核桃叶片氮元素含量的光谱预测模型

doi:10.6048/j.issn.1001-4330.2023.03.008

新疆农业科学 ›› 2023, Vol. 60 ›› Issue (3): 582-589.DOI: 10.6048/j.issn.1001-4330.2023.03.008

核桃叶片氮元素含量的光谱预测模型

马文强¹(), 刘佳¹, 沈晓贺¹, 陈中原², 杨莉玲¹(), 张漫³()

1.新疆农业科学院农业机械化研究所,乌鲁木齐 830091
2.新疆维吾尔自治区产品质量监督检验研究院,乌鲁木齐 830011
3.中国农业大学现代精细农业系统集成研究教育部重点实验室, 北京 100083

收稿日期:2022-07-30 出版日期:2023-03-20 发布日期:2023-04-18
作者简介:马文强(1986-),新疆库车人,副研究员,博士,研究方向为林果智能化检测,(E-mail)mwq4530@163.com
基金资助:
自治区重点研发计划专项(2021B02004-4);新疆农业科学院科技创新重点培育专项(xjkcpy-004);自治区“人才引领林果业提质增效”试点工作项目

Prediction Model of Nitrogen Content in Walnut Leaves Based on Spectrum

MA Wenqiang¹(), LIU Jia¹, SHEN Xiaohe¹, CHEN Zhongyuan², YANG Liling¹(), ZHANG Man³()

1. Agricultural Mechanization Institute,Xinjiang Academy of Agricultural Sciences,Urumqi 830091, China
2. Research Institute of Xinjiang Product Quality Supervision and Inspection,Urumqi 830011, China
3. Key Laboratory of Modern Precision Agriculture System Integration Research, Ministry of Education, College of Information and Electrical Engineering, China Agricultural University, Beijing 100083, China

Received:2022-07-30 Published:2023-03-20 Online:2023-04-18
Supported by:
Major Scientific R & D Project of Xinjiang Uygur Autonomous Region(2021B02004-4);Key S & T Innovation Incubation Project of Xinjiang Academy of Agricultural Sciences(xjkcpy-004);Pilot Work Project of Xinjiang Uygur Autonomous Region "the Forestry and Fruit Industry to Improve the Quality and Efficiency of the Fruit Industry Led by Talents"

摘要/Abstract

摘要：

【目的】分析325~1 075 nm范围内核桃叶片光谱与叶片氮元素含量的相关性,研究核桃叶片光谱数据预处理和特征波段筛选方法,建立核桃叶片氮元素含量的预测模型,为实现核桃生产中的快速施肥提供参考。【方法】建立多元散射校正、Savitzky-Golay卷积平滑滤波和小波去噪的组合预处理方法;采用连续投影算法筛选出了特征波段;采用特征波段建立核桃叶片氮元素含量的偏最小二乘回归预测模型。【结果】建立的组合预处理方法对核桃叶片光谱去噪效果较好;采用特征波段建立的核桃叶片氮元素含量的预测模型,模型的验证集决定系数R²达到了0.875,均方根误差RMSE达到了0.697 3 mg/g。【结论】与全光谱数据相比,筛选出的特征波段降低了冗余数据和噪声的影响,提取出了有效成分相关的光谱信息,提高了建模质量。

关键词: 核桃; 光谱分析; 氮元素; 特征波段; 预测模型

Abstract:

【Objective】 This project aims to study the correlation between the walnut leaves spectrum of 325-1,075 nm and the content of nitrogen in walnut leaves and explore the walnut leaf spectral data pretreatment and characteristic band screening methods, and establish a prediction model for the nitrogen content of walnut leaves.In order to realize rapid fertilization guidance in walnut production.【Method】 First, a combined pretreatment method of multivariate scattering correction,Savitzky-Golay convolution smoothing filter and wavelet denoising were explored and established; then the feature bands were screened by the continuous projection algorithm; finally the predictive model of the nitrogen content in feature bands of walnut leaves were established by least squares regression.【Results】 The results showed that the established combined pretreatment method had a better denoising effect on walnut leaf spectrum; Using the predictive model of nitrogen content in walnut leaves established in feature bands, the model's validation set determination coefficient R² reached 0.875, and the root mean square error RMSEP reached to 0.697,3 mg/g.【Conclusion】 Compared with the full spectrum data, this established model reduces the influence of redundant data and noise, extracts the spectral information related to the effective components, and improves the quality of modeling.

