首页 > 论文 > 红外与毫米波学报 > 30卷 > 1期(pp:48-54)

夏玉米可见/近红外光小波主成分提取与氮素含量神经网络检测

Detection of leaf nitrogen content of summer corn using visible/near infrared spectra

  • 摘要
  • 论文信息
  • 参考文献
  • 被引情况
  • PDF全文
分享:

摘要

使用高光谱仪ASD Field Spec于吐丝期采集不同氮素处理的夏玉米叶片光谱, 并进行对数变换处理; 通过对“绿峰”(450~680nm)和“近红外反射平台”(760~1000nm)谱段光谱数据进行多尺度小波分解, 获取第二层离散近似小波系数向量; 采用主成分分析, 从第二层离散近似小波系数向量中提取特征作为输入参数, 建立对叶片氮素含量的广义回归神经网络估算模型.结果表明: 对数变换显著地增强了“绿峰”和“近红外反射平台”谱段夏玉米叶片光谱对不同氮素处理的响应差异; 从第二层离散近似小波系数向量中提取的小波主成分能够反映夏玉米叶片光谱在不同氮素处理下的整体变化趋势; 以小波主成分作为输入参数的广义回归神经网络能够较为准确地预测夏玉米叶片氮素含量, 并且具有一定的推广能力.

Abstract

For the rapid detection of leaf nitrogen content of summer corn, visible and near infrared (Vis/NIR) spectra of summer corn leaves, with different nitrogen levels at spinning stage, were measured by an ASD FieldSpec. Discrete approximation wavelet coefficient vectors of the second-scale were obtained via logarithmic transformation and multi-scale wavelet decomposition of the spectra data within “near infrared spectrum platform” (760~1000nm) and “green peak” (450~ 680nm). Then principal components (PCs) were selected from these vectors by principal component analysis (PCA), and used as inputs of a generalized regression neural network (GRNN). The model was employed for the prediction of leaf nitrogen content of summer corn. Results show that logarithmic transformation can highlight the differences in the spectral response of summer corn leaves with different level of nitrogen within “near infrared spectrum platform” and “green peak” at spinning stage. The wavelet-based PCs can manifest the changes in the spectra of summer corn leaves with different nitrogen levels. Trained GRNN model with wavelet-based PCs as inputs can predict leaf nitrogen content of summer corn. The model is reliable and practicable.

Newport宣传-MKS新实验室计划
补充资料

中图分类号:S127

基金项目:国家科技支撑计划重大项目(2006BAD03A0308); 国家自然科学基金项目(30872073); “973”计划项目(2007CB407203)

收稿日期:2010-01-26

修改稿日期:2010-12-06

网络出版日期:0001-01-01

作者单位    点击查看

刘炜:西北农林科技大学 资源环境学院, 陕西 杨凌 712100
常庆瑞:西北农林科技大学 资源环境学院, 陕西 杨凌 712100
郭曼:西北农林科技大学 资源环境学院, 陕西 杨凌 712100
邢东兴:西北农林科技大学 资源环境学院, 陕西 杨凌 712100咸阳师范学院 资源环境系, 陕西 咸阳 712000
员永生:西北农林科技大学 资源环境学院, 陕西 杨凌 712100

联系人作者:刘炜(york5588@nwsuaf.edu.cn)

备注:刘炜(1978-),男,陕西咸阳人, 在读博士, 主要从事遥感与GIS应用研究。

【1】WANG Ji-Hua, ZHAO Chun-Jiang, HUANG Wen-Jiang. Base and application of quantitative remote sensing technique in agriculture[M]. Beijing: Science Press(王纪华, 赵春江, 黄文江.农业定量遥感基础与应用.北京: 科学出版社),2008: 4—289.

【2】LI Min-Zan, HAN Dong-Hai, WANG Xiu. Spectral analysis technique and its application[M]. Beijing: Science Press(李民赞, 韩东海, 王秀.光谱分析技术及其应用.北京: 科学出版社),2006: 176—228.

