Please wait a minute...
 
国土资源遥感  2021, Vol. 33 Issue (2): 33-39    DOI: 10.6046/gtzyyg.2020299
  技术方法 本期目录 | 过刊浏览 | 高级检索 |
基于小波变换和连续投影算法的黑土有机质含量高光谱估测
肖艳1(), 辛洪波1, 王斌2, 崔利1, 姜琦刚3
1.长春工程学院勘查与测绘工程学院,长春 130012
2.长春市测绘院, 长春 130021
3.吉林大学地球探测科学与技术学院,长春 130026
Hyperspectral estimation of black soil organic matter content based on wavelet transform and successive projections algorithm
XIAO Yan1(), XIN Hongbo1, WANG Bin2, CUI Li1, JIANG Qigang3
1. College of Exploration and Surveying Engineering, Changchun Insititute of Technology, Changchun 130012, China
2. Changchun Institute of Surveying and Mapping, Changchun 130021, China
3. College of Geo-Exploration Science and Technology, Jilin University, Changchun 130026, China
全文: PDF(2686 KB)   HTML  
输出: BibTeX | EndNote (RIS)      
摘要 

为实现黑土有机质含量更准确的估测,提出了基于小波变换和连续投影算法的高光谱估测方法。以典型黑土区采集的土壤样品为研究对象、分析光谱设备(analytical spectral devices,ASD)光谱仪获取的可见光—近红外区间光谱数据和经化学分析得到的土壤有机质含量为数据源,首先采用小波变换提取1~7层小波低频系数,然后利用连续投影算法分别对土壤全谱和1~7层小波低频系数进行变量筛选,最后分别基于土壤全谱、1~7层小波低频系数、连续投影算法选择的变量,利用偏最小二乘和支持向量机两种方法建立估测模型。结果表明: 经小波变换和连续投影算法处理后,不仅变量数目得到了大幅降低,而且模型精度也进一步得到了提高,采用偏最小二乘法时,R2由土壤全谱的0.79提高至第6层小波低频系数的0.93,RMSE由6.06 g·kg-1降低至3.48 g·kg-1; 采用支持向量机方法时,R2由土壤全谱的0.75提高至第3层小波低频系数的0.91,RMSE由7.46 g·kg-1降低至4.12 g·kg-1,说明提出的方法能有效用于黑土有机质含量高光谱估测。

服务
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章
肖艳
辛洪波
王斌
崔利
姜琦刚
关键词 有机质高光谱小波变换连续投影算法    
Abstract

Black soil is a valuable land resource, and the content of organic matter is an important index reflecting soil fertility, state and degradation degree. In order to estimate black soil organic matter content more accurately, this paper proposes a hyperspectral estimation method based on wavelet transform and successive projections algorithm. In this paper,the soil samples collected in the typical black soil region were used as the research object,and the Vis-NIR spectral data of the soil obtained from analytical spectral deviees (ASD) spectrometer and the organic matter content through chemical analysis were used as the data sources.Firstly, wavelet transform was used to extract the wavelet coefficients of 1 to 7 levels, and then successive projections algorithm was used to select the variables from soil original spectrum and the wavelet coefficients of 1 to 7 levels respectively. Finally, based on the soil original spectrum, the wavelet coefficients of 1 to 7 levels and the selected variables based on successive projections algorithm respectively, partial least squares and support vector machine were used to build the estimation models. The results show that, by using wavelet transform and successive projections algorithm, not only the number of variables is reduced greatly, but also the accuracies of the models are improved. When using partial least squares method,R2 increases from 0.79 of the soil original spectrum to 0.93 of the wavelet coefficient of the sixth level, and RMSE decreases from 6.06 g·kg-1 to 3.48 g·kg-1. When support vector machine method is used, R2 increases from 0.75 of the soil original spectrum to 0.91 of the wavelet coefficient of the third level, and RMSE decreases from 7.46 g·kg-1 to 4.12 g·kg-1. The results indicate that the proposed method can be effectively used for the hyperspectral estimation of black soil organic matter content.

