基于谐波分析算法的干旱区绿洲土壤光谱特性研究
|
摘要
土壤有机质(SOM)含量是评价土壤肥力的重要指标。以新疆渭-库绿洲为研究区,对室内获取的SOM含量及反射光谱数据进行Savitzky-Golay (S-G)平滑和一阶微分(FD)预处理。在此基础上,为减小敏感波段遴选对建模精度的影响,引入谐波分析(HA)算法对全波段光谱数据进行谐波分解。基于主成分分析(PCA)降维后的7个主分量对SOM含量进行基于反向传播(BP)神经网络、遗传算法(GA)-BP神经网络和多元线性回归(MLR)方法的定量估算,并对估算精度进行比较。结果表明:HA预处理后的光谱数据与SOM含量的相关性相较于FD数据有了明显提高;非线性模型BP神经网络的估算精度明显高于线性模型MLR;在非线性模型中,GA-BP模型的估算精度最高,其决定系数为0.92,预测集的均方根误差为3.92×10~(-3),相对分析误差为1.93。验证了HA算法深度挖掘光谱数据的有效性,经过GA优化的BP神经网络模型可以提高SOM含量的估算精度,为土壤属性的光谱定量估算提供借鉴。
The soil organic matter(SOM) content is an important index for evaluating soil fertility. Weigan-Kuqa region in Xinjiang is selected as the study area, based on the laboratory-derived SOM content and reflectance data, the pretreatment of Savitzky-Golay(S-G) smoothing and first order derivative(FD) are carried out. In order to further reduce the influence of sensitive band selection on modeling accuracy, we introduce the harmonic analysis(HA) algorithm to conduct the harmonic decomposition of all wavelengths. Seven principal components are obtained using dimensional reduction treatment of the principal component analysis(PCA). Subsequently, the SOM contents of soil samples are quantified by means of three methods: back propagation(BP) neural network, Genetic Algorithm(GA)-BP, and multiple linear regression(MLR). The accuracy of these methods is compared here. The results show that the correlation coefficient between SOM content and HA pretreated spectral data is improved effectively compared with those of FD data. The estimate accuracy of the non-linear model, BP neural network, is better than that of the linear model, MLR. In terms of non-linear models, the estimate accuracy of the GA-BP model is the best, with the optimal determining coefficient of 0.92, root mean square error of prediction set of 3.92×10~(-3), and the relative analysis error of 1.93. This study validates the effectiveness of the HA algorithm for the depth mining of spectral data, and the BP neural network model optimized by GA can improve estimate accuracy of SOM content, which can further provide scientific reference for the quantitative estimation of multiple soil properties.
The soil organic matter(SOM) content is an important index for evaluating soil fertility. Weigan-Kuqa region in Xinjiang is selected as the study area, based on the laboratory-derived SOM content and reflectance data, the pretreatment of Savitzky-Golay(S-G) smoothing and first order derivative(FD) are carried out. In order to further reduce the influence of sensitive band selection on modeling accuracy, we introduce the harmonic analysis(HA) algorithm to conduct the harmonic decomposition of all wavelengths. Seven principal components are obtained using dimensional reduction treatment of the principal component analysis(PCA). Subsequently, the SOM contents of soil samples are quantified by means of three methods: back propagation(BP) neural network, Genetic Algorithm(GA)-BP, and multiple linear regression(MLR). The accuracy of these methods is compared here. The results show that the correlation coefficient between SOM content and HA pretreated spectral data is improved effectively compared with those of FD data. The estimate accuracy of the non-linear model, BP neural network, is better than that of the linear model, MLR. In terms of non-linear models, the estimate accuracy of the GA-BP model is the best, with the optimal determining coefficient of 0.92, root mean square error of prediction set of 3.92×10~(-3), and the relative analysis error of 1.93. This study validates the effectiveness of the HA algorithm for the depth mining of spectral data, and the BP neural network model optimized by GA can improve estimate accuracy of SOM content, which can further provide scientific reference for the quantitative estimation of multiple soil properties.
引文
[1] Rossel R A V, McGlynn R N, McBratney A B. Determining the composition of mineral-organic mixes using UV-vis-NIR diffuse reflectance spectroscopy[J]. Geoderma, 2006, 137(1/2): 70-82.
[2] Ghamisi P, Yokoya N, Li J, et al. Advances in hyperspectral image and signal processing: a comprehensive overview of the state of the art[J]. Proceedings of the IEEE, 2017, 5(4): 37-78.
[3] Minasny B, McBratney A B, Bellon-Maurel V, et al. Removing the effect of soil moisture from NIR diffuse reflectance spectra for the prediction of soil organic carbon[J]. Geoderma, 2011, 167-168: 118-124.
