基于sCARS-RF算法的高光谱估算土壤有机质含量

李冠稳; 高小红; 肖能文; 肖云飞

doi:10.3788/fgxb20194008.1030

您当前的位置：

首页 >

文章列表页 >

基于sCARS-RF算法的高光谱估算土壤有机质含量

发光学应用及交叉前沿 | 更新时间：2020-08-12

- 基于sCARS-RF算法的高光谱估算土壤有机质含量
- Estimation Soil Organic Matter Contents with Hyperspectra Based on sCARS and RF Algorithms
- 发光学报 2019年40卷第8期页码：1030-1039
- 作者机构：
  
  1. 青海师范大学地理科学学院,青海西宁,810008
  2. 青海省自然地理与环境过程重点实验室,青海西宁,810008
  3. 中国环境科学研究院北京,100012
- 作者简介：
- 基金信息：
  
  国家自然科学基金（41550003）资助项目()
- DOI：10.3788/fgxb20194008.1030
  中图分类号： S151.9;TP79
- 收稿日期：2018-09-20，
  
  修回日期：2018-11-06，
  
  网络出版日期：2018-11-28，
  
  纸质出版日期：2019-08-05
- 稿件说明：
移动端阅览
李冠稳, 高小红, 肖能文等. 基于sCARS-RF算法的高光谱估算土壤有机质含量[J]. 发光学报, 2019,40(8): 1030-1039

LI Guan-wen, GAO Xiao-hong, XIAO Neng-wen etc. Estimation Soil Organic Matter Contents with Hyperspectra Based on sCARS and RF Algorithms[J]. Chinese Journal of Luminescence, 2019,40(8): 1030-1039
李冠稳, 高小红, 肖能文等. 基于sCARS-RF算法的高光谱估算土壤有机质含量[J]. 发光学报, 2019,40(8): 1030-1039 DOI： 10.3788/fgxb20194008.1030.

LI Guan-wen, GAO Xiao-hong, XIAO Neng-wen etc. Estimation Soil Organic Matter Contents with Hyperspectra Based on sCARS and RF Algorithms[J]. Chinese Journal of Luminescence, 2019,40(8): 1030-1039 DOI： 10.3788/fgxb20194008.1030.

摘要

针对土壤高光谱数据量大、存在光谱信息冗余和重叠现象，应用稳定竞争性自适应重加权采样策略挑选特征变量，结合偏最小二乘回归和随机森林建立土壤有机质含量估算模型，并与竞争性自适应重加权算法、迭代保留有效信息变量、连续投影算法和遗传算法所得结果进行比较。结果显示，5种变量选择算法挑选的特征变量主要分布在1 900~2 400 nm的近红外光谱区域。RF模型的预测效果优于PLSR模型；与PLSR模型相比，RF模型鲁棒性更好，对异常值和噪声的敏感度更低。基于sCARS算法挑选的特征变量建立RF模型，变量数为51个，仅占全波段的2.55%，验证集

=0.958，获得的RPD为4.7，能够很好地预测SOM含量。

Abstract

Aiming at the phenomenon of large amount of soil hyperspectral data

spectral information redundancy and overlap

a model for estimating soil organic matter content is established by using a stable competitive adaptive reweighting sampling strategy and combining partial least squares regression with random forest. The results are compared with those obtained by competitive adaptive reweighting algorithm

iterative iteratively retains information variables

successive projections algorithm and genetic algorithm. The five variable selection algorithms selecting the characteristic variables mainly distribute in the near infrared spectral region of 1 900-2 400 nm. The prediction effect of the RF model is better than that of the PLSR model. Compared with the PLSR model

the RF model has better robustness

lower sensitivity to outliers and noise. The RF model is established based on the characteristic variables selected by sCARS algorithm. The number of variables is 51

accounting for only 2.55% of the whole band. The verification set

is 0.958

and the RPD is 4.7

which can predict the SOM content very well.

关键词

Keywords

references

CROFT H,KUHN N J,ANDERSON K. On the use of remote sensing techniques for monitoring spatio-temporal soil organic carbon dynamics in agricultural systems[J]. CATENA, 2012,94:64-74.