【3】HE Yong, LI Xiao-Li. Discriminating varieties of waxberry using near infrared spectra[J]. J.Infrared Millim.Waves(何勇, 李晓丽.用近红外光谱鉴别杨梅品种的研究.红外与毫米波学报),2006,25(3): 192—194.

【4】HE Yong, LI Xiao-Li, SHAO Yong-Ni. Quantitative analysis of the varieties of apple using near infrared spectroscopy LO-phonon modes in Ga1-xMnxAs[J]. phys Rev.,2002,B66: 205—209.

【5】WANG Xiu-Zhen, HUANG Jing-Feng, LI Yun-Mei, et al. The study on hyperspectral remote sensing estimation models about LAI of rice[J]. Journal of Remote Sensing(王秀珍, 黄敬峰, 李云梅, 等.水稻叶面积指数的高光谱遥感估算模型.遥感学报),2004,8(1): 81—88.

【6】TANG Yan-Lin, WANG Ren-Chao, HUANG Jing-Feng, et al. Hyperspetral data and their relationships correlative to the pigment contents for rice under different nitrogen support level[J]. Journal of Remote Sensing(唐延林, 王人潮, 黄敬峰, 等.不同供氮水平下水稻高光谱及其红边特征研究.遥感学报),2004,8(2): 185—192.

【7】HUANG Jing-Feng, TANG Shu-Chuan, QUSAMA Abou-Ismail, et al. Rice yield estimation using remote sensing and simulation model[J]. Journal of Zhejiang University Science,2002,3(4): 461—466.

【8】LIU Wei-Dong, XIANG Yue-Qin, ZHENG Lan-Fen, et al. Relationships between rice LAI, CH. D and hyperspectra data[J]. Journal of Remote Sensing(刘伟东, 项月琴, 郑兰芬, 等.高光谱数据与水稻叶面积指数及叶绿素密度的相关分析.遥感学报),2000,4(4): 279—283.

【9】XUE Li-Hong, CAO Wei-Xing, LUO Wei-Hong. Rice yield forecasting model with canopy reflectance spectra[J]. Journal of Remote Sensing(薛利红, 曹卫星, 罗卫红.基于冠层反射光谱的水稻产量预测模型.遥感学报),2005,9(1): 100—105.

【10】ZHAO Chun-Jiang. Research and practice of precision agrculture[M]. Beijing: Science Press(赵春江.精准农业研究与实践.北京: 科学出版社),2009: 232—253.

【11】YANG Min-Hua, ZHAO Chun-Jiang, ZHAO Yong-Chao, et al. Research on a method to derive wheat canopy information from airborne imaging spectrometer data[J]. Scientia Agricultura Sinica(杨敏华, 赵春江, 赵永超, 等.用航空成像光谱数据获取小麦冠层信息的研究.中国农业科学),2002,35(6): 626—631.

【12】WAN Yu-Qing, TAN Ke-Long, ZHOU Ri-Ping. Hyperspectral remote sensing and its application[M]. Beijing: Science Press(万余庆, 谭克龙, 周日平.高光谱遥感应用研究.北京: 科学出版社),2006: 22—173.

【13】ZHANG Xia, ZHANG Bing, WEI Zheng, et al. Study on spectral indices of MODIS for wheat growth monitoring[J]. Journal of Image and Graphics(张霞, 张兵, 卫征,等.MODIS光谱指数监测小麦长势变化研究.中国图象图形学报),2005,10(4): 420—424.

【14】ZHAN Da-Qi, SUN Su-Qin, ZHOU Qun, et al. Wavelet denoising and optimization of two-dimensional correlation IR spectroscopy[J]. Spectroscopy and Spectral Analysis(詹达琦, 孙素琴, 周群, 等.小波消噪与二维相关红外光谱的质量优化.光谱学与光谱分析),2004,24(12): 1549—1552.

