基于高光谱的水稻叶片氮素营养诊断研究

doi:10.3969/j.issn.1004-1524.2019.10.01

浙江农业学报 ›› 2019, Vol. 31 ›› Issue (10): 1575-1582.DOI: 10.3969/j.issn.1004-1524.2019.10.01

基于高光谱的水稻叶片氮素营养诊断研究

杨红云^1,2, 周琼^2,3, 杨珺^1,*, 孙玉婷^2,3, 路艳^2,3, 殷华^1,2

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

收稿日期:2019-05-13 出版日期:2019-10-25 发布日期:2019-10-30
通讯作者: *,杨珺,E-mail: 392856021@qq.com
作者简介:杨红云(1975—),男,江西新干人,硕士,副教授,研究方向为机器学习与农业信息技术。E-mail:nc_yhy@163.com
基金资助:
国家自然科学基金(61562039); 江西省教育厅科技项目(GJJ160374,GJJ170279,GJJ150425)

Study on nitrogen nutrition diagnosis of rice leaves based on hyperspectrum

YANG Hongyun^1,2, ZHOU Qiong^2,3, YANG Jun^1,*, SUN Yuting^2,3, LU Yan^2,3, YIN Hua^1,2

1.School of Software Engineering, Jiangxi Agricultural University, Nanchang 330045, China;
2.Key Laboratory of Agricultural Information Technology of Colleges and Universities in Jiangxi Province, Nanchang 330045, China;
3.School of Computer and Information Engineering, Jiangxi Agricultural University, Nanchang 330045, China

Received:2019-05-13 Online:2019-10-25 Published:2019-10-30

摘要/Abstract

摘要： 为快速、准确地实现水稻氮素营养诊断,以中嘉早17水稻为试验对象,设置4种施氮水平的水稻栽培试验,利用便携式地物波谱仪获取240组水稻分蘖期顶三叶在350~2 500 nm的光谱数据。随机将样本划分为训练集(160个样本)和测试集(80个样本)。首先,通过多元散射校正(MSC)、变量标准化校正(SNV)、平滑算法(SG)3种方法分别对原始光谱进行预处理;然后,采用主成分分析(PCA)和连续投影算法(SPA)对预处理后的光谱进行特征降维,选取累积贡献率超过99.98%的前24个主成分作为模型的输入变量,对于经过MSC、SNV和SG处理后的光谱数据,还分别筛选出12、15、19个特征波长;最后,应用支持向量机(SVM)基于上述处理分别建立水稻氮素营养诊断模型。结果表明,采用MSC-PCA-SVM模型进行水稻氮素营养诊断的识别准确率最高,其在训练集和预测集上的准确率分别达99.38%和97.50%。

关键词: 水稻叶片, 氮素营养诊断, 高光谱, 主成分分析, 连续投影算法, 支持向量机

Abstract: In order to realize rice nitrogen nutrition diagnosis quickly and accurately, rice cultivation experiments with 4 nitrogen application levels were conducted on Zhongjiazao 17 rice cultivar. A total of 240 rice spectral data were collected at tillering stage within 350 to 2 500 nm from top trilobate by using portable earth mass spectrometry. All the samples were randomly divided into training set (160 samples) and prediction set (80 samples). The original spectrum was pretreated by multiplicative scatter correction (MSC), standard normal variate (SNV) and Savitzky-Golay smoothing (SG) methods, respectively. Then, principal component analysis (PCA) and successive projection algorithm (SPA) were used for feature reduction and feature selection of the pre-processed spectra. After principal component analysis, the first 24 principal components, of which the accumulative contribution exceeded 99.98%, were used as the input variables of the model, and 12, 15 and 19 characteristic wavelengths were selected for the spectrum after MSC, SNV and SG treatments, respectively. Finally, rice nitrogen nutrition diagnosis models were established with support vector machine (SVM). It was shown that the MSC-PCA-SVM model was the best method for rice nitrogen nutrition diagnosis, of which the accuracy rate on training set and prediction set was 99.38% and 97.50%, respectively.

Key words: rice leaf, nitrogen nutrition diagnosis, hyperspectrum, principal component analysis, successive projection algorithm, support vector machine

中图分类号:

S127

杨红云, 周琼, 杨珺, 孙玉婷, 路艳, 殷华. 基于高光谱的水稻叶片氮素营养诊断研究[J]. 浙江农业学报, 2019, 31(10): 1575-1582.