Key wordsorganic matter    hyperspectral    wavelet transform    successive projections algorithm
收稿日期: 2020-09-23      出版日期: 2021-07-21
ZTFLH:  TP79  
基金资助:吉林省教育厅项目“基于3S技术的吉林省西部土地荒漠化演化趋势研究——以通榆县为例”(JJKH20191267KJ);长春工程学院大学生创新创业训练计划资助项目“多光谱和PolSAR影像协同分类研究”(202011437036)
作者简介: 肖 艳(1988-),女,博士,讲师,主要从事遥感影像分类和高光谱数据反演方面的研究。Email: 459389436@qq.com
引用本文:   
肖艳, 辛洪波, 王斌, 崔利, 姜琦刚. 基于小波变换和连续投影算法的黑土有机质含量高光谱估测[J]. 国土资源遥感, 2021, 33(2): 33-39.
XIAO Yan, XIN Hongbo, WANG Bin, CUI Li, JIANG Qigang. Hyperspectral estimation of black soil organic matter content based on wavelet transform and successive projections algorithm. Remote Sensing for Land & Resources, 2021, 33(2): 33-39.
链接本文:  
https://www.gtzyyg.com/CN/10.6046/gtzyyg.2020299      或      https://www.gtzyyg.com/CN/Y2021/V33/I2/33
Fig.1  采样点分布图
类别 数量/个 最大值/
(g·kg-1)
最小值/
(g·kg-1)
平均值/
(g·kg-1)
标准差/
(g·kg-1)
建模样本 46 71.94 19.03 46.41 13.88
验证样本 15 66.78 20.72 45.41 13.38
Tab.1  土壤样本有机质含量描述性统计
Fig.2  SPA算法筛选得到变量的分布情况
级别 PLS SVM 变量数
量/个
R2 RMSE/
(g·kg-1)
R2 RMSE/
(g·kg-1)
土壤全谱 0.79 6.06 0.75 7.46 2 051
第1层 0.77 6.37 0.73 7.37 1 028
第2层 0.73 7.01 0.73 7.20 516
第3层 0.73 6.96 0.74 7.12 260
第4层 0.86 5.08 0.84 5.50 132
第5层 0.88 4.56 0.87 4.96 68
第6层 0.86 5.02 0.79 6.37 36
第7层 0.72 7.12 0.72 7.18 20
Tab.2  土壤全谱和1~7层小波低频系数的估测模型评价结果
级别 PLS SVM 变量数
量/个
R2 RMSE/
(g·kg-1)
R2 RMSE/
(g·kg-1)
土壤全谱 0.77 6.38 0.85 5.80 18
第1层 0.33 10.93 0.77 6.51 26
第2层 0.86 4.94 0.79 6.46 33
第3层 0.77 6.41 0.91 4.12 18
第4层 0.91 4.00 0.87 4.96 14
第5层 0.92 3.84 0.85 5.39 11
第6层 0.93 3.48 0.80 6.18 11
第7层 0.82 5.70 0.72 7.15 9
Tab.3  SPA算法筛选后的土壤全谱和1~7层小波低频系数的估测模型评价结果
Fig.3-1  黑土有机质实测值与预测值散点图
Fig.3-2  黑土有机质实测值与预测值散点图
[1] Rasmussen C, Heckman K, Wieder W R, et al. Beyond clay:Towards an improved set of variables for predicting soil organic matter content[J]. Biogeochemistry, 2018, 137(5):297-306.
doi: 10.1007/s10533-018-0424-3
[2] 马玥, 姜琦刚, 孟治国, 等. 基于RF-GABPSO混合选择算法的黑土有机质含量估测研究[J]. 光谱学与光谱分析, 2018, 38(1):181-187.
Ma Y, Jiang Q G, Meng Z G, et al. Black soil organic matter content estimation using hybrid selection method based on RF and GABPSO[J]. Spectroscopy and Spectral Analysis, 2018, 38(1):181-187.
[3] 谢文, 赵小敏, 郭熙, 等. 基于RBF组合模型的山地红壤有机质含量光谱估测[J]. 林业科学, 2018, 54(6):16-23.
Xie W, Zhao X M, Guo X, et al. Spectrum based estimation of the content of soil organic matters in mountain red soil using RBF combination model[J]. Scientia Silvae Sinicae, 2018, 54(6):16-23.
[4] 陈红艳, 赵庚星, 李希灿, 等. 基于DWT-GA-PLS的土壤碱解氮含量高光谱估测方法[J]. 应用生态学报, 2013, 24(11):3185-3191.
Chen H Y, Zhao G X, Li X C, et al. Hyper spectral estimation method for soil alkali hydrolysable nitrogen content based on discrete wavelet transform and genetic algorithm in combining with partial least squares[J]. Chinese Journal of Applied Ecology, 2013, 24(11):3185-3191.
