收藏 ｜ 设为首页 广告服务 ｜ 联系我们 ｜ 在线留言
高级检索

干旱区地理 >

2019 , Vol. 42 >Issue 6: 1404 - 1414

DOI: https://doi.org/10.12118/j.issn.1000-6060.2019.06.20

地球信息科学

基于随机森林算法的土壤有机质含量高光谱检测

展开
  • 1新疆大学资源与环境科学学院智慧城市与环境建模自治区普通高校重点实验室，新疆 乌鲁木齐 830046； 2绿洲生态教育部重点实验室，新疆 乌鲁木齐 830046
包青岭(1993-),男，硕士研究生，新疆伊犁人，主要从事土壤遥感研究. E-mail: 13139805801@163.com

收稿日期: 2019-03-20

  修回日期: 2019-07-18

  网络出版日期: 2019-11-18

基金资助

新疆自治区重点实验室专项基金(2016D03001)；新疆自治区科技支疆项目（201591101）

收起

Hyperspectral detection of soil organic matter content based on random forest algorithm

Expand
  • 1 Key Laboratory of Wisdom City and Environmental Modeling Department of Education,Xinjiang University,Urumqi 830046, Xinjiang,China; 2 Key Laboratory of Oasis Ecology,Xinjiang University,Urumqi 830046,Xinjiang,China

Received date: 2019-03-20

  Revised date: 2019-07-18

  Online published: 2019-11-18

Fold

摘要

为了探讨既能保留光谱信息又能准确对土壤有机质含量进行快速检测。以新疆南部渭干河—库车绿洲内部73个土壤样点及其对应的高光谱数据为研究对象，采用小波变换与数学变换进行光谱数据预处理，分析各小波分解重构光谱在不同有机质含量与不同土壤类型下光谱曲线差异，通过相关分析确定最大小波分解层并筛选敏感波段，结合灰色关联分析与随机森林预测分类模型对各小波分解特征光谱进行重要性分析，最后基于最优特征光谱建立多元线性预测模型并进行分析。结果表明：（1） 耕作土壤与林地土壤光谱曲线波段相较盐渍土壤和荒漠土壤光谱曲线变化较为平缓，同时在水分吸收波段处，盐渍土壤光谱曲线吸收谷最深。（2） 小波变换分解光谱与土壤有机质含量的相关性随着分解层数增加呈现先减后增趋势，在第6层中，特征光谱曲线与敏感波段数量变化趋于稳定，确定为小波变换最大分解层。（3） 随机森林模型相比灰色关联分析对于各小波分解层因子的筛选符合预期，按照对土壤有机质含量影响从高到低排序为L3-(1/LgR)′、L4-(1/LgR)′、L6-(1/LgR)′、L5-(1/LgR)′、L2-(1/LgR)′、L0-1/LgR、L1-1/LgR。（4）在小波分解光谱中，中频范围特征光谱对干旱区土壤有机质含量的估测能力优于高频与低频范围特征光谱，同时基于L-MC建立的模型精度最高。研究表明：基于机器学习分类方法结合小波分解的土壤光谱有机质含量监测，可以有效的减少噪声波段干扰，并提高特征波段的分类预测精度。

关键词： ; font-size:10.5pt; ">高光谱; ; Times New Roman"; ,serif; font-size:10.5pt; "> ; font-size:10.5pt; ">土壤有机质含量; ; Times New Roman"; ,serif; font-size:10.5pt; "> ; font-size:10.5pt; ">小波变换; ; Times New Roman"; ,serif; font-size:10.5pt; "> ; font-size:10.5pt; ">随机森林

本文引用格式

包青岭, 丁建丽, 王敬哲, 蔡亮红 . 基于随机森林算法的土壤有机质含量高光谱检测 [J]. 干旱区地理, 2019 , 42(6) : 1404 -1414 . DOI: 10.12118/j.issn.1000-6060.2019.06.20

Abstract

In order to explore how to retain the spectral information and accurately detect the soil organic matter content, this paper investigated the possibility of using spectral processing techniques such as wavelet decomposition and random forest method to estimate the soil organic matter content and analyze the spectral curves of different wavelet decomposition reconstruction spectra in different soil types using spectroscopy data. This study took the soil samples as the study objects which were collected in Weigan River Oasis of Kuqa County, a typical arid area oasis at north-central of the Tarim Basin in Xinjiang, China. The soil organic matter content of these samples was determined. The ASD Field Spec FR was used to measure the soil samples’spectrum, and the spectral data were preprocessed by wavelet decomposition and mathematical transformation. Discrete wavelet transform (DWT) has the function of multi-scale analysis, which can transform multi-scale wavelet decomposition of soil near infrared spectroscopy data to analyze the spectral curves of different wavelet decomposition reconstruction spectra in different organic matter content and different soil types. The correlation analysis was used to determine the maximum wavelet decomposition layer and filter sensitive bands. Finally, a multi-variant linear prediction model about soil organic matter content was established based on the optimal characteristic spectrum produced by combining grey correlation analysis, random forest method to analyze the significance of different wavelet decomposition characteristic spectra. The results showed as follows: (1) The spectral reflectance of each wavelet decomposed is decreased with the increase of organic matter content. At the same time, the spectral curve of cultivated soil and forest soil shows a more gradual change than that of the saline soil and desert soil. (2) The correlation between the decomposition spectrum of the wavelet transform and the soil organic matter content is decreased first and then increased with the increase of the decomposition layer. In the sixth layer, the characteristic spectral curve and the number of sensitive bands tend to be stable, which helps to determine this layer as the largest decomposition layer of wavelet transform. (3) Compared with the gray correlation analysis, the random forest model is in line with the expectation for screening the factors of wavelet decomposition at each layer, and it comes a list of descending order according to the impact on soil organic matter content as follows: L3-(1/LgR)′、L4-(1/LgR)′、L6-(1/LgR)′、L5-(1/LgR)′、L2-(1/LgR)′、L0-1/LgR、L1-1/LgR. (4) Combining all SOM estimation models for statistical analysis,the model based on L-MC has the highest accuracy. The research shows that the monitoring of soil spectral organic matter content based on machine learning classification method combined with wavelet decomposition can effectively reduce noise band interference and improve the classification prediction accuracy of feature bands. The random forest prediction classification model has significant advantages over the traditional linear prediction classification model, such as gray correlation analysis. The random forest model not only outperforms the grey correlation analysis in statistical results, but also shows better reliability and stability in predicting ability. The results could provide scientific reference and support for the study of soil nutrients in the arid zone and local precision agriculture.

Key words： ; font-size:10.5pt; ">; Times New Roman"; ,serif; ">hyperspectral; soil organic matter content; wavelet transform; random forest

参考文献

［1］张勇,庞学勇,包维楷,等.土壤有机质及其研究方法综述［J］.世界科技研究与发展,2005.27(5):72-78.［ZHANG Yong,PANG Xueyong,BAO Weikai,et al.A review of soil organic matter and its research methods［J］.World Sci-Tech R&D,2005,27(5):72-78.］ ［2］程朋根,吴剑,李大军,等.土壤有机质高光谱遥感和地统计定量预测［J］.农业工程学报,2009,25(3):142-147.［CHENG Penggen,WU Jian,LI Dajun,et al.Quantitative prediction of soil organic matter content using hyper spectral remote sensing and geo-statistics［J］.Transactions of the Chinese Society of Agricultural Engineering,2009,25(3):142-147.］ ［3］何挺,王静,林宗坚,等.土壤有机质光谱特征研究［J］.武汉大学学报(信息科学版),2006,31(11):975-979.［HE Ting,WANG Jing,LIN Zongjian,et al.Spectral features of soil organic matter［J］.Geomatics and Information Science of Wuhan University (Information Science Edition),2006,31(11):975-979.］ ［4］刘磊,沈润平,丁国香.基于高光谱的土壤有机质含量估算研究［J］.光谱学与光谱分析,2011,31(3):762-766.［LIU Lei,SHEN Ruiping,Ding Guoxiang.Studies on the estimation of soil organic matter content based on hyper-spectrum［J］.Spectroscopy and Spectral Analysis,2011,31(3):762-766.］ ［5］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 Qin,JIANG Xueqin,LI Xican,et al.Comparison on inversion model of soil organic matter content based on hyperspectral data［J］.Transactions of the Chinese Society for Agricultural Machinery,2017,48(3):164-172.］ ［6］郑曼迪,熊黑钢,乔娟峰,等.基于宽波段与窄波段综合光谱指数的土壤有机质遥感反演［J］.激光与光电子学进展,2018,55(7).［ZHENG Mandi,XIONG Heigang,QIAO Juanfeng,et al.Remote sensing inversion of soil organic matter based on broad band and narrow band comprehensive spectral index［J］.Laser & Optoelectronics Progress,2018,55(7).］ ［7］郑曼迪,熊黑钢,乔娟峰,等.基于高光谱的不同人类干扰程度下荒漠土壤有机质含量估算模型［J］.干旱区地理,2018,41(2):167-175.［ZHENG Mandi,XIONG Heigang,QIAO Juanfeng,et al.Hyperspectral based estimation model about organic matter in desert soil at different levels of human disturbance［J］.Arid Land Geography,2018,41(2):167-175.］ ［8］彭杰,张杨珠,庞新安,等.新疆南部土壤有机质含量的高光谱特征分析［J］.干旱区地理,2010,33(5):740-746.［PENG Jie,ZHANG Yangzhu,PANG Xinan,et al.Hyperspectral features of soil organic matter content in south Xingjiang［J］.Arid Land Geography,2010,33(5):740-746.］ ［9］沈润平,丁国香,魏国栓,等.基于人工神经网络的土壤有机质含量高光谱反演［J］.土壤学报,2009,46(3):391-397.［SHEN Ruiping,DING Guoxiang,WEI Guoshuan,et al.Retrieval of soil organic matter content from hyper-spectrum based on ANN［J］.Acta Pedologoca Sinica,2009,46(3):391-397.］ ［10］于雷,洪永胜,朱亚星,等.去除土壤水分对高光谱估算土壤有机质含量的影响［J］.光谱学与光谱分析,2017,37(7):2146-2151.［YU Lei,Hong Yongsheng,ZHU Yaxing,et al.Removing the effect of soil moisture content on hyperspectral reflectance for the estimation of soil organic matter content［J］.Spectroscopy and Spectral Analysis,2017,37(7):2146-2151.］ ［11］MORGAN C L S,WAISER T H,BROWN D J,et al.Simulated in situ characterization of soil organic and inorganic carbon with visible near-infrared diffuse reflectance spectroscopy［J］.Geoderma,2009,151(3-4):249-256. ［12］RIENZI E A,MIJATOVIC B,MUELLER T G,et al.Prediction of soil organic carbon under varying moisture levels using reflectance spectroscopy［J］.Soil Science Society of America Journal,2014,78(3):958-967. ［13］NOCITA M,STEVENS A,NOON C,et al.Prediction of soil organic carbon for different levels of soil moisture using Vis-NIR spectroscopy［J］.Geoderma,2013,199:37-42. ［14］LIAO Q H,GU X H,LI C J,et al.Estimation of fluvo-aquic soil organic matter content from hyperspectral reflectance based on continuous wavelet transformation［J］.Transactions of the Chinese Society of Agricultural Engineering,2012,28(23):132-139. ［15］YANG H F,QIAN Y R,YANG F,et al.Using wavelet transform of hyperspectral reflectance data for extracting spectral features of soil organic carbon and nitrogen［J］.Soil Science,2012,177(11):674-681. ［16］LIN L,WANG Y,TENG J Y,et al.Hyperspectral analysis of soil organic matter in coal mining regions using wavelets,correlations,and partial least squares regression［J］.Environmental Monitoring & Assessment,2016,188(2):97. ［17］张锐,李兆富,潘剑君.小波包—局部最相关算法提高土壤有机碳含量高光谱预测精度［J］.农业工程学报,2017,33(1):175-181.［ZHANG Rui,LI Zhaofu.PAN Jianjun.Coupling discrete wavelet packet transformation and local correlation maximization improving prediction accuracy of soil organic carbon based on hyperspectral reflectance［J］.Transactions of the Chinese Society of Agricultural Engineering,2017,33(1):175-181.］ ［18］陈红艳,赵庚星,李希灿,等.基于小波变换的土壤有机质含量高光谱估测［J］.应用生态学报,2011,22(11):2935-2942.［CHEN Hongyan,ZHAO Gengxing,LI Xican,et al.Hyperspectral estimation of soil organic matter content based on wavelet transformation［J］.Chinese Journal of Applied Ecology,2011,22(11):2935-2942.］ ［19］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 Yancang,YANG Guijun,ZHU Jinshan,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.］ ［20］蔡亮红,丁建丽.基于高光谱多尺度分解的土壤含水量反演［J］.激光与光电子学进展,2018,55(1):013001.［CAI Lianghong,DING Jianli.Inversion of soil moisture content based on hyperspectral multi-scale［J］.Laser & Optoelectronics Progress,2018,55(1):013001.］ ［21］唐梦迎,丁建丽,夏楠,等.干旱区典型绿洲土壤有机质含量分布特征及其影响因素［J］.土壤学报,2017,54(3):759-766 .［TANG Mengying,DING Jianli,XIA Nan,et al.Distribution of soil organic matter content and its affecting factors in oases typical of arid region［J］.Acta Pedologica Sinica,2017,54(3):759-766］ ［22］刘广崧,蒋能慧,张连第.土壤理化分析与剖面描述［M］.北京:中国标准出版社,1996:166-167.［LIU Guangsong,JIANG Nenghui,ZHANG Liandi.Soil physical and chemical analysis and profile description［M］.Beijing: Standrds Press of China,1996:166-167.］ ［23］中国土壤学会农业化学专业委员会.土壤农业化学常规分析方法［M］.北京:科学出版社,1989.［Agricultural chemical specialized committee of china soil society［M］.Conventional analytical method of soil agricultural chemistry［M］.Beijing:Science Press,1989.］ ［24］陈至坤,张菡洁,王玉田,等.基于小波变换的矿物油荧光光谱数据处理方法［J］.激光杂志,2016,37(10):78-81.［CHEN Zhikun,ZHANG Hanjie,WANG Yutian,et al.Fluorescence spectral date of mineral oil processing based on wavelet transform［J］.Laser Journal,2016,37(10):78-81.］ ［25］刘燕德,欧阳爱国,应义斌.小波分析用于光谱信号处理及其在Matlab中的实现［J］.传感技术学报,2006,19(3): 821-823.［LIU Yande,OUYANG Aiguo,YING Yibin.Application of wavelet analysis in signal process using Matlab［J］.Chinese Journal of Sensors and Actuators,2006,19(3): 821-823.］ ［26］沈润平,郭佳,张婧娴,等.基于随机森林的遥感干旱监测模型的构建［J］.地球信息科学学报,2017,19(1): 125-133.［SHEN Ruiping,Guo Jia,ZHANG Jingxian,et al.Construction of a drought monitoring model using the random forest based remote sensing［J］.Journal of Geoinformation Science,2017,19(1):125-133.］ ［27］VAUDOUR E,GILLIOT J M,BEL L,et al.Regional prediction of soil organic carbon content over temperate croplands using visible near-infrared airborne hyperspectral imagery and synchronous field spectral［J］.International Journal of Applied Earth Observation & Geoinformation,2016,49:24-3. ［28］SHI Z,WANG Q L,PENG J,et al.Development of a national VNIR soilspectral library for soil classification and prediction of organic matter concentrations［J］.Science China Earth Sciences,2014,57(7):1671-1680. ［29］高志海,白黎娜,王琫瑜,等.荒漠化土地土壤有机质含量的实测光谱估测［J］.林业科学,2011,47(6):9-16.［GAO Zhihai,BAI Lina,WANG Bingyu,et al.Estimation of soil organic matter content in desertified lands using measured soil spectral data［J］.Scientia Silvae Sinicae,2011,47(6):9-16.］ ［30］李洪.官厅水库消落带土壤有机质分布特征及其高光谱反演研究［D］.北京:首都师范大学,2014:40-60.［LI Hong.Distribution characteristics of soil organic matter and its hyperspectral retrieval in the water-level-fluctuating zone of guanting reservoir［D］.Beijing:Capital Normal University,2014:40-60.］
Options
文章导航

/

〈 〉