|
|||||
|
|
| 基于遗传神经网络混合模型预测马尾松毛虫发生量的研究 | |
| 引用本文： | 陈绘画,朱寿燕,周泽华.基于遗传神经网络混合模型预测马尾松毛虫发生量的研究[J].安徽农业科学,2009,37(12):5548-5551. |
| 作者姓名： | 陈绘画 朱寿燕 周泽华 |
| 作者单位： | 1. 浙江省仙居县林业局,浙江仙居,317300 2. 浙江省仙居县气象局,浙江仙居,317300 3. 浙江省仙居县农业局,浙江仙居,317300 |
| 基金项目： | 仙居县科技局《仙居县林业主要有害生物数值预报的研究》(200628) |
| 摘 要： | 根据相关系数法、均生函数法及逐步回归法分别选取与马尾松毛虫有虫面积、虫口密度、虫株率相关关系密切的气象因子和延拓均生函数序列作为各预测模型的输入特征，分别建立马尾松毛虫有虫面积、虫口密度、虫株率与气象因子的GA-BP混合模型。结果表明，所建立的各GA-BP混合预测模型，具有令人满意的拟合精度和预测精度。当隐含层神经元个数为13个，预报因子数为6个时，3组预留有虫面积的平均预测误差为4．41％；虫口密度GA-BP混合模型的隐层神经元个数为9个，预报因子数为4个时，3组预留样本的平均预测误差为2．17％；虫株率GA-BP混合模型的隐层神经元个数为9个，预报因子数为4个时，3组预留样本的平均预测误差为4．25％。 |
| 关 键 词： | 马尾松毛虫 遗传神经网络 发生量 预测预报 GA-BP混合模型 |
Study on Forecasting the Occurrence Amount of Dendrolimus punctatus Walker Based on Genetic Neural Network Mixed Model |
|
| CHEN Hui-hua et al.Study on Forecasting the Occurrence Amount of Dendrolimus punctatus Walker Based on Genetic Neural Network Mixed Model[J].Journal of Anhui Agricultural Sciences,2009,37(12):5548-5551. | |
| Authors: | CHEN Hui-hua |
| Institution: | CHEN Hui-hua et al(Forestry Bureau of Xianju County in Zhejiang Province,Xianju,Zhejiang 317300) |
| Abstract: | According to correlation coefficient,mean-generating function and stepwise regression methods,meteorological factors corresponding to the area of infested wood,the population density and the attacking rate of Dendrolimus punctatus Walker,and continuation-mean-generating function sequence were selected as the imported characters to establish the GA-BP mixed models.Results showed that the established GA-BP mixed models had satisfactory fitting accuracy and forecasting precision.Under the condition of the numb... |
| Keywords: | Dendrolimus punctatus Walker Genetic neural network Occurrence Quantity Prediction GA-BP mix mode |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ | |