|本期目录/Table of Contents|

[1]裴浩杰,冯海宽,李长春,等.基于多元线性回归和随机森林的苹果叶绿素含量高光谱估测方法比较[J].江苏农业科学,2018,46(17):224-230.
 Pei Haojie,et al.Comparison of hyperspectral estimation methods for chlorophyll contents of apple based on multiple linear regression and random forest[J].Jiangsu Agricultural Sciences,2018,46(17):224-230.
点击复制

基于多元线性回归和随机森林的苹果叶绿素
含量高光谱估测方法比较
(PDF)
分享到:

《江苏农业科学》[ISSN:1002-1302/CN:32-1214/S]

卷:
第46卷
期数:
2018年第17期
页码:
224-230
栏目:
农业工程与信息技术
出版日期:
2018-09-05

文章信息/Info

Title:
Comparison of hyperspectral estimation methods for chlorophyll contents of apple based on multiple linear regression and random forest
作者:
裴浩杰1234 冯海宽234 李长春1 李振海234 杨贵军234 王衍安5 郭建华234
1.河南理工大学测绘与国土信息工程学院,河南焦作 454000; 2.国家农业信息化工程技术研究中心,北京 100097; 3.农业部农业信息技术
重点实验室,北京 100097; 4.北京市农业物联网工程技术研究中心,北京 100097; 5.山东农业大学生命科学学院,山东泰安 271018
Author(s):
Pei Haojieet al
关键词:
苹果叶片高光谱叶绿素MLRRF
Keywords:
-
分类号:
S127
DOI:
-
文献标志码:
A
摘要:
叶绿素含量是果树营养胁迫和光合作用等生理状态的良好指示剂。为快速准确地估测苹果叶片叶绿素含量,利用采集的苹果叶片光谱和叶片叶绿素含量数据,通过分析原始光谱与叶绿素含量的相关性,筛选出554、708、995 nm 3个最佳敏感波段,构建基于原始光谱敏感波段的多元线性回归(multivariable linear regression,简称MLR)模型和随机森林(random forest,简称RF)模型,用于叶绿素含量估测;使用相关系数绝对值(absolute value of correlation coefficient,简称|r|)和RF的袋外数据(out of bag,简称OOB)重要性分别对植被指数与叶片叶绿素含量的关联性进行分析,筛选植被指数,然后使用MLR和RF算法构建模型,依次增加植被指数的输入数,筛选出10个植被指数的MLR最优模型和5个植被指数的RF最优模型;比较上述4个模型的估测精度。基于原始光谱的MLR模型和RF模型以及基于植被指数的MLR最优模型和RF最优模型建模的R2分别为0.578、0.527,0.602、0.609,RMSE分别为8.240、8.728,8.004、7.930 μg/cm2,4个模型建模精度相近。在模型验证方面,4个模型的R2分别为0.899、0.411、0.854、0843,RMSE分别为8.297、14.455、11.242、11.034 μg/cm2。基于原始光谱的MLR模型的叶绿素含量估测精度高于其他3个模型,能够精确地估测苹果叶片叶绿素含量。另外,基于植被指数的MLR模型和RF模型对苹果叶片叶绿素含量估测也具有一定的应用潜力。
Abstract:
-

参考文献/References:

