Abstract:

Chinese fir is the most important fast-growing and high-yield tree species in southern China, it occupies a very significant position in Chinese plantation management. However, the rate of sterile seeds of Chinese fir is high, for example in Fujian Province, which seriously affects the production and development of Chinese fir. So it is an urgent problem to study the prediction and prevention of sterile seeds in the production of Chinese fir seeds. For the sake of revealing the epidemic law of sterile seeds, this paper studied the relationships between Chinese fir sterile seeds and geographic epidemic by a new method-artificial neural network.Artificial neural network is a good method in handling the overall nonlinear mapping problems between input variables and output ones, which has a wide application in many research fields such as system simulating, automation controlling, paralled data processing and so on. In this paper, the authors selected BP artificial neural network to deal with the relationships between Chinese fir sterile seeds and geographic epidemic, where the input variables are longitude and latitude, the output variable is rate of sterile seeds of Chinese fir, the number of neurons of hidelevel (M) is M=2L+1 according to document (L is the number of factors of input-level), and the network activity function is Sigmiod function as follows: F (x) =1/ (1+e^-x). Using the built BP network, the samples were trained until =min, where O_nj and Y_nj are output values of network and real values of rate of Chinese fir sterile seeds respectively, N is the number of trained samples, and E_j is sum of square deviation of BP network. If E_j didn't converge, the weights and thresholds of BP network were adjusted as follows: The results showed that the accuracy of BP model in simulating the epidemic rate of Chinese fir sterile seeds in different countries is high, which is 88.40%. Thereforce, this paper not only provided a basis for establishing Chinese fir seeds orchard rationally, but also opened up a new train of thought in the application of artificial neural network to forestry research.

Key words: Chinese fir, Sterile seed, Geographic epidemic, BP network