土壤有机质含量地面高光谱估测模型对比分析
|
摘要
采用高光谱技术获得的数据进行土壤有机质含量的反演和估测是近年来的研究热点。为确定有效的估测建模方法,利用地面实测的土壤高光谱反射率及有机质含量等数据,采用小波分析方法实现去噪,包络线去除法实现建模参数提取和数据量压缩,结合多种不同的数据变换方法,利用BP神经网络法、多元线性回归法及最小二乘回归法建立不同的估测模型。对比发现,BP神经网络模型的估测效果优于回归模型,其中结合对数的平方变换和神经网络所建立的模型为最优估测模型,模型的决定系数达到0. 933,检验样本的均方根误差达到0. 069。实验证明,BP神经网络+对数的平方变换模型的学习机制适用于土壤有机质含量地面高光谱估测且效果好。通过在建模因子层面上进行数据变换建立了较好的估测模型,其研究方法、模型和结论,对土壤有机质含量地面高光谱估测具有一定的参考意义。
Using the data obtained by hyperspectral techniques to estimate the content of soil organic matter is a hotspot in recent years.For the purpose of determining the effective estimation modeling method,specific data such as reflectance obtained by hyperspectral on ground and organic matter content were used in this paper.Wavelet analysis was used to remove the noise,and continuum removal was used to extract the parameters and compress the data.Combining a variety of different data transformation methods and utilizing BP neural networks,multiple linear regression(MLR) and least squares regression(LSR),many different estimation models of soil were established.It is found that the neural network method is superior to the regression model among various data transformation methods after comparing different estimation models established by the three modeling methods.The optimal estimation model is the model established by the combination of logarithmic square transformation and neural network.The R2 of the model is 0.933 and the RMSE is 0.069.The authors creatively carried out the data transformation at the modeling factor level and established the good estimation model.It is shown that the learning mechanism of BP + LS model is suitable for hyperspectral estimation of soil organic matter and works well.The methods,models and conclusions of this paper have some reference significance for the hyperspectral estimation of soil organic matter.
Using the data obtained by hyperspectral techniques to estimate the content of soil organic matter is a hotspot in recent years.For the purpose of determining the effective estimation modeling method,specific data such as reflectance obtained by hyperspectral on ground and organic matter content were used in this paper.Wavelet analysis was used to remove the noise,and continuum removal was used to extract the parameters and compress the data.Combining a variety of different data transformation methods and utilizing BP neural networks,multiple linear regression(MLR) and least squares regression(LSR),many different estimation models of soil were established.It is found that the neural network method is superior to the regression model among various data transformation methods after comparing different estimation models established by the three modeling methods.The optimal estimation model is the model established by the combination of logarithmic square transformation and neural network.The R2 of the model is 0.933 and the RMSE is 0.069.The authors creatively carried out the data transformation at the modeling factor level and established the good estimation model.It is shown that the learning mechanism of BP + LS model is suitable for hyperspectral estimation of soil organic matter and works well.The methods,models and conclusions of this paper have some reference significance for the hyperspectral estimation of soil organic matter.
引文
[1]王晓.土壤含水量高光谱特性与估测模型研究[D].泰安:山东农业大学,2012.Wang X.Studies on Soil Moisture Hyper-spectrum Characteristics and Estimating Model[D].Taian:Shandong Agricultural University,2012.
[2]邱华旭,黄张裕,李希灿.土壤性质指标光谱反演数据变换模型研究[J].测绘科学,2013,38(3):131-133.Qiu H X,Huang Z Y,Li X C.Data transformation model analysis on spectral retrieved deduction of soil properties index[J].Science of Surveying and Mapping,2013,38(3):131-133.
[3]郭超凡,郭逍宇.基于可见光波段包络线去除的湿地植物叶片叶绿素估算[J].生态学报,2016,36(20):6538-6546.Guo C F,Guo X Y.Estimation of wetland plant leaf chlorophyll content based on continuum removal in the visible domain[J].Acta Ecologica Sinica,2016,36(20):6538-6546.
[4]Kokaly R F,Clark R N.Spectroscopic determination of leaf biochemistry using band-depth analysis of absorption features and stepwise multiple linear regression[J].Remote Sensing of Environment,1999,67(3):267-287.
[5]陈增文,陈光水,钟羡芳,等.基于高光谱遥感的土壤有机碳含量估算研究进展[J].亚热带资源与环境学报,2009,4(1):78-87.Chen Z W,Chen G S,Zhong X F,et al.Review on estimation of soil organic carbon content based on hyperspectral measurements[J].Journal of Subtropical Resources and Environment,2009,4(1):78-87.
