基于Stacking集成卷积神经网络的水稻氮素营养诊断  

Rice nitrogen nutrition diagnosis based on stacking integrated convolutional neural network

作　　者：杨红云[1,2] 郭紫微 郭高飞 黄进龙 钱政 张林朋 刘娇娇 YANG Hong-yun;GUO Zi-wei;GUO Gao-fei;HUANG Jin-long;QIAN Zheng;ZHANG Lin-peng;LIU Jiao-jiao(School of Software,Jiangxi Agricultural University,Nanchang,Jiangxi 330045,China;Key Laboratory of Agricultural Information Technology of Colleges and Universities in Jiangxi Province,Nanchang,Jiangxi 330045,China;School of Computer and Information Engineering,Jiangxi Agricultural University,Nanchang,Jiangxi 330045,China;Technology Center of China Tobacco Anhui Industrial Co.,Ltd.,Hefei,Anhui 230088,China;Jiangxi General Technical Engineering School,Yongxiu,Jiangxi 330306,China;Liu'an Branch of Anhui Provincial Tobacco Company,Liu'an,Anhui 237010)

机构地区：[1]江西农业大学软件学院,江西南昌330045 [2]江西省高等学校农业信息技术重点实验室,江西南昌330045 [3]江西农业大学计算机与信息工程学院,江西南昌330045 [4]安徽中烟工业有限责任公司技术中心,安徽合肥230088 [5]江西省通用技术工程学校,江西永修330306 [6]安徽省烟草公司六安市公司,安徽六安237010

出　　处：《植物营养与肥料学报》2023年第3期573-581,共9页Journal of Plant Nutrition and Fertilizers

基　　金：国家自然科学基金项目(62162030,61562039)。

摘　　要：【目的】为实现水稻氮素营养状况的快速、准确诊断,提出了基于集成卷积神经网络的水稻氮素营养诊断模型,为建立高性能的氮素营养诊断模型提供思路和方法。【方法】水稻田间试验以超级杂交水稻‘两优培九’为材料,设置4个施氮水平(0、210、300、390 kg/hm^(2))。扫描获取水稻幼穗分化期顶部3片完全展开叶的叶片图像,将图像裁剪至只包含叶尖片段的图像,进行水稻叶片图像数据采集。分别以单一卷积神经网络模型DenseNet121、ResNet50、InceptionResNet V2为基学习器,多层感知机(MLP)为元学习器,集成卷积神经网络模型,比较了集成模型与单一卷积神经网络模型以及不同基学习器组成的集成模型的氮素营养诊断结果。【结果】4个单一模型中,DenseNet121的氮素诊断准确率最高,为96.41%。二元集成模型和三元集成模型的准确率均高于任意一个单一模型的准确率,由3个基学习器组成的集成模型的准确率最高,达到98.10%,相比准确率最高的单一模型准确率提高了1.69个百分点。【结论】采用DenseNet、ResNet50、InceptionResNet V2集成的卷积神经网络建立的氮素营养诊断模型,具有很强的泛化能力和学习能力,能够准确识别氮素营养状况。【Objectives】To achieve rapid and accurate diagnosis of rice nitrogen nutrition status,we established a rice nitrogen nutrition diagnosis model involving stacking integrated convolution neural networks.【Methods】In a rice field experiment,a super hybrid rice cultivar“Liangyoupeijiu”was used as the test material,and four N application levels(0,210,300,390 kg/hm^(2))were the treatments.At the young panicle differentiation stage of rice,the images of the top three fully unfolded leaves were taken by scanning,and the images were cut into images containing leaf tip parts,and the rice leaf image dataset was established after preprocessing.A stacking integrated convolutional neural network model with different four combinations of three base learners(i.e.,DenseNet121,ResNet50,InceptionResNet V2)and MLP as the meta learner was constructed.The results of the integrated models on nitrogen nutrition diagnosis task were compared with that of the single convolutional neural network model of different single base learners(i.e.,DenseNet121,ResNet50,InceptionResNet V2,and VGG16).【Results】Among the four single models,DenseNet121 had the highest accuracy of 96.41%.The accuracy rate of the binary integration model and the ternary integration model were higher than that of the single model.The accuracy rate of the stacking integration model was the highest,reaching 98.10%,with an increase of 1.69 percentage points compared with the single model which had the highest accuracy.【Conclusions】The nitrogen nutrition diagnosis model established by stacking integrated convolution neural network has strong generalization ability and learning ability,and can accurately identify nitrogen nutrition status.

关 键 词：水稻 氮素营养诊断 单一卷积神经网络 集成模型 

分 类 号：S511[农业科学—作物学] TP183[自动化与计算机技术—控制理论与控制工程] TP391.41[自动化与计算机技术—控制科学与工程]