首页 > 论文 > 激光与光电子学进展 > 56卷 > 15期(pp:153002--1)

基于分数阶微分和连续投影算法-反向传播神经网络的小麦叶片含水量高光谱估算

Hyperspectral Estimation of Wheat Leaf Water Content Using Fractional Differentials and Successive Projection Algorithm-Back Propagation Neural Network

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

摘要

为了探索分数阶微分在高光谱估算小麦叶片含水量上的可行性,在农田尺度上,利用春小麦野外光谱数据与实测叶片含水量数据,以0.2阶为步长,计算光谱0~2阶微分,并分析其与小麦叶片含水量的相关性,再利用连续投影算法(SPA)从通过0.01水平显著性检验的波段中筛选出估算叶片含水量的最佳波段组合,并建立估算春小麦叶片含水量的反射传播(BP)神经网络模型。结果表明:分数阶微分可以细化小麦叶片含水量与光谱数据相关性的变化趋势;分数阶微分处理后,相关系数通过0.01水平显著性检验的波段数量呈现先增后减的趋势,在不同的波段范围内,分数阶微分的最佳阶数也有所不同;SPA筛选出的敏感波段基本上集中在红光、近红外波段范围内,1.2阶微分后水分敏感波段数最多,达到13个;所建立的模型中,基于1.8阶微分建立的6-4-1结构的BP神经网络模型为最佳模型,其建模组均方根误差为0.701,决定系数为0.751,验证组的均方根误差为0.227,决定系数为0.917,相对分析误差为3.253,说明了分数阶微分后的模型稳定性和预测能力较整数阶微分得到明显的提升,可为高光谱定量反演春小麦叶片含水量提供参考。

Abstract

To explore the feasibility of using fractional differentials in the hyperspectral estimation of wheat leaf water content, we select the Fukang experimental science base of Xinjiang University as the study area. Based on springtime wheat-field spectral data and wheat leaf water content data, we calculate the fractional differentials of the spectrum from the 0-order to the 2-order in 0.2-order steps; further, we analyze their correlations with the water content of the wheat leaves. We then use the successive projection algorithm (SPA) to select the optimal combination of bands for estimating the leaf water content from bands passing the 0.01 significance test. Finally, we establish a back propagation (BP) neural network model for estimating the water content of spring wheat leaves. The results show that fractional differentials can refine the trend of correlation between wheat leaf water content and the wheat leaves'' spectral data. After fractional differential processing, the number of bands for which the correlation coefficients pass the 0.01 significance test first increases and subsequently decreases; in addition, the optimal order of fractional differentials is also different in different bands. Sensitive bands selected by the SPA are mainly concentrated in the red and near infrared bands, and the number of water sensitive bands is highest (reaching 13) after 1.2-order differential processing. Among the models considered herein, the BP neural network model with the 6-4-1 structure based on the 1.8-order differential is the best model, with the following specifications: the root-mean-square error of the modeling group is 0.701, the determination coefficient of the modeling group is 0.751, the root-mean-square error of the verification group is 0.227, the determination coefficient of the verification group is 0.917, and the relative analysis error of the verification group is 3.253. These conclusions show that the stability and predictive ability of the model using fractional differentials are better than those of integer differentials, and it provides a well-defined reference for the quantitative inversion of hyperspectral data to estimate the water content of spring wheat.

Newport宣传-MKS新实验室计划
补充资料

DOI:10.3788/LOP56.153002

所属栏目:光谱学

基金项目:国家自然科学基金(41361016,40901163,41761077);

收稿日期:2019-02-22

修改稿日期:2019-03-11

网络出版日期:2019-08-01

作者单位    点击查看

吾木提·艾山江:新疆大学资源与环境科学学院, 新疆 乌鲁木齐 830046新疆绿洲生态教育部重点实验室, 新疆 乌鲁木齐 830046
买买提·沙吾提:新疆大学资源与环境科学学院, 新疆 乌鲁木齐 830046新疆绿洲生态教育部重点实验室, 新疆 乌鲁木齐 830046新疆智慧城市与环境建模普通高校重点实验室, 新疆 乌鲁木齐 830046
马春玥:新疆大学资源与环境科学学院, 新疆 乌鲁木齐 830046新疆绿洲生态教育部重点实验室, 新疆 乌鲁木齐 830046

联系人作者:买买提·沙吾提(korxat@xju.edu.cn)

备注:国家自然科学基金(41361016,40901163,41761077);

【1】Rodríguez-Pérez J R, Ordó ez C, González-Fernández A B et al. . Leaf water content estimation by functional linear regression of field spectroscopy data. Biosystems Engineering. 165, 36-46(2018).

【2】Fang M H, Ju W M, Zhan W F et al. A new spectral similarity water index for the estimation of leaf water content from hyperspectral data of leaves. Remote Sensing of Environment. 196, 13-27(2017).

【3】Lin Y, Li Q, Wang H B et al. Research summary of vegetation water content inversion with hyperspectral technology. Chinese Agricultural Science Bulletin. 31(3), 167-172(2015).
林毅, 李倩, 王宏博 等. 高光谱反演植被水分含量研究综述. 中国农学通报. 31(3), 167-172(2015).

【4】Liang L, Zhang L P, Lin H et al. Estimating canopy leaf water content in wheat based on derivative spectra. Scientia Agricultura Sinica. 46(1), 18-29(2013).
梁亮, 张连蓬, 林卉 等. 基于导数光谱的小麦冠层叶片含水量反演. 中国农业科学. 46(1), 18-29(2013).

