Evaluation of geostatistical method and hybrid artificial neural network with imperialist competitive algorithm for predicting distribution pattern of Tetranychus urticae (Acari: Tetranychidae) in cucumber field of Behbahan, Iran

Abstract

In this study, the statistical methods and artificial neural network (ANN) were used to estimate the spatial distribution of Tetranychus urticae in cucumber field of Behbahan, Iran. Pest density assessments were performed following a 10 × 10 m 2 grid pattern on the field and a total of 100 sampling units on field. In both methods latitude and longitude information were used as input data and output of each methods showed number of pest. In Geostatistics methods ordinary kriging, and ANN with imperialist competitive algorithm were evaluated. Comparison of ANN and geostatistical showed that ANN capability is more than ordinary kriging method so that the ANN predicts distribution of this pest dispersion with 0.98 coefficient of determination and 0.0038 mean squares errors lower than the Geostatistical methods. In general, it can be concluded that the ANN with imperialist competitive algorithm approach with combining latitude and longitude can forecast pest density with sufficient accuracy. Our map showed that patchy pest distribution offers large potential for using site-specific pest control on this field.