基于BP神经网络的柑橘农药残留预测  

Prediction of pesticide residues in citrus using BP neural network

作　　者：周佳俊 龚道新[1,2] 蒋紫烟 梁佳豪 赵佳[1,2] 苏龙 廖婵娟[1,2] ZHOU Jiajun;GONG Daoxin;JIANG Ziyan;LIANG Jiahao;ZHAO Jia;SU Long;LIAO Chanjuan(College of Resources&Environment,Hunan Agricultural University,Changsha,Hunan 410128,China;Institute of Agricultural Environmental Protection,Hunan Agricultural University,Changsha,Hunan 410128,China)

机构地区：[1]湖南农业大学资源环境学院,湖南长沙410128 [2]湖南农业大学农业环境保护研究所,湖南长沙410128

出　　处：《湖南农业大学学报（自然科学版）》2022年第5期572-577,共6页Journal of Hunan Agricultural University(Natural Sciences)

基　　金：湖南省教育厅重点项目(21A0129)。

摘　　要：基于BP神经网络算法,采用主成分分析法得到农药相对分子质量、气温、降水量、pH、CEC、有机质、施药浓度、采收间隔期是影响农药残留量的主要因素,并将其作为输入变量,初步构建柑橘农药残留预测模型。结果表明:经160组样本数据模型训练和测试,预测相对误差为0.92%~18.93%,平均为7.42%,绝对误差为0.001~0.153 mg/kg;BP神经网络预测模型的决定系数为0.96205。可见,面对复杂的自然环境及柑橘种质性状,基于BP神经网络的柑橘农药残留预测系统对柑橘上多种农药的残留显示出较高的预测精度,说明将机器学习算法用于柑橘的农药残留检测是可行的。By use of the BP neural network algorithm,the principal component analysis method was used to obtain the main factors affecting the pesticide residues including the relative molecular weight of pesticides,temperature,precipitation,pH,CEC,organic matter,application concentration and harvest interval.These factors were then used as input variables to preliminarily build the pesticide residue prediction model.The relative error of prediction was 0.92%-18.93%,the average relative error was 7.42%,and the absolute error was 0.001-0.153 mg/kg,and the coefficient of determination of BP neural network prediction model was 0.96205.It can be seen that in the face of complex natural environment and citrus germplasm characteristics,the pesticide residue prediction system on citrus based on BP neural network showed a high prediction accuracy for the residues of various pesticides on citrus,indicating that it was feasible to apply machine learning algorithm to pesticide residues detection on citrus.

关 键 词：柑橘 农药残留 BP神经网络 主成分分析 预测模型 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程] TS255.7[自动化与计算机技术—控制科学与工程]