【5】Deng B, Yang W N, Mu N et al. The research of vegetation water content based on spectrum analysis and angle slope index. Spectroscopy and Spectral Analysis. 36(8), 2546-2552(2016).
邓兵, 杨武年, 慕楠 等. 基于光谱分析与角度斜率指数的植被含水量研究. 光谱学与光谱分析. 36(8), 2546-2552(2016).

【6】Dobrowski S, Pushnik J, Zarco-Tejada P et al. Simple reflectance indices track heat and water stress-induced changes in steady-state chlorophyll fluorescence at the canopy scale. Remote Sensing of Environment. 97(3), 403-414(2005).

【7】Tian Y C, Zhu Y, Cao W X et al. Relationship between canopy reflectance and plant water status of wheat. Chinese Journal of Applied Ecology. 15(11), 2072-2076(2004).
田永超, 朱艳, 曹卫星 等. 小麦冠层反射光谱与植株水分状况的关系. 应用生态学报. 15(11), 2072-2076(2004).

【8】Wang Y Y, Li G C, Zhang L J et al. Retrieval of leaf water content of winter wheat from canopy hyperspectral data using partial least square regression. Spectroscopy and Spectral Analysis. 30(4), 1070-1074(2010).
王圆圆, 李贵才, 张立军 等. 利用偏最小二乘回归从冬小麦冠层光谱提取叶片含水量. 光谱学与光谱分析. 30(4), 1070-1074(2010).

【9】Chen D Y, Huang J F and Jackson T J. Vegetation water content estimation for corn and soybeans using spectral indices derived from MODIS near- and short-wave infrared bands. Remote Sensing of Environment. 98(2/3), 225-236(2005).

【10】Zheng X M, Ding Y L, Zhao K et al. Estimation of vegetation water content from Landsat 8 OLI data. Spectroscopy and Spectral Analysis. 34(12), 3385-3390(2014).
郑兴明, 丁艳玲, 赵凯 等. 基于Landsat 8 OLI数据的玉米冠层含水量反演研究. 光谱学与光谱分析. 34(12), 3385-3390(2014).

【11】Ghulam A, Li Z L, Qin Q M et al. A method for remote sensing monitoring of total vegetation canopy water: short wave infrared vertical water loss index. Science in China. 37(7), 957-965(2007).
李召良, 秦其明 等. 全覆盖植被冠层水分遥感监测的一种方法: 短波红外垂直失水指数. 中国科学. 37(7), 957-965(2007).

【12】Xu J G, Feng X L, Guan L et al. Fractional differential application in reprocessing infrared spectral data. Control and Instruments in Chemical Industry. 39(3), 347-351(2012).
徐继刚, 冯新泸, 管亮 等. 分数阶微分在红外光谱数据预处理中的应用. 化工自动化及仪表. 39(3), 347-351(2012).

【13】Zhang W W, Yang K M, Xia T et al. Correlation analysis on spectral fractional-order differential and the content of heavy metal copper in corn leaves. Science Technology and Engineering. 17(25), 33-38(2017).
张文文, 杨可明, 夏天 等. 光谱分数阶微分与玉米叶片重金属铜含量的相关性分析. 科学技术与工程. 17(25), 33-38(2017).

【14】Lin S M and Xu C J. Theoretical and numerical investigation of fractional differential equations. Mathematica Numerica Sinica. 38(1), 1-24(2016).
林世敏, 许传炬. 分数阶微分方程的理论和数值方法研究. 计算数学. 38(1), 1-24(2016).

【15】Zhang D, Tiyip T, Zhang F et al. Effect of fractional differential algorithm on hyperspectral data of saline soil. Acta Optica Sinica. 36(3), (2016).
张东. 塔西甫拉提·特依拜, 张飞, 等. 分数阶微分算法对盐渍土高光谱数据的影响研究. 光学学报. 36(3), (2016).

【16】Liu K, Chen X J, Li L M et al. A consensus successive projections algorithm-multiple linear regression method for analyzing near infrared spectra. Analytica Chimica Acta. 858, 16-23(2015).

【17】Liu M B, Tang Y L, Li X L et al. Feasibility of using successive projections algorithm in spectral monitoring of rice leaves nitrogen contents. Infrared and Laser Engineering. 43(4), 1265-1271(2014).
刘明博, 唐延林, 李晓利 等. 水稻叶片氮含量光谱监测中使用连续投影算法的可行性. 红外与激光工程. 43(4), 1265-1271(2014).

【18】Liu Q M, Cheng Q M, Wang X et al. Soil salinity inversion in Hetao Irrigation district using microwave radar. Transactions of the Chinese Society of Agricultural Engineering. 32(16), 109-114(2016).
刘全明, 成秋明, 王学 等. 河套灌区土壤盐渍化微波雷达反演. 农业工程学报. 32(16), 109-114(2016).

【19】Umut H, Mamat S, Ilyas N et al. Inversion model of soil salt content based on WorldView-2 image. Transactions of the Chinese Society of Agricultural Engineering. 33(24), 200-206(2017).
等. 基于WorldView-2影像的土壤含盐量反演模型. 农业工程学报. 33(24), 200-206(2017).

引用该论文

Umut Hasan,Mamat Sawut,Ma Chunyue. Hyperspectral Estimation of Wheat Leaf Water Content Using Fractional Differentials and Successive Projection Algorithm-Back Propagation Neural Network[J]. Laser & Optoelectronics Progress, 2019, 56(15): 153002

吾木提·艾山江,买买提·沙吾提,马春玥. 基于分数阶微分和连续投影算法-反向传播神经网络的小麦叶片含水量高光谱估算[J]. 激光与光电子学进展, 2019, 56(15): 153002

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