基于大样本土壤光谱数据库的氮含量反演

充分挖掘大样本土壤光谱库中有效信息，建立普适性强的土壤全氮(TN)含量反演模型，是高光谱分析的重要应用方向之一。研究采用偏最小二乘回归(PLSR)全局建模、局部加权回归(LWR)和模糊K均值聚类结合PLSR(FKMC-PLSR)局部建模三种方法，分别建立了来自中国西藏、新疆、黑龙江、海南等13个省采集的17种土类1661个土壤样本TN值的高光谱反演模型，并对浙江省104个水稻土样本进行模型验证。结果表明，在大样本下PLSR全局模型对高TN值待预测样本存在低估现象，导致整体预测精度偏低； LWR和FKMC-PLSR局部模型比PLSR全局模型能够更为准确地反演TN含量。研究结果可为利用大样本光谱数据库建立稳定性和普适性较高的土壤TN含量预测模型提供参考。

Abstract

Building universal deduction models for predicting the soil total nitrogen (TN) content by using data mining of large soil spectral libraries is one of the most important applications of hyperspectral analysis. In this study, 1661 soil samples representing 17 soil types from 13 provinces of China (e.g., Tibet, Xinjiang, Heilongjiang and Hainan) are employed for modeling the soil TN content using global partial least squares regression (PLSR), locally weighted regression (LWR) and fuzzy K-means clustering combined with PLSR (FKMC-PLSR). Another 104 paddy soil samples collected from Zhejiang Province are used to validate the established models. Results showed that when predicting soil TN from a large dataset, global PLSR underestimates high values of TN, which generates an overall low prediction accuracy. By contrast, LWR and FKMC-PLSR perform better than global PLSR. It is suggested that the results can provide useful information for establishing robust and universal models for soil TN prediction using large soil spectral libraries.

参考文献

[1] A V Bilgili, H M V Es, F Akbas, et al.. Visible-near infrared reflectance spectroscopy for assessment of soil properties in a semi-arid area of Turkey [J]. Journal of Arid Environments, 2010, 74(2): 229-238.

[2] 陆婉珍. 现代近红外光谱分析技术 (第2版) [M]. 北京: 中国石化出版社, 2006. 10-13.

Lu Wanzhen. The Modern Analysis Technique of Near-Infrared Spectrum (2nd edition) [M]. Beijing: China Petrochemical Press, 2006. 10-13.

[3] 陈丛, 卢启鹏, 彭忠琦. 基于NLMS自适应滤波的近红外光谱去噪处理方法研究[J]. 光学学报, 2012, 32(5): 0530001.

Chen Cong, Lu Qipeng, Peng Zhongqi. Preprocessing methods of near-infrared spectrum based on NLMS adaptive filtering [J]. Acta Optica Sinica, 2012, 32(5): 0530001.

[4] 高洪智, 卢启鹏, 丁海泉, 等. 基于随机抽样一致性算法的近红外光谱稳健模型研究[J]. 光学学报, 2013, 33(s2): s230001.

Gao Hongzhi, Lu Qipeng, Ding Haiquan, et al.. Robust calibration methods of near-infrared spectrum based on random sample consensus algorithm [J]. Acta Optica Sinica, 2013, 33(s2): s230001.

[5] B Stenberg, R A V Rossel, A M Mouazen, et al.. Visible and near infrared spectroscopy in soil science [J]. Advances in Agronomy, 2010, 107: 163-215.

[6] B Y Kuang, H S Mahmood, M Z Quraishi, et al.. Sensing soil properties in the laboratory, in situ, and on-line: a review [J]. Advances in Agronomy, 2012, 114: 155-223.

[7] Y X Song, F L Li, Z F Yang, et al.. Diffuse reflectance spectroscopy for monitoring potentially toxic elements in the agricultural soils of Changjiang River Delta, China [J]. Applied Clay Science, 2012, 64: 75-83.

[8] M Nocita, A Stevens, G Toth, et al.. Prediction of soil organic carbon content by diffuse reflectance spectroscopy using a local partial least square regression approach [J]. Soil Biology and Biochemistry, 2014, 68: 337-347.

[9] D J Brown, K D Shepherd, M G Walse, et al.. Global soil characterization with VNIR diffuse reflectance spectroscopy [J]. Geoderma, 2006, 132(3-4): 273-290.

[10] R A V Rossel, R Webster. Predicting soil properties from the Australian soil visible-near infrared spectroscopic database [J]. European Journal of Soil Science, 2012, 63(6): 848-860.

[11] Z Shi, Q L Wang, J Peng, et al.. Development of national VNIR soil-spectral library for soil classification and the predictions of organic matter [J]. Science China Earth Sciences, 2014, 57(7): 1671-1680.

[12] D J Brow. Using a global VNIR soil-spectral library for local soil characterization and landscape modeling in a 2nd-order Uganda watershed [J]. Geoderma, 2007, 140(4): 444-453.

[13] J Wetterlind, B Stenberg. Near-infrared spectroscopy for within-field soil characterization: small local calibrations compared with national libraries spiked with local samples [J]. European Journal of Soil Science, 2010, 61(6): 823-843.

[14] F Goge, R Joffre, C Jolivet, et al.. Optimization criteria in sample selection step of local regression for quantitative analysis of large soil NIRS database [J]. Chemometr Intell Lab, 2012, 110(1): 168-176.