YANG Hongyun, ZHOU Qiong, YANG Jun, SUN Yuting, LU Yan, YIN Hua. Study on nitrogen nutrition diagnosis of rice leaves based on hyperspectrum[J]. , 2019, 31(10): 1575-1582.

参考文献

[1] 朱德峰, 张玉屏, 陈惠哲, 等. 中国水稻高产栽培技术创新与实践[J]. 中国农业科学, 2015, 48(17): 3404-3414.
ZHU D F, ZHANG Y P, CHEN H Z, et al.Innovation and practice of high-yield rice cultivation technology in China[J]. Scientia Agricultura Sinica, 2015, 48(17): 3404-3414.(in Chinese with English abstract)
[2] 徐艳玲. 氮肥对水稻生长的影响[J]. 现代农业科技, 2014(19): 27.
XU Y L.Effect of nitrogen fertilizer on rice growth[J]. Modern Agricultural Science and Technology, 2014(19): 27.(in Chinese)
[3] 李金文. 基于水稻叶片生理生态学特征的氮营养诊断[D]. 杭州: 浙江大学, 2010.
LI J W.The diagnosis of rice N status based on leaf physioecological characteristics[D]. Hangzhou: Zhejiang University, 2010.(in Chinese with English abstract)
[4] 孙棋. 基于数字图像处理技术的水稻氮素营养诊断研究[D]. 杭州: 浙江大学, 2008.
SUN Q.Rice nitrogen nutrition diagnosis based on digital image processing technique[D]. Hangzhou: Zhejiang University, 2008.(in Chinese with English abstract)
[5] 李岚涛, 张萌, 任涛, 等. 应用数字图像技术进行水稻氮素营养诊断[J]. 植物营养与肥料学报, 2015, 21(1): 259-268.
LI L T, ZHANG M, REN T, et al.Diagnosis of N nutrition of rice using digital image processing technique[J]. Journal of Plant Nutrition and Fertilizer, 2015, 21(1): 259-268.(in Chinese with English abstract)
[6] 王远, 王德建, 张刚, 等. 基于数码相机的水稻冠层图像分割及氮素营养诊断[J]. 农业工程学报, 2012, 28(17): 131-136.
WANG Y, WANG D J, ZHANG G, et al.Digital camera-based image segmentation of rice canopy and diagnosis of nitrogen nutrition[J]. Transactions of the CSAE, 2012, 28(17): 131-136.(in Chinese with English abstract)
[7] 刘江桓. 基于机器视觉技术的水稻营养快速诊断研究[D]. 南昌: 江西农业大学, 2011.
LIU J H.Research of paddy rice nutrition rapid diagnosis based on computer vision technology[D]. Nanchang: Jiangxi Agricultural University, 2011.(in Chinese with English abstract)
[8] 邵华, 石庆华, 郭熙, 等. 基于冠层高光谱的南方丘陵地区晚稻氮素营养诊断[J]. 江西农业大学学报, 2015, 37(6): 975-981.
SHAO H, SHI Q H, GUO X, et al.Diagnosis of nitrogen nutrition of late rice based on canopy hyper-spectrum in hilly areas of Jiangxi Province[J]. Acta Agriculturae Universitatis Jiangxiensis, 2015, 37(6): 975-981.(in Chinese with English abstract)
[9] 祝锦霞, 邓劲松, 石媛媛, 等. 基于水稻扫描叶片图像特征的氮素营养诊断研究[J]. 光谱学与光谱分析, 2009, 29(8): 2171-2175.
ZHU J X, DENG J S, SHI Y Y, et al.Diagnoses of rice nitrogen status based on characteristics of scanning leaf[J]. Spectroscopy and Spectral Analysis, 2009, 29(8): 2171-2175.(in Chinese with English abstract)
[10] 祝锦霞, 陈祝炉, 石媛媛, 等. 基于无人机和地面数字影像的水稻氮素营养诊断研究[J]. 浙江大学学报(农业与生命科学版), 2010, 36(1): 78-83.
ZHU J X, CHEN Z L, SHI Y Y, et al.Diagnoses of rice nitrogen status based on spectral characteristics of leaf and canopy[J]. Journal of Zhejiang University(Agriculture and Life Sciences), 2010, 36(1): 78-83.(in Chinese with English abstract)
[11] 陈利苏. 基于机器视觉技术的水稻氮磷钾营养识别和诊断[D]. 杭州: 浙江大学, 2014.
CHEN L S.Rice nutrition identification and diagnosis based on machine vision technology[D]. Hangzhou: Zhejiang University, 2014.(in Chinese with English abstract)
[12] 王树文, 赵越, 王丽凤, 等. 基于高光谱的寒地水稻叶片氮素含量预测[J]. 农业工程学报, 2016, 32(20): 187-194.
WANG S W, ZHAO Y, WANG L F, et al.Prediction for nitrogen content of rice leaves in cold region based on hyperspectrum[J]. Transactions of the CSAE, 2016, 32(20): 187-194.(in Chinese with English abstract)
