainingpatterns without a need to pre-process the data set. Using this methodology SVR modelswere created for air temperature prediction from one to twelve hours ahead. These modelswere more accurate than ANN models that were trained on data sets of 300,000 patterns andcompetitive with ANN models that were trained on 1.25 million patterns. A fuzzy expertsystem was also developed which incorporates the knowledge of local agrometeorologists inorder to assess the risk of frost. Wind speed, as well as ANN models of air temperatureand dew point temperature, enabled the expert system to make frost predictions from oneto twelve hours ahead. This tool will be made available to Georgia farmers through a webbasedinterface that was created for The University of Georgias Automated EnvironmentalMonitoring Network website (http://www.georgiaweather.net).