prediction of spatial distribution pattern of hordeum glaucum steud. population using neural network model

abstract recent interest in describing the spatial distribution patterns of weeds through using interpolation methods has increased to estimate weed seedling density from spatially refferenced data and evaluation of applicable to site-specific weed management. in this research, a multi layer perceptron neural network (mlpnn) model was developed to predict the spatial distribution of h. glaucum density, with respect to its ability to interpolate and map weed seedling densities. this method was evaluated on data of h. glaucum density in a saffron field in southern khorasan. 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 interpolation method. results showed that in training mlpnn, test and total phase p- value was greater than 0.49, 0.18 and 0.27 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 mlp neural network can learn weed density model very well. in addition results indicated that trained mlp neural network has a high capability in predicting weed density at unsampled points. the technique showed that the mlpnn could interpolate and map spatial h. glaucum density variability. patchy weed distribution offers large potential for using site-specific weed control on this field.