[13] YUAN Y, CHEN L, LI M, et al.Diagnosis of nitrogen nutrition of rice based on image processing of visible light[C]//2016 IEEE International Conference on Functional-Structural Plant Growth Modeling, Simulation, Visualization and Applications (FSPMA), November 7-11, 2016. New York, USA: IEEE, 2016.
[14] 孙小香, 王芳东, 赵小敏, 等. 基于冠层光谱和BP神经网络的水稻叶片氮素浓度估算模型[J]. 中国农业资源与区划, 2019, 40(3): 35-44.
SUN X X, WANG F D, ZHAO X M, et al.The estimation models of rice leaf nitrogen concentration based on canopy spectrum and BP neural network[J]. Journal of China Agricultural Resources and Regional Planning, 2019, 40(3): 35-44.(in Chinese with English abstract)
[15] 张晶, 张珏, 田海清. 基于高光谱成像技术的甜菜叶片氮素遥感估测[J]. 中山大学学报(自然科学版), 2018, 57(6): 103-112.
ZHANG J, ZHANG J, TIAN H Q.Remote sensing estimation research of leaf nitrogen in sugar beet based on hyperspectral imaging[J]. Acta Scientiarum Naturalium Universitatis Sunyatseni, 2018, 57(6): 103-112.(in Chinese with English abstract)
[16] 白丽敏, 李粉玲, 常庆瑞, 等. 结合SPA和PLS法提高冬小麦冠层全氮高光谱估算的精确度[J]. 植物营养与肥料学报, 2018, 24(5): 1178-1184.
BAI L M, LI F L, CHANG Q R, et al.Increasing accuracy of hyper-spectral remote sensing for total nitrogen of winter wheat canopy by use of SPA and PLS methods[J]. Journal of Plant Nutrition and Fertilizers, 2018, 24(5): 1178-1184.(in Chinese with English abstract)
[17] 单贵莲, 初晓辉, 陈功, 等. 多花黑麦草氮素营养及生长状况的高光谱监测[J]. 中国草地学报, 2017, 39(1): 50-55.
SHAN G L, CHU X H, CHEN G, et al.Hyperspectral monitoring on nitrogen nutrition and growth condition of annual ryegrass[J]. Chinese Journal of Grassland, 2017, 39(1): 50-55.(in Chinese with English abstract)
[18] 张国圣, 许童羽, 于丰华, 等. 基于高光谱的水稻叶片氮素估测与反演模型[J]. 浙江农业学报, 2017, 29(5): 845-849.
ZHANG G S, XU T Y, YU F H, et al.Nitrogen content inversion of rice leaf based on the hyperspectral data[J]. Acta Agriculturae Zhejiangensis, 2017, 29(5): 845-849.(in Chinese with English abstract)
[19] 李颖, 薛利红, 潘复燕, 等. 氮磷互作对水稻冠层光谱的影响及其PNN识别[J]. 中国农业科学, 2014, 47(14): 2742-2750.
LI Y, XUE L H, PAN F Y, et al.Effects of interaction of N and P on rice canopy spectral reflectance and its PNN identification[J]. Scientia Agricultura Sinica, 2014, 47(14): 2742-2750.(in Chinese with English abstract)
[20] 黄志鸿. 基于近红外、中红外和拉曼光谱法甲醇柴油品质检测研究[D]. 南昌: 华东交通大学, 2016.
HUANG Z H.Research on detection of methanol diesel quality based on near-infrared, mid-infrared and Raman spectroscopy[D]. Nanchang: East China Jiaotong University, 2016.(in Chinese with English abstract)
[21] 蔡红, 陈荣耀. 基于PCA-BP神经网络的股票价格预测研究[J]. 计算机仿真, 2011, 28(3): 365-368.
CAI H, CHEN R Y.Stock price prediction based on PCA and BP neural network[J]. Computer Simulation, 2011, 28(3): 365-368.(in Chinese with English abstract)
[22] 李勋兰, 易时来, 何绍兰, 等. 高光谱成像技术的柚类品种鉴别研究[J]. 光谱学与光谱分析, 2015, 35(9): 2639-2643.
LI X L, YI S L, HE S L, et al.Identification of pummelo cultivars based on hyperspectral imaging technology[J]. Spectroscopy and Spectral Analysis, 2015, 35(9): 2639-2643.(in Chinese with English abstract)
[23] LV J, DENG F L, YAN Z G. Using PROSEPCT and SVM for the estimation of chlorophyll concentration[J]. Advanced Materials Research, 2014, 989/990/991/992/993/994: 2184-2187.
[24] 顾清, 邓劲松, 陆超, 等. 基于光谱和形状特征的水稻扫描叶片氮素营养诊断[J]. 农业机械学报, 2012, 43(8): 170-174.
GU Q, DENG J S, LU C, et al.Diagnosis of rice nitrogen nutrition based on spectral and shape characteristics of scanning leaves[J]. Transactions of the Chinese Society for Agricultural Machinery, 2012, 43(8): 170-174.(in Chinese with English abstract)