[6]彭杰,张杨珠,周清,等.土壤理化特性与土壤光谱特征关系的研究进展[J].土壤通报,2009,40(5):1204-1208.Peng J,Zhang Y Z,Zhou Q,et al.The progress on the relationship physics-chemistry properties with spectrum characteristic of the soil[J].Chinese Journal of Soil Science,2009,40(5):1204-1208.
[7]廖钦洪,顾晓鹤,李存军,等.基于连续小波变换的潮土有机质含量高光谱估算[J].农业工程学报,2012,28(23):132-139.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.
[8]Liu H J,Zhang Y Z,Zhang B,et al.Novel hyperspectral reectance models for estimating black-soil organic matter in Northeast China[J].Environmental Monitoring and Assessment,2009,154(1-4):147-154.
[9]Karnieli A,Verchovsky I,Hall J K,et al.Geographic information system for semi-detailed mapping of soils in semi-arid region[J].Geocarto International,1998,13(3):29-42.
[10]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 R P,Ding G X,Wei G S,et al.Retrieval of soil organic matter content from hyper-spectrum based on ANN[J].Acta Pedologica Sinica,2009,46(3):391-397.
[11]于雷,洪永胜,周勇,等.连续小波变换高光谱数据的土壤有机质含量反演模型构建[J].光谱学与光谱分析,2016,36(5):1428-1433.Yu L,Hong Y S,Zhou Y,et al.Inversion of soil organic matter content using hyperspectral data based on continuous wavelet transformation[J].Spectroscopy and Spectral Analysis,2016,36(5):1428-1433.
[12]彭小婷,高文秀,王俊杰.基于包络线去除和偏最小二乘的土壤参数光谱反演[J].武汉大学学报(信息科学版),2014,39(7):862-866.Peng X T,Gao W X,Wang J J.Inversion of soil parameters from hyperspectra based on continuum removal and partial least squares regression[J].Geomatics and Information Science of Wuhan University,2014,39(7):862-866.
[13]孔玲军.MATLAB小波分析超级学习手册[M].北京:人民邮电出版社,2014:100-160.Kong L J.Super Learning Manual of Wavelet Analysis Based on MATLAB[M].Beijing:Posts and Telecom Press,2014:100-160.
[14]Ben-Dor E,Banin A.Visible and near infrared(0.4-1.1μm)analysis of arid and semiarid soil[J].Remote Sensing of Environment,1994,48(3):261-274.
[15]李希灿,王静,李玉环,等.基于模糊集分析的土壤质量指标高光谱反演[J].地理与地理信息科学,2008,24(4):25-28.Li X C,Wang J,Li Y H,et al.High spectral retrieved deduction of soil quality index based on fuzzy sets analysis[J].Geography and Geo-Information Science,2008,24(4):25-28.
[16]沈士喆,张小龙,衡伟.一种自适应阈值的预筛选Harris角点检测方法[J].数据采集与处理,2011,26(2):207-213.Shen S Z,Zhang X L,Heng W.Improved Harris corner detection algorithm based on auto-adaptive threshold and pre-selection[J].Journal of Data Acquisition and Processing,2011,26(2):207-213.
[17]邓小炼,王长耀,亢庆,等.一种基于角点提取的遥感影像地面控制点自适应匹配算法[J].宇航学报,2006,27(1):45-50,88.Deng X L,Wang C Y,Kang Q,et al.An adaptive matching algorithm for ground control point of remote sensing image based on corner extraction[J].Journal of Astronautics,2006,27(1):45-50,88.
[18]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 T,Wang J,Lin Z J,et al.Spectral features of soil organic matter[J].Geomatics and Information Science of Wuhan University,2006,31(11):975-979.
[19]郭斗斗,黄绍敏,张水清,等.多种潮土有机质高光谱预测模型的对比分析[J].农业工程学报,2014,30(21):192-200.Guo D D,Huang S M,Zhang S Q,et al.Comparative analysis of various hyperspectral prediction models of fluvo-aquicsoil organic matter[J].Transactions of the Chinese Society of Agricultural Engineering,2014,30(21):192-200.
[2]邱华旭,黄张裕,李希灿.土壤性质指标光谱反演数据变换模型研究[J].测绘科学,2013,38(3):131-133.Qiu H X,Huang Z Y,Li X C.Data transformation model analysis on spectral retrieved deduction of soil properties index[J].Science of Surveying and Mapping,2013,38(3):131-133.
[3]郭超凡,郭逍宇.基于可见光波段包络线去除的湿地植物叶片叶绿素估算[J].生态学报,2016,36(20):6538-6546.Guo C F,Guo X Y.Estimation of wetland plant leaf chlorophyll content based on continuum removal in the visible domain[J].Acta Ecologica Sinica,2016,36(20):6538-6546.