[5] 王延仓, 张兰, 王欢, 等. 连续小波变换定量反演土壤有机质含量[J]. 光谱学与光谱分析, 2018, 38(11):207-213.
Wang Y C, Zhang L, Wang H, et al. Quantitative inversion of soil organic matter content based on continuous wavelet transform[J]. Spectroscopy and Spectral Analysis, 2018, 38(11):207-213.
[6] 王延仓, 杨贵军, 朱金山, 等. 基于小波变换与偏最小二乘耦合模型估测北方潮土有机质含量[J]. 光谱学与光谱分析, 2014, 34(7):1922-1926.
Wang Y C, Yang G J, Zhu J S, et al. Estimation of organic matter content of north fluvo-aquic soil based on the coupling model of wavelet transform and partial least squares[J]. Spectroscopy and Spectral Analysis, 2014, 34(7):1922-1926.
[7] 李旭青, 李龙, 庄连英, 等. 基于小波变换和BP神经网络的水稻冠层重金属含量反演[J]. 农业机械学报, 2019, 50(6):226-232.
Li X Q, Li L, Zhuang L Y, et al. Inversion of heavy metal content in rice canopy based on wavelet transform and BP neural network[J]. Transactions of the Chinese Society for Agricultural Machinery, 2019, 50(6):226-232.
[8] 吴迪, 吴洪喜, 蔡景波, 等. 基于无信息变量消除法和连续投影算法的可见-近红外光谱技术白虾种分类方法研究[J]. 红外与毫米波学报, 2009, 28(6):423-427.
Wu D, Wu H X, Cai J B, et al. Classifying the species of exopalaemon by using visible and near infrared spectra with uninformative variable elimination and successive projections algorithm[J]. Journal of Infrared and Millimeter Waves, 2009, 28(6):423-427.
[9] 章海亮, 罗微, 刘雪梅, 等. 应用遗传算法结合连续投影算法近红外光谱检测土壤有机质研究[J]. 光谱学与光谱分析, 2017, 37(2):584-587.
Zhang H L, Luo W, Liu X M, et al. Measurement of soil organic matter with near infrared spectroscopy combined with genetic algorithm and successive projection algorithm[J]. Spectroscopy and Spectral Analysis, 2017, 37(2):584-587.
[10] Peng X, Shi T, Song A, et al. Estimating soil organic carbon using VIS/NIR spectroscopy with SVMR and SPA Methods[J]. Remote Sensing, 2014, 6(4):2699-2717.
doi: 10.3390/rs6042699
[11] 印影. 黑土有机质含量的高光谱估测模型研究[D]. 长春:吉林大学, 2015.
Yin Y. Study on hyper-spectral models for predicting black soil organic matter content[D]. Changchun:Jilin University, 2015.
[12] Sharma M, Pachori R B. A novel approach to detect epileptic seizures using a combination of tunable-Q wavelet transform and fractal dimension[J]. Journal of Mechanics in Medicine and Biology, 2017, 17(4):1740003.
doi: 10.1142/S0219519417400036
[13] Zhao R, Biswas A, Zhou Y, et al. Identifying localized and scale-specific multivariate controls of soil organic matter variations using multiple wavelet coherence[J]. Science of the Total Environment, 2018, 643:548-558.
doi: 10.1016/j.scitotenv.2018.06.210
[14] 陈红艳, 赵庚星, 李希灿, 等. 小波分析用于土壤速效钾含量高光谱估测研究[J]. 中国农业科学, 2012, 45(7):1425-1431.
Chen H Y, Zhao G X, Li X C, et al. Application of wavelet analysis for estimation of soil available potassium content with hyperspectral reflectance[J]. Scientia Agricultura Sinica, 2012, 45(7):1425-1431.
[15] 栾福明, 熊黑钢, 王芳, 等. 基于小波分析的土壤碱解氮含量高光谱反演[J]. 光谱学与光谱分析, 2013, 33(10):2828-2832.
Luan F M, Xiong H G, Wang F, et al. The inversion of soil alkaline hydrolysis nutrient content with hyperspectral reflectance based on wavelet analysis[J]. Spectroscopy and Spectral Analysis, 2013, 33(10):2828-2832.
[16] 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.
Gao H Z, Lu Q P, Ding H Q, 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.