基于高光谱的水稻叶片氮素营养诊断研究

Study on nitrogen nutrition diagnosis of rice leaves based on hyperspectrum

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	崔鹏飞, 魏灵珠, 程建徽, 向江, 李明山, 吴江, . 不同砧木对天工翠玉葡萄生长和果实品质的影响[J]. 浙江农业学报, 2021, 33(1): 52-61.
[2]	卢牧原, 刘源, 刘桂建. 基于组合模型的黑土区土壤有机质含量预测分析[J]. 浙江农业学报, 2020, 32(8): 1427-1436.
[3]	钱家炜, 刘晓青, 张静静, 周卫红, 李建龙. 张家港市农田土壤重金属含量高光谱遥感监测模型构建[J]. 浙江农业学报, 2020, 32(8): 1437-1445.
[4]	陆锡昆, 罗亚辉, 蒋蘋, 胡文武. 基于高光谱的油茶籽含水量检测方法[J]. 浙江农业学报, 2020, 32(7): 1302-1310.
[5]	张宇, 张继, 荣涛, 欧克纬, 黄国弟, 宋红霞. 杧果品种亲缘关系的CDDP分析[J]. 浙江农业学报, 2020, 32(5): 824-830.
[6]	沈迪, 陈龙正, 路晓华, 陶建平, 冯顾城, 刘洁霞, 冯凯, 尹莲, 丁旭, 贾丽丽, 徐志胜, 刘惠吉, 熊爱生. 苏南地区29个秋冬茬芹菜品种资源评价[J]. 浙江农业学报, 2020, 32(4): 653-660.
[7]	禹文杰, 王彩霞, 乔芦, 王松磊, 贺晓光. 基于高光谱成像技术的泾源黄牛肉色度PLSR预测模型构建[J]. 浙江农业学报, 2020, 32(3): 527-533.
[8]	张红涛, 李艺嘉, 谭联, 许帅涛. 基于CS-SVM的谷子叶片病害图像识别[J]. 浙江农业学报, 2020, 32(2): 274-282.
[9]	王念一, 于丰华, 许童羽, 杜文, 郭忠辉, 张国圣. 基于机器学习的粳稻叶片叶绿素含量高光谱反演建模[J]. 浙江农业学报, 2020, 32(2): 359-366.
[10]	杨红云, 罗建军, 孙爱珍, 万颖, 易文龙. 基于图像特征的水稻叶片全氮含量估测模型研究[J]. 浙江农业学报, 2020, 32(12): 2232-2243.
[11]	宋春雨, 甘淑, 袁希平, 胡琳, 李雁, 闫馨方. 滇中典型乔木植被高光谱特征[J]. 浙江农业学报, 2020, 32(11): 1978-1986.
[12]	方向, 金秀, 朱娟娟, 李绍稳. 基于可见-近红外光谱预处理建模的土壤速效氮含量预测[J]. 浙江农业学报, 2019, 31(9): 1523-1530.
[13]	闫晶秋子, 李钢铁, 刘玉军, 麻云霞, 杨颖. 基于主成分分析及隶属函数法的巨菌草幼苗耐盐碱性评价[J]. 浙江农业学报, 2019, 31(9): 1531-1540.
[14]	孟庆龙, 张艳, 尚静. 基于高光谱成像的猕猴桃表面疤痕无损识别[J]. 浙江农业学报, 2019, 31(8): 1372-1378.
[15]	曹玥华, 魏灵珠, 沈碧薇, 程建徽, 向江, 吴江. 砧木对新郁葡萄生长和果实品质的影响[J]. 浙江农业学报, 2019, 31(6): 908-914.