Forecasting different phenological phases of apple using artificial neural network

Abstract

Apple is one of the oldest trees in the world, which is widely cultivated because of its high compatibility with different climatic conditions. In this study, we applied phenological statistics of agricultural meteorology data of Golmakan to anticipate different phenologic phases in apple using Intelligent Neural Network. At first, the matrix of input data which is consisting of climatic parameters such as minimum temperature, maximum temperature, the mean of daily temperature, absolute minimum temperature, and absolute maximum temperature were established. The range of temperature changes, growing degree days and chill unit (in silver tip phase) had been prepared for different phenological stages during 1999-2005. The matrix of collected data was worked out which, in fact, were the occurrence dates of different phenological stages was prepared and the modeling of different phenological stages in apple by using neural network. The accuracy of model was examined by using RMSE index and by contrasting real and anticipation dates during two years. For this purpose observed climatic and phenological data was also used in similar figure at investigating zone. The phenological stages of apple could be anticipated with acceptable accuracy using climatic parameters.