تعیین الگوی توزیع جمعیت علفهرز خارشتر Alhagi pseudalhagi (M.B) Desv. با استفاده از شبکه عصبی مصنوعی چندی ساز بردار یادگیر (LVQ۴ )

Abstract

Mapping of weeds distribution patterns for using in site-specific weed management has been favored by researchers. In this study, a learning vector quantization neural network (LVQ4) model was developed to predict and classify the spatial distribution patterns of Alhagi pseudalhagi. This method was evaluated on data of weed density counted at 550 points of a fallow field located in Faculty of Agriculture, Shahrood University of Technology, Semnan, Iran, in 2010. Some statistical tests, such as comparisions of the means, variance, statistical distribution as well as coefficient of determination in linear regression were used between the observed point sample data and the estimated weed seedling density surfaces to evaluate the performance of the pattern recognition method. Results showed that in training LVQ4, test and total phase P-value was greater than 0.7, 0.2 and 1.000 percent respectively, indicating that there was no significant (p<0.05) difference between statsitcal parameters such as average, variance, statistical distribution and also coefficient of determination in the observed and the estimated weed seedling density. This results suggest that LVQ4 neural network can learn weed density model very well. In addition, results indicated that trained LVQ4 neural network has a high capability in predicting weed density with recognition accuracy less than 0.9 percent at unsampled points. The technique showed that the LVQ4 could classify and map A. pseudalhagi spatial variability on the field. Our map showed that patchy weed distribution offers large potential for using site-specific weed control on this field.