[4] Peón J, Fernández S, Recondo C, et al. Evaluation of the spectral characteristics of five hyperspectral and multispectral sensors for soil organic carbon estimation in burned areas[J]. International Journal of Wildland Fire, 2017, 26(3): 230-239.
[5] Tahmasbian I, Xu Z H, Boyd S, et al. Laboratory-based hyperspectral image analysis for predicting soil carbon, nitrogen and their isotopic compositions[J]. Geoderma, 2018, 330: 254-263.
[6] Lin L X, Xue F C, Wang Y J, et al. Photography measured-value magnification improves local correlation maximization-complementary superiority method of hyperspectral analysis of soil total nitrogen[J]. Catena, 2018, 165: 106-114.
[7] 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.
[8] Stenberg B. Effects of soil sample pretreatments and standardized rewetting as interacted with sand classes on Vis-NIR predictions of clay and soil organic carbon[J]. Geoderma, 2010, 158(1/2): 15-22.
[9] Gomez C, Lagacherie P, Coulouma G. Regional predictions of eight common soil properties and their spatial structures from hyperspectral Vis-NIR data[J]. Geoderma, 2012, 189-190: 176-185.
[10] 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. 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.
[11] Hong Y S, Yu L, Chen Y Y, et al. Prediction of soil organic matter by VIS-NIR spectroscopy using normalized soil moisture index as a proxy of soil moisture[J]. Remote Sensing, 2017, 10(2): 28.
[12] Luo H L, Yang Y, Tong B, et al. Traffic sign recognition using a multi-task convolutional neural network[J]. IEEE Transactions on Intelligent Transportation Systems, 2018, 19(4): 1100-1111.
[13] Peng X T, Shi T Z, Song A H, et al. Estimating soil organic carbon using VIS/NIR spectroscopy with SVMR and SPA methods[J]. Remote Sensing, 2014, 6(4): 2699-2717.
[14] Bioucas-Dias J M, Plaza A, Camps-Valls G, et al. Hyperspectral remote sensing data analysis and future challenges[J]. Proceedings of the IEEE, 2013, 1(2): 6-36.
[15] Xue Z H, Du P J, Su H J. Harmonic analysis for hyperspectral image classification integrated with PSO optimized SVM[J]. Proceedings of the IEEE, 2014, 7(6): 2131-2146.
[16] Donoho D L, Maleki A, Rahman I U, et al. Reproducible research in computational harmonic analysis[J]. Computing in Science & Engineering, 2009, 11(1): 8-18.
[17] Ding J L, Yu D L. Monitoring and evaluating spatial variability of soil salinity in dry and wet seasons in the Werigan-Kuqa Oasis, China, using remote sensing and electromagnetic induction instruments[J]. Geoderma, 2014, 235-236: 316-322.
[18] Cao L, Ding J L, Yu H Y. Relationship between multi-scale landscape pattern and salinity in Weigan and Kuqa rivers delta oasis[J]. Transactions of the Chinese Society of Agricultural Engineering, 2016, 32(3): 101-110. 曹雷, 丁建丽, 于海洋. 渭-库绿洲多尺度景观格局与盐度关系[J]. 农业工程学报, 2016, 32(3): 101-110.
[19] Bao S D. Soil agrochemical analysis[M]. 3rd ed. Beijing: China Agriculture Press, 2000. 鲍士旦. 土壤农化分析[M]. 3版. 北京: 中国农业出版社, 2000.
[20] Wang J Z, Ding J L, Abulimiti A, et al. Quantitative estimation of soil salinity by means of different modeling methods and visible-near infrared (VIS-NIR) spectroscopy, Ebinur Lake Wetland, Northwest China[J]. PeerJ, 2018, 6: e4703.
[21] 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.
[22] Savitzky A, Golay M J E. Smoothing and differentiation of data by simplified least squares procedures[J]. Analytical Chemistry, 1964, 36(8): 1627-1639.
[23] Du J, Hu B L, Zhang Z F. Gastric carcinoma classification based on convolutional neural network and micro-hyperspectral imaging[J]. Acta Optica Sinica, 2018, 38(6): 0617001. 杜剑, 胡炳樑, 张周锋. 基于卷积神经网络与显微高光谱的胃癌组织分类方法研究[J]. 光学学报, 2018, 38(6): 0617001.
[24] Yang K M, Zhang T, Wang L B, et al. A new algorithm on hyperspectral image fusion based on the harmonic analysis[J]. Journal of China University of Mining & Technology, 2014, 43(3): 547-553. 杨可明, 张涛, 王立博, 等. 高光谱影像的谐波分析融合算法研究[J]. 中国矿业大学学报, 2014, 43(3): 547-553.