[4]Kokaly R F,Clark R N.Spectroscopic determination of leaf biochemistry using band-depth analysis of absorption features and stepwise multiple linear regression[J].Remote Sensing of Environment,1999,67(3):267-287.
[5]陈增文,陈光水,钟羡芳,等.基于高光谱遥感的土壤有机碳含量估算研究进展[J].亚热带资源与环境学报,2009,4(1):78-87.Chen Z W,Chen G S,Zhong X F,et al.Review on estimation of soil organic carbon content based on hyperspectral measurements[J].Journal of Subtropical Resources and Environment,2009,4(1):78-87.
[6]彭杰,张杨珠,周清,等.土壤理化特性与土壤光谱特征关系的研究进展[J].土壤通报,2009,40(5):1204-1208.Peng J,Zhang Y Z,Zhou Q,et al.The progress on the relationship physics-chemistry properties with spectrum characteristic of the soil[J].Chinese Journal of Soil Science,2009,40(5):1204-1208.
[7]廖钦洪,顾晓鹤,李存军,等.基于连续小波变换的潮土有机质含量高光谱估算[J].农业工程学报,2012,28(23):132-139.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.
[8]Liu H J,Zhang Y Z,Zhang B,et al.Novel hyperspectral reectance models for estimating black-soil organic matter in Northeast China[J].Environmental Monitoring and Assessment,2009,154(1-4):147-154.
[9]Karnieli A,Verchovsky I,Hall J K,et al.Geographic information system for semi-detailed mapping of soils in semi-arid region[J].Geocarto International,1998,13(3):29-42.
[10]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 R P,Ding G X,Wei G S,et al.Retrieval of soil organic matter content from hyper-spectrum based on ANN[J].Acta Pedologica Sinica,2009,46(3):391-397.
[11]于雷,洪永胜,周勇,等.连续小波变换高光谱数据的土壤有机质含量反演模型构建[J].光谱学与光谱分析,2016,36(5):1428-1433.Yu L,Hong Y S,Zhou Y,et al.Inversion of soil organic matter content using hyperspectral data based on continuous wavelet transformation[J].Spectroscopy and Spectral Analysis,2016,36(5):1428-1433.
[12]彭小婷,高文秀,王俊杰.基于包络线去除和偏最小二乘的土壤参数光谱反演[J].武汉大学学报(信息科学版),2014,39(7):862-866.Peng X T,Gao W X,Wang J J.Inversion of soil parameters from hyperspectra based on continuum removal and partial least squares regression[J].Geomatics and Information Science of Wuhan University,2014,39(7):862-866.
[13]孔玲军.MATLAB小波分析超级学习手册[M].北京:人民邮电出版社,2014:100-160.Kong L J.Super Learning Manual of Wavelet Analysis Based on MATLAB[M].Beijing:Posts and Telecom Press,2014:100-160.
[14]Ben-Dor E,Banin A.Visible and near infrared(0.4-1.1μm)analysis of arid and semiarid soil[J].Remote Sensing of Environment,1994,48(3):261-274.
[15]李希灿,王静,李玉环,等.基于模糊集分析的土壤质量指标高光谱反演[J].地理与地理信息科学,2008,24(4):25-28.Li X C,Wang J,Li Y H,et al.High spectral retrieved deduction of soil quality index based on fuzzy sets analysis[J].Geography and Geo-Information Science,2008,24(4):25-28.
[16]沈士喆,张小龙,衡伟.一种自适应阈值的预筛选Harris角点检测方法[J].数据采集与处理,2011,26(2):207-213.Shen S Z,Zhang X L,Heng W.Improved Harris corner detection algorithm based on auto-adaptive threshold and pre-selection[J].Journal of Data Acquisition and Processing,2011,26(2):207-213.
[17]邓小炼,王长耀,亢庆,等.一种基于角点提取的遥感影像地面控制点自适应匹配算法[J].宇航学报,2006,27(1):45-50,88.Deng X L,Wang C Y,Kang Q,et al.An adaptive matching algorithm for ground control point of remote sensing image based on corner extraction[J].Journal of Astronautics,2006,27(1):45-50,88.
[18]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 T,Wang J,Lin Z J,et al.Spectral features of soil organic matter[J].Geomatics and Information Science of Wuhan University,2006,31(11):975-979.
[19]郭斗斗,黄绍敏,张水清,等.多种潮土有机质高光谱预测模型的对比分析[J].农业工程学报,2014,30(21):192-200.Guo D D,Huang S M,Zhang S Q,et al.Comparative analysis of various hyperspectral prediction models of fluvo-aquicsoil organic matter[J].Transactions of the Chinese Society of Agricultural Engineering,2014,30(21):192-200.