Key words: walnut; spectral analysis; nitrogen; feature band; prediction model

中图分类号:

S664.1

马文强, 刘佳, 沈晓贺, 陈中原, 杨莉玲, 张漫. 核桃叶片氮元素含量的光谱预测模型[J]. 新疆农业科学, 2023, 60(3): 582-589.

MA Wenqiang, LIU Jia, SHEN Xiaohe, CHEN Zhongyuan, YANG Liling, ZHANG Man. Prediction Model of Nitrogen Content in Walnut Leaves Based on Spectrum[J]. Xinjiang Agricultural Sciences, 2023, 60(3): 582-589.

图/表 10

图1 核桃叶片位置示意

Fig.1 Position of walnut leaves

图2 核桃叶片光谱曲线

Fig.2 Walnut leaf spectrum curve

表1 原始光谱与MSC预处理光谱氮元素含量预测建模比较

Tab.1 Comparison of predictive modeling of nitrogen content between original Spectra and MSC pretreatment spectra

预处理方法 Pretreatment method	PLSR 主成分数 Number of principal components of PLSR	校正集 Calibration set		验证集 Validation set
预处理方法 Pretreatment method	PLSR 主成分数 Number of principal components of PLSR	均方根误差 RMES (mg/g)	决定系数 R²	均方根误差 RMSE (mg/g)	决定系数 R²
未处理 None	5	0.644 8	0.842 4	2.796 4	0.596 0
多元散射校正 MSC	5	0.616 8	0.870 3	1.411 5	0.721 4

图3 MSC预处理后的核桃叶片光谱曲线

Fig.3 Spectral curve of walnut leaves after MSC pretreatment

表2 不同光谱预处理方法氮元素含量预测建模比较

Tab.2 Comparison of prediction modeling of nitrogen content in different spectral pretreatment methods

预处理方法 Pretreatment method	PLSR 主成分数 Number of principal components of PLSR	校正集 Calibration set		验证集 Validation set
预处理方法 Pretreatment method	PLSR 主成分数 Number of principal components of PLSR	均方根误差 RMES (mg/g)	决定系数 R²	均方根误差 RMSE (mg/g)	决定系数 R²
标准正态化 SNV	5	0.617 7	0.870 8	1.443	0.723 3
一阶微分 FD	5	0.221 4	0.946 6	3.633 5	0.404 5
二阶微分 SD	5	0.332	0.930 5	3.982 1	0.386 1
卷积平滑滤波 Savitzky- Golay S-G	5	0.609 7	0.880 1	1.246	0.756 8

图4 db小波去噪处理的核桃叶片光谱曲线

Fig.4 Spectral curve of walnut leaves processed by db wavelet denoising

表3 不同分解层数小波去噪预处理光谱的氮元素含量预测建模比较

Tab.3 Comparison of predictive modeling of nitrogen content based on wavelet denoising pretreatment spectra with different decomposition layers

分解层数 Decompo sition layers	PLSR 主成分数 Number of principal components of PLSR	校正集 Calibration set		验证集 Validation set
分解层数 Decompo sition layers	PLSR 主成分数 Number of principal components of PLSR	均方根误差 RMES (mg/g)	决定系数 R²	均方根误差 RMSE (mg/g)	决定系数 R²
1	5	0.595	0.893	1.127	0.771 4
2	5	0.632 1	0.862 4	1.471	0.728
3	5	0.880 3	0.791 2	2.492 7	0.632 3
4	5	0.896 4	0.796 5	2.653	0.646 6

图5 参与建模变量数目下模型均方根误差变化

Fig.5 The Influence of the Number of Variables Participating in Modeling on the Root Mean Square Error of the Model

图6 筛选出的特征波段点位置分布

Fig.6 Location distribution of selected feature band points

图7 特征波段的PLSR模型氮元素含量预测结果

Fig.7 Prediction results of nitrogen content in PLSR model based on feature wavebands

参考文献 29

[1]	Dedeoglu M, Basayigit L. Determining the Zn content of cherry in field using VNIR spectroscopy[J]. Spectroscopy and Spectral Analysis, 2015, 35(2):355-361. PMID
[2]	Kasim N, Sawut R, Abliz A. Estimation of the relative chlorophyll content in spring wheat based on an optimized spectral index[J]. Photogrammetric Engineering and Remote Sensing, 2015, 84(12):801-811. DOI URL
[3]	Chen F Y, Zhou X, Chen Y Y, et al. Estimating biochemical component contents of diverse plant leaves with different kernel based support vector regression models and VNIR spectroscopy[J]. Spectroscopy and Spectral Analysis, 2019, 39(2):428-434.
[4]	李园, 王振锡, 刘玉霞, 等. 不同时期香梨叶片铁元素含量高光谱估算模型[J]. 西南农业学报, 2019, 32(1):161-168.
	LI Yuan, WANG Zhenxi, LIU Yuxia, et al. Hyperspectral estimation model of foliar Fe concentration of Pyrus brestschneideri Rehd.in different periods[J]. Southwest China Journal of Agricultural Sciences, 2019, 32(1):161-168.
[5]	孙红, 陈香, 孙梓淳, 等. 基于透射光谱的玉米叶片含水率快速检测仪研究[J]. 农业机械学报, 2018, 49(3):173-178.
	SUN Hong, CHEN Xiang, SUN Zichun, et al. Rapid detection of moisture content in maize leaves based on transmission spectrum[J]. Transactions of the Chinese Society for Agricultural Machinery, 2017, 49(3): 173-178.
[6]	钟穗希, 李子波, 唐荣年. 基于PCA-Kmeans聚类法的橡胶树叶片氮含量的近红外高光谱诊断模型研究[J]. 海南大学学报(自然科学版), 2020, 38(3) :260-269.
	ZHONG Suixi, LI Zibo, TANG Rongnian. Near infrared hyperspectral diagnostic model for nitrogen content of rubber tree leaves based on PCA kmeans clustering spectrum[J]. Natural Science Journal of Hainan University, 2020, 38(3) :260-269.
[7]	杨红云, 周琼, 杨珺, 等. 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. DOI
	YANG Hongyun, ZHOU Qiong, YANG Jun, et al. Study on nitrogen nutrition diagnosis of rice leaves based on hyperspectrum[J]. Acta Agriculturae Zhejiangensis, 2019, 31(10):1575-1582. DOI
[8]	石吉勇, 李文亭, 胡雪桃, 等. 基于叶绿素叶面分布特征的黄瓜氮镁元素亏缺快速诊断[J]. 农业工程学报, 2019, 35(13):170-176.
	SHI Jiyong, LI Wenting, HU Xuetao, et al. Diagnosis of nitrogen and magnesium deficiencies based on chlorophyll distribution features of cucumber leaf[J]. Transactions of the Chinese Society of Agricultural Engineering, 2019, 35(13):170-176.
[9]	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 Xiaoxiang, WANG Fangdong, ZHAO Xiaomin, et al. The estimation models of rice leaf nitrogen concentration based on canopy spectrum and BP neural network[J]. Chinese Journal of Agricultural Resources and Regional Planning, 2019, 40(3):35-44.
[10]	庄红梅, 王强, 韩宏, 等. 芜菁营养生长期叶片光谱特性及对氮的敏感性[J]. 新疆农业科学, 2018, 55(3):477-489. DOI
	ZHUANG Hongmei, WANG Qiang, HAN Hong, et al. Leaf spectral characteristics and its sensitivity to N in different vegetative growth stages of turnips[J]. Xinjiang Agricultural Sciences, 2018, 55(3):477-489. DOI
[11]	张瑶. 基于光谱技术的农林环境关键参数信息获取研究[D]. 北京: 中国农业大学, 2017.
	ZHANG Yao. Measurement of key parameters in agriculture and fruit farming based on spectroscopy[D]. Beijing: China Agricultural University, 2017.
[12]	翟丽婷, 魏峰远, 冯海宽, 等. 不同水分处理下冬小麦叶片光谱特征及氮素垂直分布情况分析[J]. 中国农业信息, 2019, 31(2):39-54.
	ZHAI Liting, WEI Fengyuan, FENG Haikuan, et al. Analysis of spectral characteristics and vertical distribution of nitrogen in winter wheat under different water treatments[J]. China Agricultural Informatics, 2019, 31(2):39-54.
[13]	Jiang J, Zhu J, Wang X, et al. Estimating the leaf nitrogen content with a new feature extracted from the ultra-high spectral and spatial sesolution smages in wheat[J]. Remote Sensing, 2021, 13(4): 739-739. DOI URL
[14]	Yang B, Ma J, Yao X, et al. Estimation of leaf nitrogen content in wheat based on fusion of spectral features and deep features from near infrared hyperspectral imagery[J]. Sensors (Basel, Switzerland), 2021, 21(2): 6133. DOI URL
[15]	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. DOI
	LI Ying, XUE Lihong, PAN Fuyan, et al. Effects of interaction of N and P on rice canopy spectral reflectance and its PNN identification[J]. Seientia Agricultura Sinica, 2014, 47(14):2742-2750.
[16]	Wang J J, Li Z K, Jin X L, et al. Phenotyping flag leaf nitrogen content in rice using a three-band spectral index[J]. Computers and Electronics in Agriculture, 2019, (162):475-481.
[17]	李俊霞, 杨俐苹, 白由路, 等. 不同品种玉米氮含量与叶片光谱反射率及SPAD值的相关性[J]. 中国土壤与肥料, 2015,(3):34-39.
	LI Junxia, YANG Liping, BAI Youlu, et al. The correlation of total nitrogen content with leaf spectral reflectance and SPAD values in different maize varieties[J]. Soil and Fertilizer Sciences in China, 2015,(3):34-39.
[18]	Cláudio K J, Eduardo F C, Alaine M G, et al. Regression modeling nitrogen fertilization requirement for maize crop by combining spectral reflectance and agronomic efficiency[J]. Journal of Plant Nutrition, 2020, 43(14):2152-2163. DOI URL
[19]	Xu X B, Zhu H C, Li Z H, et al. A nitrogen spectral response model and nitrogen estimation of summer maize during the entire growth period[J]. International Journal of Remote Sensing, 2020, 41(5):1867-1883. DOI URL
[20]	胡珍珠, 潘存德, 肖冰, 等. 基于光谱特征参量的核桃叶片氮素含量估测模型[J]. 农业工程学报, 2015, 31(9):180-186.
	HU Zhenzhu, PAN Cunde, XIAO Bing, et al. Spectral characteristic parameter-based models for foliar nitrogen concentration estimation of Juglans regia[J]. Transactions of the Chinese Society of Agricultural Engineering, 2015, 31(9):180-186
[21]	丁雅, 王振锡, 瞿余红, 等. 枣叶片N素质量分数高光谱估算模型[J]. 东北林业大学学报, 2018, 46(11):45-50.
	DING Ya, WANG Zhenxi, QU Yuhong, et al. Hyperspectral estimation model for nitrogen content of jujube leaves[J]. Journal of Northeast Forestry University, 2018, 46(11):45-50.
[22]	胡珍珠, 潘存德, 王世伟, 等. 轮台白杏叶片氮磷钾含量光谱估算模型[J]. 新疆农业科学, 2013, 50(2):238-248.
	HU Zhenzhu, PAN Cunde, WANG Shiwei, et al. Models for estimating foliar NPK content of armeniaca vulgaris ‘Luntaibaixing’ using spectral reflectance[J]. Xinjiang Agricultural Sciences, 2013, 50(2):238-248.
[23]	Elvanidi A, Katsoulas N, Augoustaki D, et al. Crop reflectance measurements for nitrogen deficiency detection in a soilless tomato crop[J]. Biosystems Engineering, 2018,(176):1-11.
[24]	朱咏莉, 李萍萍, 毛罕平, 等. 生菜叶片光谱红边参数对氮营养的响应特征分析[J]. 农业机械学报, 2011, 42(11):174-177.
	ZHU Yongli, LI Pingping, MAO Hanping, et al. Response features of red edge parameters for lettuce leaf spectra under different nitrogen levels[J]. Transactions of The Chinese Society for Agricultural Machinery, 2011, 42(11):174-177.
[25]	乔星星, 冯美臣, 杨武德, 等. SG平滑处理对冬小麦地上干生物量光谱监测的影响[J]. 山西农业科学, 2016, 44(10):1450-1454.
	QIAO Xingxing, FENG Meichen, YANG Wude, et al. Effect of SG smoothing processing on predicting the above ground dry biomass of winter wheat[J]. Journal of Shanxi Agricultural Sciences, 2016, 44(10): 1450-1454.
[26]	刘桂松, 郭昊淞, 潘涛, 等. Vis-NIR光谱模式识别结合SG平滑用于转基因甘蔗育种筛查[J]. 光谱学与光谱分析, 2014, 34(10):2701-2706. PMID
	LIU Guisong, GUO Haosong, PAN Tao, et al. Vis-nir spectroscopic pattern recognition combined with SG smoothing applied to breed screening of transgenic sugarcane[J]. Spectroscopy and Spectral Analysis, 2014, 34(10):2701-2706. PMID
[27]	杨玮, 李民赞, 孙红, 等. 温室黄瓜叶片近红外图像消噪算法与含氮量快速检测[J]. 农业机械学报, 2013, 44(7):216-221.
	YANG Wei, LI Minzan, SUN Hong, et al. Denoising algorithm of multispectral images and nonlinear estimation ofnitrogen content of cucumber leaves in greenhouse[J]. Transactions of The Chinese Society for Agricultural Machinery, 2013, 44(7):216-221.
[28]	M. Araújo, T. Saldanha, R. Galvao, et al. The successive projections algorithm for variable selection in spectroscopic multicomponent analysis[J]. Chemometrics and Intelligent Laboratory Systems, 2001, 57(2):65-73. DOI URL
[29]	高洪智, 卢启鹏, 丁海泉, 等. 基于连续投影算法的土壤总氮近红外特征波长的选取[J]. 光谱学与光谱分析, 2009, 29(11):2951-2954. PMID
	GAO Hongzhi, LU Qipeng, DING Haiquan, et al. Choice of characteristic near-infrared wavelengths for soil total nitrogen based on successive projection algorithm[J]. Spectroscopy and Spectral Analysis, 2009, 29(11):2951-2954. PMID