[25] Ge X Y, Ding J L, Wang J Z, et al. Estimation of soil moisture content based on competitive adaptive reweighted sampling algorithm coupled with machine learning[J]. Acta Optica Sinica, 2018, 38(10): 1030001. 葛翔宇, 丁建丽, 王敬哲, 等. 基于竞争适应重加权采样算法耦合机器学习的土壤含水量估算[J]. 光学学报, 2018, 38(10): 1030001.
[26] Wang W X, Tang R C, Li C, et al. A BP neural network model optimized by Mind Evolutionary Algorithm for predicting the ocean wave heights[J]. Ocean Engineering, 2018, 162: 98-107.
[27] Shi Z, Ji W, Viscarra Rossel R A, et al. Prediction of soil organic matter using a spatially constrained local partial least squares regression and the Chinese vis-NIR spectral library[J]. European Journal of Soil Science, 2015, 66(4): 679-687.
[28] Jiang X Q, Ye Q, Lin Y, et al. Inverting study on soil water content based on harmonic analysis and hyperspectral remote sensing[J]. Acta Optica Sinica, 2017, 37(10): 1028001. 姜雪芹, 叶勤, 林怡, 等. 基于谐波分析和高光谱遥感的土壤含水量反演研究[J]. 光学学报, 2017, 37(10): 1028001.
[29] Liu H J, Zhang Y Z, Zhang X L, et al. Quantitative analysis of moisture effect on black soil reflectance[J]. Pedosphere, 2009, 19(4): 532-540.
[30] Zhou Q Q, Ding J L, Tang M Y, et al. Inversion of soil organic matter content in oasis typical of arid area and its influencing factors[J]. Acta Pedologica Sinica, 2018, 55(2): 313-324. 周倩倩, 丁建丽, 唐梦迎, 等. 干旱区典型绿洲土壤有机质的反演及影响因素研究[J]. 土壤学报, 2018, 55(2): 313-324.
[31] Luan F M, Zhang X L, Xiong H G, et al. Comparative analysis of soil organic matter content based on different inversion models[J]. Spectroscopy and Spectral Analysis, 2013, 33(1): 196-200. 栾福明, 张小雷, 熊黑钢, 等. 基于不同模型的土壤有机质含量高光谱反演比较分析[J]. 光谱学与光谱分析, 2013, 33(1): 196-200.
[2] Ghamisi P, Yokoya N, Li J, et al. Advances in hyperspectral image and signal processing: a comprehensive overview of the state of the art[J]. Proceedings of the IEEE, 2017, 5(4): 37-78.
[3] Minasny B, McBratney A B, Bellon-Maurel V, et al. Removing the effect of soil moisture from NIR diffuse reflectance spectra for the prediction of soil organic carbon[J]. Geoderma, 2011, 167-168: 118-124.
[4] Peón J, Fernández S, Recondo C, et al. Evaluation of the spectral characteristics of five hyperspectral and multispectral sensors for soil organic carbon estimation in burned areas[J]. International Journal of Wildland Fire, 2017, 26(3): 230-239.
[5] Tahmasbian I, Xu Z H, Boyd S, et al. Laboratory-based hyperspectral image analysis for predicting soil carbon, nitrogen and their isotopic compositions[J]. Geoderma, 2018, 330: 254-263.
[6] Lin L X, Xue F C, Wang Y J, et al. Photography measured-value magnification improves local correlation maximization-complementary superiority method of hyperspectral analysis of soil total nitrogen[J]. Catena, 2018, 165: 106-114.
[7] 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.
[8] Stenberg B. Effects of soil sample pretreatments and standardized rewetting as interacted with sand classes on Vis-NIR predictions of clay and soil organic carbon[J]. Geoderma, 2010, 158(1/2): 15-22.
[9] Gomez C, Lagacherie P, Coulouma G. Regional predictions of eight common soil properties and their spatial structures from hyperspectral Vis-NIR data[J]. Geoderma, 2012, 189-190: 176-185.
[10] 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. 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.
[11] Hong Y S, Yu L, Chen Y Y, et al. Prediction of soil organic matter by VIS-NIR spectroscopy using normalized soil moisture index as a proxy of soil moisture[J]. Remote Sensing, 2017, 10(2): 28.
[12] Luo H L, Yang Y, Tong B, et al. Traffic sign recognition using a multi-task convolutional neural network[J]. IEEE Transactions on Intelligent Transportation Systems, 2018, 19(4): 1100-1111.
[13] Peng X T, Shi T Z, Song A H, et al. Estimating soil organic carbon using VIS/NIR spectroscopy with SVMR and SPA methods[J]. Remote Sensing, 2014, 6(4): 2699-2717.
[14] Bioucas-Dias J M, Plaza A, Camps-Valls G, et al. Hyperspectral remote sensing data analysis and future challenges[J]. Proceedings of the IEEE, 2013, 1(2): 6-36.
[15] Xue Z H, Du P J, Su H J. Harmonic analysis for hyperspectral image classification integrated with PSO optimized SVM[J]. Proceedings of the IEEE, 2014, 7(6): 2131-2146.