[1]蒋金豹,陈云浩,黄文江. 用高光谱微分指数估测条锈病胁迫下小麦冠层叶绿素密度[J]. 光谱学与光谱分析,2010,30(8):2243-2247.
[2]徐新刚,赵春江,王纪华,等. 新型光谱曲线特征参数与水稻叶绿素含量间的关系研究[J]. 光谱学与光谱分析,2011,31(1):188-191.
[3]Mark S,Anatoly G,Donald C R. Nondestructive estimation of leaf chlorophyll content in grapes[J]. American Journal of Enology & Viticulture,2008,59(3):299-305.
[4]张瑶,郑立华,李民赞,等. 基于光谱特征分析的苹果树叶片营养素预测模型构建[J]. 农业工程学报,2013(8):171-178.
[5]李敏夏. 苹果叶片光谱反射率与叶绿素和全氮含量的相关研究[D]. 杨凌:西北农林科技大学,2009.
[6]李萍. 基于光谱分析的库尔勒香梨叶片全氮、全磷含量估测模型建立[D]. 乌鲁木齐:新疆农业大学,2013.
[7]张蕾蕾. 苹果幼树叶片叶绿素与水分含量的高光谱估测研究[D]. 泰安:山东农业大学,2013.
[8]王丽爱,周旭东,朱新开,等. 基于HJ-CCD数据和随机森林算法的小麦叶面积指数反演[J]. 农业工程学报,2016(3):149-154.
[9]李粉玲,王力,刘京,等. 基于高分一号卫星数据的冬小麦叶片SPAD值遥感估算[J]. 农业机械学报,2015,46(9):273-281.
[10]王丽爱,马昌,周旭东,等. 基于随机森林回归算法的小麦叶片SPAD值遥感估算[J]. 农业机械学报,2015,46(1):259-265.
[11]韩兆迎,朱西存,房贤一,等. 基于SVM与RF的苹果树冠LAI高光谱估测[J]. 光谱学与光谱分析,2016,36(3):800-805.
[12]岳继博,杨贵军,冯海宽. 基于随机森林算法的冬小麦生物量遥感估算模型对比[J]. 农业工程学报,2016(18):175-182.
[13]Lichtenthaler H K. Chlorophylls and carotenoids:pigments of photosynthetic biomembranes[J]. Methods in Enzymology,1987,148:350-382.
[14]Peuelas J,Gamon J A,Fredeen A L,et al. Reflectance indices associated with physiological changes in nitrogen-and water-limited sunflower leaves[J]. Remote Sensing of Environment,1994,48(2):135-146.
[15]Peuelas J,Filella I,Lloret P,et al. Reflectance assessment of mite effects on apple trees[J]. International Journal of Remote Sensing,1995,16(14):2727-2733.
[16]Daughtry C S T,Walthall C L,Kim M S,et al. Estimating corn leaf chlorophyll concentration from leaf and canopy reflectance[J]. Remote Sensing of Environment,2000,74(2):229-239.
[17]Haboudane D,Miller J R,Pattey E,et al. Hyperspectral vegetation indices and novel algorithms for predicting green LAI of crop canopies:modeling and validation in the context of precision agriculture[J]. Remote Sensing of Environment,2004,90(3):337-352.
[18]Haboudane D,Miller J R,Tremblay N,et al. Integrated narrow-band vegetation indices for prediction of crop chlorophyll content for application to precision agriculture[J]. Remote Sensing of Environment,2002,81(2):416-426.
[19]Dash J,Curran P J. The MERIS terrestrial chlorophyll index[J]. International Journal of Remote Sensing,2004,25(23):5403-5413.
[20]Sims D A,Gamon J A. Relationships between leaf pigment content and spectral reflectance across a wide range of species,leaf structures and developmental stages[J]. Remote Sensing of Environment,2002,81(2/3):337-354.
[21]Tucker C J. Red and photographic infrared linear combinations for monitoring vegetation[J]. Remote Sensing of Environment,1979,8(2):127-150.
[22]Gitelson A A,Merzlyak M N,Chivkunova O B. Optical properties and nondestructive estimation of anthocyanin content in plant leaves[J]. Photochemistry and Photobiology,2001,74(1):38-45.
[23]Roujean J L,Breon F M. Estimating PAR absorbed by vegetation from bidirectional reflectance measurements[J]. Remote Sensing of Environment,1995,51(3):375-384.
[24]Qi J,Chehbouni A,Huete A R,et al. A modified soil adjusted vegetation index[J]. Remote Sensing of Environment,1994,48(2):119-126.
[25]Horler D N H,Dockray M,Barber J. The red edge of plant leaf reflectance[J]. International Journal of Remote Sensing,1983,4(2):273-288.
[26]Vincini M,Frazzi E,DAlessio P. Narrow-band vegetation indexes from hyperion and directional chris/proba data for canopy chlorophyll density[C]//Envisat Symposium 2007.Montr eux,Switzerland,2007.
[27]Gitelson A A,Merzlyak M N. Remote estimation of chlorophyll content in higher plant leaves[J]. International Journal of Remote Sensing,1997,18(12):2691-2697.
[28]Vogelmann J E,Rock B N,Moss D M. Red edge spectral measurements from sugar maple leaves[J]. International Journal of Remote Sensing,1993,14(8):1563-1575.
[29]Zarco-Tejada P J,Miller J R,Noland T L,et al. Scaling-up and model inversion methods with narrowband optical indices for chlorophyll content estimation in closed forest canopies with hyperspectral data[J]. IEEE Transactions on Geoscience & Remote Sensing,2001,39(7):1491-1507.
[30]Mahlein A K,Steiner U,Dehne H W,et al. Spectral signatures of sugar beet leaves for the detection and differentiation of diseases[J]. Precision Agriculture,2010,11(4):413-431.
[31]Zarco-Tejada P J,Pushnik J C,Dobrowski S,et al. Steady-state chlorophyll a fluorescence detection from canopy derivative reflectance and double-peak red-edge effects[J]. Remote Sensing of Environment,2003,84(2):283-294.
[32]Kim M S,Daughtry C T,Chapelle E W. The use of high spectral resolution bands for estimating absorbed photosynthetically active radiation(Apar.)[C]//Proceedingsof the Sixth Symposium on Physical Measurements and Signatures in Remote Sensing.Val DIsure,France,1994:299.
[33]Chen P F,Haboudane D,Tremblay N,et al. New spectral indicator assessing the efficiency of crop nitrogen treatment in corn and wheat[J]. Remote Sensing of Environment,2010,114(9):1987-1997.
[34]Jin X,Li Z,Feng H,et al. Newly combined spectral indices to improve estimation of total leaf chlorophyll content in cotton[J]. IEEE Journal of Selected Topics in Applied Earth Observations & Remote Sensing,2014,7(1):4589-4600.
[35]Breiman L. Random forests[J]. Machine Learning,2001,45(1):5-32.
[36]Breiman L. Bagging predictors[J]. Machine Learning,1996,24(2):123-140.
[37]王惠文,孟洁. 多元线性回归的预测建模方法[J]. 北京航空航天大学学报,2007,33(4):500-504.
[38]李旭青,刘湘南,刘美玲,等. 水稻冠层氮素含量光谱反演的随机森林算法及区域应用[J]. 遥感学报,2014,18(4):923-945.
[39]Verikas A,Gelzinis A,Bacauskiene M. Mining data with random forests:a survey and results of new tests[J]. Pattern Recognition,2011,44(2):330-349.