吴才武,夏建新,段峥嵘. 土壤有机质测定方法述评与展望[J]. 土壤, 2015,47(3):453-460. WU C W,XIA J X,DUAN Z R. Review on detection methods of soil organic matter (SOM)[J]. Soil, 2015,47(3):453-460. (in Chinese)

杨梅花,赵小敏,方倩,等. 基于可见-近红外光谱变量选择的土壤全氮含量估测研究[J]. 中国农业科学, 2014,47(12):2374-2383. YANG M H,ZHAO X M,FANG Q,et al.. Study on soil total N estimation by Vis-NIR spectra with variable selection[J]. Sci. Agric. Sinica, 2014,47(12):2374-2383. (in Chinese)

汪六三,鲁翠萍,王儒敬,等. 土壤碱解氮含量可见/近红外光谱预测模型优化[J]. 发光学报, 2018,39(7):1016-1023. WANG L S,LU C P,WANG R J,et al.. Optimization for Vis/NIRS prediction model of soil available nitrogen content[J]. Chin. J. Lumin., 2018,39(7):1016-1023. (in Chinese)

叶勤,姜雪芹,李西灿,等. 基于高光谱数据的土壤有机质含量反演模型比较[J]. 农业机械学报, 2017,48(3):164-172. YE Q,JIANG X Q,LI X C,et al.. Comparison on inversion model of soil organic matter content based on hyperspectral data[J]. Trans. Chin. Soc. Agric. Mach., 2017,48(3):164-172. (in Chinese)

刘亚秋,陈红艳,王瑞燕,等. 基于可见/近红外光谱的黄河口区土壤盐分及其主要离子的定量分析[J]. 中国农业科学, 2016,49(10):1925-1935. LIU Y Q,CHEN H Y,WANG R Y,et al.. Quantitative analysis of soil salt and its main ions based on visible/near Infrared spectroscopy in estuary area of Yellow River[J]. Sci. Agric. Sinica, 2016,49(10):1925-1935. (in Chinese)

WANG X M,CHEN Y Y,GUO L,et al.. Construction of the calibration set through multivariate analysis in visible and near-infrared prediction model for estimating soil organic matter[J]. Remote Sens., 2017,9(3):201-1-18.

宋相中. 近红外光谱定量分析中三种新型波长选择方法研究[D]. 北京:中国农业大学, 2017. SONG X Z. Research of Three New Wavelength Selection Methods in Near Infrared Spectroscopy Quantitative Analysis Area[D]. Beijing:China Agricultural University, 2017. (in Chinese)

林志丹,汪玉冰,王儒敬,等. 波长优选对土壤有机质含量可见光/近红外光谱模型的优化[J]. 发光学报, 2016,37(11):1428-1435. LIN Z D,WANG Y B,WANG R J,et al.. Improvements of Vis-NIRS model in the prediction of soil organic matter content using wavelength optimization[J]. Chin. J. Lumin., 2016,37(11):1428-1435. (in Chinese)

LI Y K,JING J. A consensus PLS method based on diverse wavelength variables models for analysis of near-infrared spectra[J]. Chemom. Intell. Lab. Syst., 2014,130:45-49.

LIU K,CHEN X J,LI L M,et al.. A consensus successive projections algorithm-multiple linear regression method for analyzing near infrared spectra[J]. Anal. Chim. Acta, 2015,858:16-23.

LIN Z D,WANG Y B,WANG R J,et al.. Improvements of the vis-NIRS model in the prediction of soil organic matter content using spectral pretreatments,sample selection,and wavelength optimization[J]. J. Appl. Spectrosc., 2017,84(3):529-534.

朱亚星,于雷,洪永胜,等. 土壤有机质高光谱特征与波长变量优选方法[J]. 中国农业科学, 2017,50(22):4325-4337. ZHU Y X,YU L,HONG Y S,et al.. Hyperspectral features and wavelength variables selection methods of soil organic matter[J]. Sci. Agric. Sinica, 2017,50(22):4325-4337. (in Chinese)

张晓羽,李庆波,张广军. 基于稳定竞争自适应重加权采样的光谱分析无标模型传递方法[J]. 光谱学与光谱分析, 2014,34(5):1429-1433. ZHANG X Y,LI Q B,ZHANG G J. Calibration transfer without standards for spectral analysis based on stability competitive adaptive reweighted sampling[J]. Spectrosc. Spect. Anal., 2014,34(5):1429-1433. (in Chinese)

刘国海,夏荣盛,江辉,等. 一种基于SCARS策略的近红外特征波长选择方法及其应用[J]. 光谱学与光谱分析, 2014,34(8):2094-2097. LIU G H,XIA RS,JIANG H,et al.. A wavelength selection approach of near infrared spectra based on SCARS strategy and its application[J]. Spectrosc. Spect. Anal., 2014,34(8):2094-2097. (in Chinese)

丁泊洋,陈万超,张飞宇,等. 波长选择SCARS和偏最小二乘法建立香菇中多糖含量预测的近红外光谱模型[J]. 天然产物研究与开发, 2017,29(1):125-128. DING B Y,CHEN W C,ZHANG F Y,et al.. Establishment of near infrared spectral model for the prediction of the content of Lentinan using wavelength selection SCARS and partial least square analysis[J]. Nat. Prod. Res. Dev., 2017,29(1):125-128. (in Chinese)

李冠稳,高小红,杨灵玉,等. 不同粒径土壤有机质含量可见光-近红外光谱估算研究-以湟水流域为例[J]. 土壤通报, 2017,48(6):1360-1370. LI G W,GAO X H,YANG L Y,et al.. Estimating soil organic matter contents in different soil particle size fractions by visible and near-infrared reflectance spectrum-a case study of the Huangshui River Basin[J]. Chin. J. Soil Sci., 2017,48(6):1360-1370. (in Chinese)

ABDEL RAHMAN A M,PAWLING J,RYCZKO M,et al.. Targeted metabolomics in cultured cells and tissues by mass spectrometry:method development and validation[J]. Anal. Chim. Acta, 2014,845:53-61.

惠光艳,孙来军,王佳楠,等. 可见-近红外光谱的小麦硬度预测模型预处理方法的研究[J]. 光谱学与光谱分析,2016,36(7):2111-2116. HUI G Y,SUN L J,WANG J N,et al.. Research on the pre-processing methods of wheat hardness prediction model based on visible-near infrared spectroscopy[J]. Spectrosc. Spect. Anal., 2016,36(7):2111-2116. (in Chinese)

CHANG C W,LAIRD D A,MAUSBACH M J,et al.. Near-infrared reflectance spectroscopy-principal components regression analyses of soil properties[J]. Soil Sci. Soc. Amer. J., 2001,65(2):480-490.

YUN Y H,WANG W T,TAN M L,et al.. A strategy that iteratively retains informative variables for selecting optimal variable subset in multivariate calibration[J]. Anal. Chim. Acta, 2014,807:36-43.

VOHLAND M,LUDWIG M,HARBICH M,et al.. Using variable selection and wavelets to exploit the full potential of visible-near infrared spectra for predicting soil properties[J]. J. Near Infrared Spectrosc., 2016,24(3):255-269.

张建新,张银露,胡旭东. 光谱优化处理结合多层次支持向量机的混合染液浓度检测方法[J]. 纺织学报, 2017,38(7):90-94. ZHANG J X,ZHANG Y L,HU X D. Method of mixed dye liquor concentration detection based on spectral optimization and multi-level support vector machine[J]. J. Text. Res., 2017,38(7):90-94. (in Chinese)

杨爱霞,丁建丽,李艳红,等. 基于可见-近红外光谱变量选择的荒漠土壤全磷含量估测研究[J]. 光谱学与光谱分析, 2016,36(3):691-696. YANG A X,DING J L,LI Y H,et al.. Study on estimation of deserts soil total phosphorus content by Vis-NIR spectra with variable selection[J]. Spectrosc. Spect. Anal., 2016,36(3):691-696. (in Chinese)

ISLAM K,SINGH B,MCBRATNEY A. Simultaneous estimation of several soil properties by ultra-violet,visible,and near-infrared reflectance spectroscopy[J]. Aust. J. Soil Res., 2003,41(6):1101-1114.

DOUGLAS R K,NAWAR S,ALAMAR M C,et al.. Rapid prediction of total petroleum hydrocarbons concentration in contaminated soil using vis-NIR spectroscopy and regression techniques[J]. Sci. Total Environ., 2018,616-617:147-155.

浏览量

204

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

利用改进自动编码器光谱法预测土壤有机质