[16] Donoho D L, Maleki A, Rahman I U, et al. Reproducible research in computational harmonic analysis[J]. Computing in Science & Engineering, 2009, 11(1): 8-18.
[17] Ding J L, Yu D L. Monitoring and evaluating spatial variability of soil salinity in dry and wet seasons in the Werigan-Kuqa Oasis, China, using remote sensing and electromagnetic induction instruments[J]. Geoderma, 2014, 235-236: 316-322.
[18] Cao L, Ding J L, Yu H Y. Relationship between multi-scale landscape pattern and salinity in Weigan and Kuqa rivers delta oasis[J]. Transactions of the Chinese Society of Agricultural Engineering, 2016, 32(3): 101-110. 曹雷, 丁建丽, 于海洋. 渭-库绿洲多尺度景观格局与盐度关系[J]. 农业工程学报, 2016, 32(3): 101-110.
[19] Bao S D. Soil agrochemical analysis[M]. 3rd ed. Beijing: China Agriculture Press, 2000. 鲍士旦. 土壤农化分析[M]. 3版. 北京: 中国农业出版社, 2000.
[20] Wang J Z, Ding J L, Abulimiti A, et al. Quantitative estimation of soil salinity by means of different modeling methods and visible-near infrared (VIS-NIR) spectroscopy, Ebinur Lake Wetland, Northwest China[J]. PeerJ, 2018, 6: e4703.
[21] 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.
[22] Savitzky A, Golay M J E. Smoothing and differentiation of data by simplified least squares procedures[J]. Analytical Chemistry, 1964, 36(8): 1627-1639.
[23] Du J, Hu B L, Zhang Z F. Gastric carcinoma classification based on convolutional neural network and micro-hyperspectral imaging[J]. Acta Optica Sinica, 2018, 38(6): 0617001. 杜剑, 胡炳樑, 张周锋. 基于卷积神经网络与显微高光谱的胃癌组织分类方法研究[J]. 光学学报, 2018, 38(6): 0617001.
[24] Yang K M, Zhang T, Wang L B, et al. A new algorithm on hyperspectral image fusion based on the harmonic analysis[J]. Journal of China University of Mining & Technology, 2014, 43(3): 547-553. 杨可明, 张涛, 王立博, 等. 高光谱影像的谐波分析融合算法研究[J]. 中国矿业大学学报, 2014, 43(3): 547-553.
[25] Ge X Y, Ding J L, Wang J Z, et al. Estimation of soil moisture content based on competitive adaptive reweighted sampling algorithm coupled with machine learning[J]. Acta Optica Sinica, 2018, 38(10): 1030001. 葛翔宇, 丁建丽, 王敬哲, 等. 基于竞争适应重加权采样算法耦合机器学习的土壤含水量估算[J]. 光学学报, 2018, 38(10): 1030001.
[26] Wang W X, Tang R C, Li C, et al. A BP neural network model optimized by Mind Evolutionary Algorithm for predicting the ocean wave heights[J]. Ocean Engineering, 2018, 162: 98-107.
[27] Shi Z, Ji W, Viscarra Rossel R A, et al. Prediction of soil organic matter using a spatially constrained local partial least squares regression and the Chinese vis-NIR spectral library[J]. European Journal of Soil Science, 2015, 66(4): 679-687.
[28] Jiang X Q, Ye Q, Lin Y, et al. Inverting study on soil water content based on harmonic analysis and hyperspectral remote sensing[J]. Acta Optica Sinica, 2017, 37(10): 1028001. 姜雪芹, 叶勤, 林怡, 等. 基于谐波分析和高光谱遥感的土壤含水量反演研究[J]. 光学学报, 2017, 37(10): 1028001.
[29] Liu H J, Zhang Y Z, Zhang X L, et al. Quantitative analysis of moisture effect on black soil reflectance[J]. Pedosphere, 2009, 19(4): 532-540.
[30] Zhou Q Q, Ding J L, Tang M Y, et al. Inversion of soil organic matter content in oasis typical of arid area and its influencing factors[J]. Acta Pedologica Sinica, 2018, 55(2): 313-324. 周倩倩, 丁建丽, 唐梦迎, 等. 干旱区典型绿洲土壤有机质的反演及影响因素研究[J]. 土壤学报, 2018, 55(2): 313-324.
[31] Luan F M, Zhang X L, Xiong H G, et al. Comparative analysis of soil organic matter content based on different inversion models[J]. Spectroscopy and Spectral Analysis, 2013, 33(1): 196-200. 栾福明, 张小雷, 熊黑钢, 等. 基于不同模型的土壤有机质含量高光谱反演比较分析[J]. 光谱学与光谱分析, 2013, 33(1): 196-200.
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |