|本期目录/Table of Contents|

[1]胡鹏飞,唐荣年,胡文锋,等.基于近红外光谱与双权重竞争特征搜索策略的橡胶树叶片氮素检测[J].江苏农业科学,2024,52(18):222-231.
 Hu Pengfei,et al.Detection of nitrogen content in hevea rubber leaves based on near infrared spectroscopy and double weight feature search strategy[J].Jiangsu Agricultural Sciences,2024,52(18):222-231.
点击复制

基于近红外光谱与双权重竞争特征搜索策略的橡胶树叶片氮素检测(PDF)
分享到:

《江苏农业科学》[ISSN:1002-1302/CN:32-1214/S]

卷:
第52卷
期数:
2024年第18期
页码:
222-231
栏目:
农业工程与信息技术
出版日期:
2024-09-20

文章信息/Info

Title:
Detection of nitrogen content in hevea rubber leaves based on near infrared spectroscopy and double weight feature search strategy
作者:
胡鹏飞唐荣年胡文锋李创
海南大学机电工程学院,海南海口 570228
Author(s):
Hu Pengfeiet al
关键词:
近红外光谱橡胶树机器学习光谱波段选择叶片氮含量DWCARS
Keywords:
-
分类号:
S127
DOI:
-
文献标志码:
A
摘要:
本研究旨在解决传统近红外光谱分析在橡胶树叶片氮含量(LNC)检测中模型精度和稳定性的局限。通过对180张橡胶树叶片进行定量分析,提出了一种改进的重加权采样算法,即双权重竞争性自适应重加权采样(DWCARS)。该方法综合运用回归系数和变量投影重要性(VIP)2种权重评价标准,并通过竞争性机制优化特征选择。比较分析结果表明,与传统CARS和差分进化(DE)等方法相比,DWCARS能够提取出更少且预测精度更高的波长变量。在测试集上,DWCARS模型展现了显著性能优势,其决定系数(R2P)为0.936 7,均方根误差(RMSEP)为 0.121 5,相比于CARS算法建立的预测模型RMSEP值降低了21.66%。表明DWCARS算法在提高橡胶树叶片氮含量检测的准确性和稳定性方面表现卓越,适用于精确监测橡胶树生长阶段的氮素状况。
Abstract:
-

参考文献/References:

[1] Warren-Thomas E,Dolman P M,Edwards D P.Increasing demand for natural rubber necessitates a robust sustainability initiative to mitigate impacts on tropical biodiversity[J]. Conservation Letters,2015,8(4):230-241.
[2]黎舟,杨思林,刘云根,等. 基于微分变换的湿地植物高光谱全氮反演[J]. 环境科学研究,2022,35(5):1268-1276.
[3]Ali M M,Al-Ani A,Eamus D,et al. Leaf nitrogen determination using non-destructive techniques:a review[J]. Journal of Plant Nutrition,2017,40(7):928-953.
[4]冯镇,刘馨,张震,等. 基于近红外光谱技术对小麦中毒死蜱农药残留测定方法的研究[J]. 食品工业科技,2022,43(4):271-277.
[5]Li Y J,Sun H G,Tomasetto F,et al. Spectrometric prediction of nitrogen content in different tissues of slash pine trees[J]. Plant Phenomics,2022,2022:9892728.
[6]Liu W J,Li Y J,Tomasetto F,et al. Non-destructive measurements of Toona sinensis chlorophyll and nitrogen content under drought stress using near infrared spectroscopy[J]. Frontiers in Plant Science,2022,12:809828.
[7]郭拓,梁小娟,马晋芳,等. 基于可扩展的自表示学习波段选择算法在近红外光谱回归建模中的影响研究[J]. 分析测试学报,2022,41(8):1214-1220.
[8]Yun Y H,Li H D,Deng B C,et al. An overview of variable selection methods in multivariate analysis of near-infrared spectra[J]. TrAC Trends in Analytical Chemistry,2019,113:102-115.
[9]Wu X H,Zeng S P,Fu H J,et al. Determination of corn protein content using near-infrared spectroscopy combined with A-CARS-PLS[J]. Food Chemistry:X,2023,18:100666.
[10] Zhang D Y,Yang Y,Chen G,et al. Nondestructive evaluation of soluble solids content in tomato with different stage by using Vis/NIR technology and multivariate algorithms[J]. Spectrochimica Acta(Part A:Molecular and Biomolecular Spectroscopy),2021,248:119139.
[11]王偲晗,万幼川,王明威,等. 改进蚁群算法及其在高光谱影像分类中的研究[J]. 计算机工程与应用,2018,54(1):196-203.
[12]Bin J,Ai F F,Fan W,et al. An efficient variable selection method based on variable permutation and model population analysis for multivariate calibration of NIR spectra[J]. Chemometrics and Intelligent Laboratory Systems,2016,158:1-13.
[13]Zhang J,Cui X Y,Cai W S,et al. A variable importance criterion for variable selection in near-infrared spectral analysis[J]. Science China Chemistry,2019,62(2):271-279.
[14]刘翠玲,胡玉君,吴胜男,等. 近红外光谱奇异样本剔除方法研究[J]. 食品科学技术学报,2014,32(5):74-79.
[15]Huang X,Xia L. Improved kernel PLS combined with wavelength variable importance for near infrared spectral analysis[J]. Chemometrics and Intelligent Laboratory Systems,2017,168:107-113.
[16]Wang Z Z,Wu Q Y,Kamruzzaman M. Portable NIR spectroscopy and PLS based variable selection for adulteration detection in quinoa flour[J]. Food Control,2022,138:108970.
[17]Kumar B,Dikshit O,Gupta A,et al. Feature extraction for hyperspectral image classification:a review[J]. International Journal of Remote Sensing,2020,41(16):6248-6287.
[18]Liang L,Wei L L,Fang G G,et al. Prediction of holocellulose and lignin content of pulp wood feedstock using near infrared spectroscopy and variable selection[J]. Spectrochimica Acta Part A:Molecular and Biomolecular Spectroscopy,2020,225:117515.
[19]Bruning B,Liu H J,Brien C,et al. The development of hyperspectral distribution maps to predict the content and distribution of nitrogen and water in wheat (Triticum aestivum)[J]. Frontiers in Plant Science,2019,10:1380.

相似文献/References:

[1]朱银,颜伟,杨欣,等.基于近红外光谱的小麦种子发芽率测试[J].江苏农业科学,2015,43(12):111.
 Zhu Yin,et al.Measurement of germination rate of wheat seeds based on near infrared spectroscopy[J].Jiangsu Agricultural Sciences,2015,43(18):111.
[2]彭云发,罗华平,王丽,等.3种不同红枣水分检测方法的比较[J].江苏农业科学,2016,44(01):308.
 Peng Yunfa,et al.Comparison of three test methods of red jujube moisture[J].Jiangsu Agricultural Sciences,2016,44(18):308.
[3]王惠君,王文泉,和丽岗,等.橡胶树SSR-SRAP-AFLP标记遗传图谱构建[J].江苏农业科学,2015,43(07):41.
 Wang Huijun,et al.Construction of a genetic linkage map of Hevea brasiliensis based on SSR-SRAP-AFLP[J].Jiangsu Agricultural Sciences,2015,43(18):41.
[4]张峰,连芬燕,蓝洪桥,等.基于烟叶信息的近红外光谱和化学成分模式识别比较[J].江苏农业科学,2015,43(05):291.
 Zhang Feng,et al.Comparison of pattern recognition capacity between near-infrared spectra and chemical composition based on tobacco leaf information[J].Jiangsu Agricultural Sciences,2015,43(18):291.
[5]陈纪航,陶忠良,邱育毅.海南岛橡胶树风害坡度的影响特征[J].江苏农业科学,2015,43(05):141.
 Chen Jihang,et al.Characteristics affecting wind damage gradient of rubber tree in Hainan Province[J].Jiangsu Agricultural Sciences,2015,43(18):141.
[6]翟哲,李伟凯,李长凯,等.EMD在叶绿素光谱信号去噪中的应用[J].江苏农业科学,2015,43(04):392.
 Zhai Zhe,et al.Application of empirical mode decomposition in signal denoising of chlorophyll spectroscopy[J].Jiangsu Agricultural Sciences,2015,43(18):392.
[7]王海霞,周文婷,林萍,等.NIRS在广金钱草水分含量测定中的应用[J].江苏农业科学,2014,42(07):324.
 Wang Haixia,et al.Determination of moisture contents in Desmodium styracifolium by near-infrared spectroscopy[J].Jiangsu Agricultural Sciences,2014,42(18):324.
[8]张慧君,葛宇,杨先锋,等.内源激素对橡胶树花药体细胞胚发生的影响[J].江苏农业科学,2016,44(07):239.
 Zhang Huijun,et al.Effect of different endogenous hormones on anther somatic embryogenesis of rubber tree[J].Jiangsu Agricultural Sciences,2016,44(18):239.
[9]张兵,范泽华,姚江河,等.基于近红外光谱与多元模型的小麦氮含量估算[J].江苏农业科学,2016,44(09):374.
 Zhang Bing,et al.Estimation of wheat nitrogen content based on near infrared spectra and multivariate model[J].Jiangsu Agricultural Sciences,2016,44(18):374.
[10]郝婧,刘桂礼,李响.基于近红外光谱和LabVIEW技术的番茄抗灰霉病检测系统[J].江苏农业科学,2016,44(11):408.
 Hao jing,et al.Design of testing system for tomato Botrytis cinerea based on near-infrared spectroscopy and LabVIEW[J].Jiangsu Agricultural Sciences,2016,44(18):408.

备注/Memo

备注/Memo:
收稿日期:2023-09-20
基金项目:海南省自然科学基金创新研究团队项目(编号:320CXTD431);国家自然科学基金(编号:32060413);海南省重点研发计划(编号:ZDYF2022GXJS008);海南省自然科学基金高层次人才项目(编号:321RC468)。
作者简介:胡鹏飞(1996—),男,山东潍坊人,硕士研究生,主要从事植物养分无损检测研究。E-mail:hpf@hainanu.edu.cn。
通信作者:李创,博士,教授,博士生导师,主要从事高光谱遥感技术研究。E-mail:lc@hainanu.edu.cn。
更新日期/Last Update: 2024-09-20