基于BP神经网络的色板蚜虫诱捕量预测

Number forecast of trapping aphides by colorful plate based on BP neural network

检验水溶性黏着剂色板的蚜虫发生量预测预报潜能,了解其田间蚜虫诱捕量的影响因素。利用羧甲基纤维素钠和甘油为主要原料配制的水溶性胶黏着剂制作了3种颜色粘板,在露天菜地同一处地点进行了不同糖醋混合液含量、不同添加物有机硫估值以及水溶胶与机油2种黏着剂粘板的田间蚜虫诱捕测试。将测试结果作为BP神经网络模型的训练样本与预测样本进行建模分析。结果表明,黏合剂的极性、颜色、添加的引诱剂3个因素对蚜总科害虫田间诱捕量的影响权重较大,模型对预测样本的预测值与实际观测值基本吻合;黄色大型粘板诱捕蚜虫效果好,利用水溶胶粘板可以对田间蚜虫发生进行调查和预测预报。

The aim was to test the probability of aphid number forecast by colorful plate with water-soluble adhesive and to clarify the factors which influenced the aphid number entrapped on field. Three color sticky plates were made out by water- soluble adhesive prepared with carboxymethylcellulose sodium and glycerine as main raw materials, and the field experiment of trapping aphides was carried out in one place of a vegetable garden by the deferent adhesives that were with different mixes of sugar, vinegar and wine, different estimations of organic sulfur added and different polarity. Finally the data of this experiment as the training samples and the forecasting samples were analyzed using BP neural network model. The results showed that the three factors which were polarity of adhesive, color and the attrahent added had more weight than the other two factors to the number of entrapped aphides on the field, and the forecast results of model were consistent with the actual results perfectly. The bigger yellow sticky plates had the best effect of trapping aphides, and the plates with water-soluble adhesive could be used in investigating and forecasting aphides on field.