相似文献/References:

[1]王有宁,赵丽艳,章爱群,等.花生高光谱叶片营养诊断研究[J].江苏农业科学,2014,42(12):129.
 Wang Youning,et al.Study on nutrition diagnosis of peanut leaves based on hyperspectral data[J].Jiangsu Agricultural Sciences,2014,42(17):129.
[2]杨粉团,顾晓鹤,李刚,等.吐丝期玉米倒伏后地面高光谱特征参数分析[J].江苏农业科学,2016,44(03):85.
 Yang Fentuan,et al.Analysis of hyper-spectral characteristic parameters of lodging corn at silking stage[J].Jiangsu Agricultural Sciences,2016,44(17):85.
[3]孙俊,金夏明,毛罕平,等.基于有监督特征提取的生菜叶片农药残留浓度高光谱鉴别研究[J].江苏农业科学,2014,42(05):227.
 Sun Jun,et al.Study on detection of hyperspectral data of lettuce leaves with pesticide residue based on supervised feature extraction method[J].Jiangsu Agricultural Sciences,2014,42(17):227.
[4]赵文,刘国顺,贾方方,等.烤烟烟碱含量的高光谱预测模型[J].江苏农业科学,2014,42(03):275.
 Zhao Wen,et al.Hyperspectral prediction model of nicotine content in flue-cured tobacco[J].Jiangsu Agricultural Sciences,2014,42(17):275.
[5]田敏,周杰,张泽,等.基于高光谱植被指数对棉花叶绿素含量的估算[J].江苏农业科学,2017,45(02):216.
 Tian Min,et al.Estimation of cotton chlorophyll contents based on hyperspectral vegetation index[J].Jiangsu Agricultural Sciences,2017,45(17):216.
[6]喻俊,李晓敏,张权,等.基于实测高光谱数据的太湖湖滨带典型植被分类[J].江苏农业科学,2017,45(05):240.
 Yu Jun,et al.Classification of typical vegetation zones of Taihu Lake based on measured hyperspectral data[J].Jiangsu Agricultural Sciences,2017,45(17):240.
[7]杨荣超,田海清,李斐,等.基于甜菜冠层高光谱红边参数的SPAD值诊断[J].江苏农业科学,2017,45(11):153.
 Yang Rongchao,et al.SPAD value diagnosis based on red edge parameters of sugarbeet canopy hyperspectral[J].Jiangsu Agricultural Sciences,2017,45(17):153.
[8]张城芳,董恒.基于高光谱数据的作物净初级生产力估算方法[J].江苏农业科学,2017,45(22):260.
 Zhang Chengfang,et al.Estimation method of crop net primary productivity based on hyperspectral data[J].Jiangsu Agricultural Sciences,2017,45(17):260.
[9]向佳琳,姚鑫锋,刘倩,等.基于高光谱的温室网纹甜瓜不同叶位叶片含水率监测[J].江苏农业科学,2018,46(04):105.
 Xiang Jialin,et al.Hyperspectral monitoring of leaf water content in different leaf position of muskmelon in greenhouse[J].Jiangsu Agricultural Sciences,2018,46(17):105.
[10]叶春,李艳大,舒时富,等.基于高光谱的柑橘叶片氮素营养监测模型[J].江苏农业科学,2018,46(07):223.
 Ye Chun,et al.Study on nitrogen nutrition monitoring model of citrus leaves based on hyperspectrum[J].Jiangsu Agricultural Sciences,2018,46(17):223.

备注/Memo

备注/Memo:
收稿日期:2017-12-10
基金项目:国家自然科学基金(编号:41601346、41471285、41301475);国家高技术研究发展计划(编号:2011AA100703)。
作者简介:裴浩杰(1991—),男,河南郑州人,硕士研究生,主要从事农业定量遥感研究。E-mail:xmljphj@163.com。
通信作者:冯海宽,硕士,助理研究员,主要从事农业定量遥感研究,E-mail:fenghaikuan123@163.com;李长春,博士,副教授,主要从事农业遥感长势监测与评估研究工作,E-mail:lichangchun610@126.com。
更新日期/Last Update: 2018-09-05