编辑推荐 0

Metrics

阅读次数

全文

HTML			PDF

最新录用	在线预览	正式出版	最新录用	在线预览	正式出版
0	0	9	0	0	38

来源	本网站	其他网站

次数	31	16
比例	66%	34%

摘要

332

最新录用	在线预览	正式出版

0	0	332

来源	本网站	其他网站

次数	121	211
比例	36%	64%

核桃叶片氮元素含量的光谱预测模型

Prediction Model of Nitrogen Content in Walnut Leaves Based on Spectrum

在线阅读

PDF下载

可视化

摘要/Abstract

引用本文

使用本文

图/表 10

参考文献 29

相关文章 15

编辑推荐 0

Metrics

[1]	帕孜丽耶·艾合麦提, 王新勇, 周燕, 宋彬, 玉苏甫·阿不力提甫. 微生物菌剂对核桃叶片生理及光合特性的影响[J]. 新疆农业科学, 2024, 61(9): 2299-2306.
[2]	李汝勇, 任久明, 雷霆, 王克林, 刘鹏程, 李江涛. 基于光合法和生物量法分析塔里木沙漠公路防护林带碳汇估算差异性[J]. 新疆农业科学, 2024, 61(8): 2014-2022.
[3]	亚森·吐尔迪, 马天宇, 图尔迪麦麦提·努尔麦麦提, 阿地力·沙塔尔. 苹果蠹蛾和梨小食心虫迷向丝在核桃园中的使用模式[J]. 新疆农业科学, 2024, 61(7): 1757-1765.
[4]	周光辉, 陈凤, 孙守霞, 吕威, 朴涵琪, 郝金莲, 张述斌, 陈虹. 水肥耦合对核桃光合特性及产量和品质的效应[J]. 新疆农业科学, 2024, 61(5): 1151-1159.
[5]	刘钧庆, 梁国成, 张欣, 王庆勇, 赵经华. 调亏灌溉对滴灌核桃树根系空间分布特征的影响[J]. 新疆农业科学, 2024, 61(5): 1160-1171.
[6]	马合木提·阿不来提, 木合塔尔·扎热, 米热古力·外力, 哈地尔·依沙克. 核桃叶缘焦枯病与其养分含量的相关性回归分析[J]. 新疆农业科学, 2024, 61(4): 945-953.
[7]	王文窈, 施万斌, 芦屹, 图尔荪托合提·阿卜杜拉, 叶尔胜·哈尔肯, 马荣. 两种助剂在核桃腐烂病化学防控中的减药增效分析[J]. 新疆农业科学, 2024, 61(3): 672-680.
[8]	欧源, 罗莎莎, 王如月, 孙雅丽, 虎海防. 盐胁迫对美国黑核桃幼苗生长和生理特性的影响[J]. 新疆农业科学, 2024, 61(2): 393-401.
[9]	叶晓琴, 曹小艳, 阿地力·沙塔尔. 苹果蠹蛾生物学特性及其幼虫对核桃果实的为害习性[J]. 新疆农业科学, 2024, 61(2): 434-440.
[10]	文霞, 郭发城, 高桂珍. 集团外猎物种类及猎物密度对七星瓢虫集团内捕食作用的影响[J]. 新疆农业科学, 2024, 61(2): 441-447.
[11]	李慧, 毕莹, 王新宇, 雷雅馨, 张琪, 黄帅, 热扎·库忘德克, 王静. 核桃青皮多酚调控对哈密瓜采后活性氧代谢水平及腐烂率的影响[J]. 新疆农业科学, 2024, 61(12): 2966-2975.
[12]	赵莎莎, 王世伟, 张翠芳, 郝洪龙, 郭桐, 杨先安, 杨雯洁. 核桃焦叶病与矿质元素关系分析[J]. 新疆农业科学, 2024, 61(11): 2750-2760.
[13]	王苹, 孔娜, 潘俨, 孙席平, 徐斌, 张婷. ClO₂熏蒸处理对湿鲜核桃贮藏效果的影响[J]. 新疆农业科学, 2023, 60(8): 1940-1949.
[14]	郑贺云, 姚军, 李超, 张翠环, 耿新丽. 不同贮藏温度对甜瓜品质的影响及预测模型建立[J]. 新疆农业科学, 2023, 60(8): 1950-1957.
[15]	徐静, 石书兵, 秦小钢, 朱军. 核桃林间作西红花对其土壤微生物数量的动态变化[J]. 新疆农业科学, 2023, 60(8): 2022-2027.