Modeling fluctuation of Pyricularia grisea spore population as affected by meteorological factors in Guilan province (Iran) using artificial neural network

Rice blast, caused by Pyricularia grisea, is one of the most important diseases of this crop in Iran and all over the world. To evaluate the relationship between spore population (SP) and meteorological factors, SP was measured daily using spore trap during growing seasons of 2006-2008 in Rasht and Lahijan regions (Guilan province, Iran). Weather data including precipitation, daily maximum and minimum temperatures, daily maximum and minimum relative humidity and duration of sunny hours were obtained from weather stations which were five kilometers away from the fields. The relationship between spore population and metrological factors was evaluated by Neurosolution 5.0 software. Weather data and spore population were considered as input and output data, respectively. In this study, multilayer perceptron neural network, regression model and Log(x + 1) transformation were performed. To evaluate the model efficiency, correlation coefficient and mean square error were used. The results showed that the correlation coefficient (r) and mean square error (MSE) parameters were 0.55 and 0.03 in Rasht and 0.1 and 0.03 in Lahijan, respectively. The results also showed the potential of this model for modeling SP using meteorological factors; however more data is needed for validation of this model. There has been no previous report on modeling the relationship between SP and meteorological data using artificial neural network in Guilan province (Iran).