【15】JIANG Qing-Song, WANG Jian-Yu. Study on signal-to-noise ratio estimtion and compression method of operational modular imaging spectrometer multi-spectral images[J]. Acta Optica Sinica(蒋青松, 王建宇.实用型模块化成像光谱仪多光谱图像的信噪比估算及压缩方法研究.光学学报),2003,23(11): 1335—1340.

【16】ZHANG Lin, FANG Zhi-Jun, WANG Sheng-Qian, et al. Multi wavelet adaptive denoising method based on genetic algorithm[J]. J.Infrared Millim.Waves(章琳, 方志军, 汪胜前, 等.基于遗传算法的多小波自适应去噪方法研究.红外与毫米波学报),2009,28(1): 77—80.

【17】TIAN Gao-You, YUAN Hong-Fu, LIU Hui-Ying, et al. Wavelet property analysis of near infrared spectra[J]. Spectroscopy and Spectral Analysis(田高友, 袁洪福, 刘慧颖.近红外光谱的小波特性研究.光谱学与光谱分析),2006,26(8): 1441—1444.

【18】LI Xiao-Li, HU Xing-Yue, HE Yong. New approach of discrimination of varieties of juicy peach by near infrared spectra based on PCA and MDA model[J]. J. Infrared Millim. Waves(李晓丽, 胡兴越, 何勇.基于主成分和多类判别分析的可见-红外光谱水蜜桃品种鉴别新方法.红外与毫米波学报),2006,25(6): 417—420.

【19】SHAO Yong-Ni, CAO Fang, HE Yong. Discrimination years of rough rice by using visible/ near infrared spectroscopy based on independent component analysis and BP neural network[J]. J. Infrared Millim. Waves(邵咏妮, 曹芳, 何勇.基于独立组分分析和BP神经网络的可见/近红外光谱稻谷年份的鉴别.红外与毫米波学报),2007,26(6): 433—436.

【20】YIN Qiu, SU Xiao-Zhou, XU Zhao-An, et al. Analysis on the ultra-spectral characteristics of water environmental parameters about lake[J]. J. Infrared Millim. Waves(尹球, 疏小舟, 徐兆安, 等.湖泊水环境指标的超光谱响应特征分析.红外与毫米波学报),2004,23(6): 427—430.

【21】LIU Liang-Yun, ZHANG Bing, ZHENG Lan-Fen, et al. Target classification and soil water content regression using land surface temperature(LST) and vegetation index(VI)[J]. J. Infrared Millim. Waves(刘良云, 张兵, 郑兰芬, 等.利用温度和植被指数进行地物分类和土壤水分反演.红外与毫米波学报),2002,21(4): 269—273.

【22】LI Hong-Bo, SHU Rong, XUE Yong-Qi. Pushbroom hyperspectral imager and its potential application to oceanographic remote sensing[J]. J. Infrared Millim. Waves(李红波, 舒嵘, 薛永祺.PHI超光谱成像系统及其海洋遥感应用前景分析.红外与毫米波学报),2002,21(6): 429—433.

引用该论文

LIU Wei,CHANG Qing-Rui,GUO Man,XING Dong-Xing,YUAN Yong-Sheng. Detection of leaf nitrogen content of summer corn using visible/near infrared spectra[J]. Journal of Infrared and Millimeter Waves, 2011, 30(1): 48-54

刘炜,常庆瑞,郭曼,邢东兴,员永生. 夏玉米可见/近红外光小波主成分提取与氮素含量神经网络检测[J]. 红外与毫米波学报, 2011, 30(1): 48-54

被引情况

【1】龚志远,李轶凡,刘燕德,孙旭东. 光源照射角度对苹果糖度近红外光谱检测的影响研究. 激光与光电子学进展, 2016, 53(2): 23004--1

【2】刘 明,李忠任,张海涛,于春霞,唐兴宏,丁香乾. 基于二分搜索结合修剪随机森林的特征选择算法在近红外光谱分类中的应用. 激光与光电子学进展, 2017, 54(10): 103001--1

您的浏览器不支持PDF插件,请使用最新的(Chrome/Fire Fox等)浏览器.或者您还可以点击此处下载该论文PDF