[17] 沈掌泉, 卢必慧, 单英杰, 等. 基于变量选择的偏最小二乘回归法和田间行走式近红外光谱进行土壤碳含量测定研究[J]. 光谱学与光谱分析, 2013, 33(7):1775-1780.
Shen Z Q, Lu B H, Shan Y J, et al. Study on soil carbon estimation by on-the-go near-infrared spectra and partial least squares regression with variable selection[J]. Spectroscopy and Spectral Analysis, 2013, 33(7):1775-1780.
[18] Xiao Y, Jiang Q, Wang B, et al. Object-oriented fusion of RADARSAT-2 polarimetric synthetic aperture Radar and HJ-1A multispectral data for land-cover classification[J]. Journal of Applied Remote Sensing, 2016, 10(2):026021.
doi: 10.1117/1.JRS.10.026021
[1] 王嘉芃, 徐建国, 沈家晓, 张登荣. 德兴铜矿矿山重金属污染修复效果高光谱遥感评价[J]. 自然资源遥感, 2023, 35(3): 284-291.
[2] 郑宗生, 刘海霞, 王振华, 卢鹏, 沈绪坤, 唐鹏飞. 改进3D-CNN的高光谱图像地物分类方法[J]. 自然资源遥感, 2023, 35(2): 105-111.
[3] 张国建, 刘胜震, 孙英君, 俞凯杰, 刘丽娜. 基于弱监督鲁棒性自编码的高光谱异常检测[J]. 自然资源遥感, 2023, 35(2): 167-175.
[4] 孔卓, 杨海涛, 郑逢杰, 李扬, 齐济, 朱沁雨, 杨忠霖. 高光谱遥感图像大气校正研究进展[J]. 自然资源遥感, 2022, 34(4): 1-10.
[5] 张鹏强, 高奎亮, 刘冰, 谭熊. 联合空谱信息的高光谱影像深度Transformer网络分类[J]. 自然资源遥感, 2022, 34(3): 27-32.
[6] 孙肖, 徐林林, 王晓阳, 田野, 王伟, 张中跃. 基于优化K-P-Means解混方法的高光谱图像矿物识别[J]. 自然资源遥感, 2022, 34(3): 43-49.
[7] 孙肖, 彭军还, 赵锋, 王晓阳, 吕洁, 张登峰. 基于空间统计学的高光谱遥感影像主成分选择方法[J]. 自然资源遥感, 2022, 34(2): 37-46.
[8] 晏红波, 韦晚秋, 卢献健, 杨志高, 黎振宝. 基于高光谱特征的土壤含水量遥感反演方法综述[J]. 自然资源遥感, 2022, 34(2): 1-9.
[9] 王茜, 任广利. 高光谱遥感异常信息在阿尔金索拉克地区铜金矿找矿工作中的应用[J]. 自然资源遥感, 2022, 34(1): 277-285.
[10] 曲海成, 王雅萱, 申磊. 多感受野特征与空谱注意力结合的高光谱图像超分辨率算法[J]. 自然资源遥感, 2022, 34(1): 43-52.
[11] 周超凡, 宫辉力, 陈蓓蓓, 雷坤超, 施轹原, 赵宇. 联合WT-RF的津保高铁沿线地面沉降预测[J]. 自然资源遥感, 2021, 33(4): 34-42.
[12] 陈洁, 张立福, 张琳珊, 张红明, 童庆禧. 紫外-可见光水质参数在线监测技术研究进展[J]. 自然资源遥感, 2021, 33(4): 1-9.
[13] 肖烨辉, 宋妮迪, 孟盼盼, 王培俊, 范胜龙. 模型集群分析策略联合ELM的土壤重金属Pb含量预测[J]. 自然资源遥感, 2021, 33(4): 143-152.
[14] 高文龙, 张圣微, 林汐, 雒萌, 任照怡. 煤矿开采中SOM的遥感估算和时空动态分析[J]. 自然资源遥感, 2021, 33(4): 235-242.
[15] 刘咏梅, 范鸿建, 盖星华, 刘建红, 王雷. 基于无人机高光谱影像的NDVI估算植被盖度精度分析[J]. 自然资源遥感, 2021, 33(3): 11-17.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
京ICP备05055290号-2
版权所有 © 2015 《自然资源遥感》编辑部
地址:北京学院路31号中国国土资源航空物探遥感中心 邮编:100083
电话:010-62060291/62060292 E-mail:zrzyyg@163.com
本系统由北京玛格泰克科技发展有限公司设计开发