[15] A Stevens, M Nocita, G Toth, et al.. Prediction of soil organic carbon at the european scale by visible and near infrared reflectance spectroscopy [J]. Plos One, 2013, 8(6): 1-13.

[16] Y Peng, M Knadel, R Gislum, et al.. Predicting soil organic carbon at field scale using a national soil spectral library [J]. J Near Infrared Spectroscopy, 2013, 21(3): 213-222.

[17] 徐永明, 蔺启忠, 黄秀华, 等. 利用可见光/近红外反射光谱估算土壤总氮含量的实验研究[J]. 地理与地理信息科学, 2005, 21(1): 19-22.

Xu Yongming, Lin Qizhong, Huang Xiuhua, et al.. Experimental study on total nitrogen concentration in soil by VNIR reflectance spectrum [J]. Geography and Geo-Information Science, 2005, 21(1): 19-22.

[18] 卢艳丽, 白由路, 王磊, 等. 黑土土壤中TN含量的高光谱预测分析[J]. 农业工程学报, 2010, 26(1): 256-261.

Lu Yanli, Bai Youlu, Wang Lei, et al.. Determination for total nitrogen content in black soil using hyperspectral data [J]. Transactions of the CSAE, 2010, 26(1): 256-261.

[19] 李硕, 汪善勤, 张美琴. 基于可见近红外光谱比较主成分回归、偏最小二乘回归和反向传播神经网络对土壤氮的预测研究[J]. 光学学报, 2012, 32(8): 0830001.

Li Shuo, Wang Shanqin, Zhang Meiqin. Comparison among principal component regression, partial least squares regression and back propagation neural network for prediction of soil nitrogen with visible-near infrared spectroscopy [J]. Acta Optica Sinica, 2012, 32(8): 0830001.

[20] 张娟娟, 田永超, 姚霞, 等. 基于高光谱的土壤TN含量估测[J]. 自然资源学报, 2011, 26(5): 881-890.

Zhang Juanjuan, Tian Yongchao, Yao Xia, et al.. Estimating soil total nitrogen content based on hyperspectral analysis technology [J]. J Natural Resources, 2011, 26(5): 881-890.

[21] 张娟娟, 田永超, 姚霞, 等. 基于近红外光谱的土壤TN含量估算模型[J]. 农业工程学报, 2012, 28(12): 183-188.

Zhang Juanjuan, Tian Yongchao, Yao Xia, et al.. Estimating model of soil total nitrogen content based on near-infrared spectroscopy analysis [J]. Transactions of the CSAE, 2012, 28(12): 183-188.

[22] 纪文君, 史舟, 周清, 等. 几种不同类型土壤VIS-NIR光谱特性及有机质响应波段[J]. 红外与毫米波学报, 2012, 31(3): 277-282.

Ji Wenjun, Shi Zhou, Zhou Qing, et al.. VIS-NIR reflectance spectroscopy of the organic matter in several types of soils [J]. Journal of Infrared and Millimeter Waves, 2012, 31(3): 277-282.

[23] 纪文君, 李曦, 李成学, 等. 基于全谱数据挖掘技术的土壤有机质高光谱预测建模研究[J]. 光谱学与光谱分析, 2012, 32(9): 2393-2398.

Ji Wenjun, Li Xi, Li Chengxue, et al.. Using different data mining algorithms to predict soil organic matter based on visible-near infrared spetroscopy [J]. Spectroscopy and Spectral Analysis, 2012, 32(9): 2393-2398.

[24] T Naes, T Isaksson, B Kowalski. Locally weighted regression and scatter correction for near infrared reflectance data [J]. Analytical Chemistry, 1990, 62(7): 664-673.

[25] Y Guo, Z Shi, H Y Li, et al.. Application of digital soil mapping methods to identify salinity management classes in coastal lands of central China [J]. Soil Use and Management, 2013, 29(3): 445-456.

[26] Y Li, Z Shi, F Li, et al.. Delineation of site-specific management zones using fuzzy clustering analysis in a coastal saline land [J]. Computers and Electronics in Agriculture, 2007, 56(2): 174-186.

[27] V Bellon-Maurel, E Fernandez-Ahumada, B Palagos, et al.. Critical review of chemometric indicators commonly used for assessing the quality of the prediction of soil attributes by NIR spectroscopy [J]. TrAC Trends in Analytical Chemistry, 2010, 29(9): 1073-1081.

[28] L Ramirez-Lopez, T Behrens, K Schmidt, et al.. Distance and similarity-search metrics for use with soil vis-NIR spectra [J]. Geoderma, 2013, 199: 43-53.

王乾龙, 李硕, 卢艳丽, 彭杰, 史舟, 周炼清. 基于大样本土壤光谱数据库的氮含量反演[J]. 光学学报, 2014, 34(9): 0930003. Wang Qianlong, Li Shuo, Lu Yanli, Peng Jie, Shi Zhou, Zhou Lianqing. Nitrogen Content Inversion Based on Large Sample Soil Spectral Library[J]. Acta Optica Sinica, 2014, 34(9): 0930003.

基于大样本土壤光谱数据库的氮含量反演

关于本站 Cookie 的使用提示

全站搜索

基于大样本土壤光谱数据库的氮含量反演

相关论文

相关资讯

关于本站 Cookie 的使用提示

全站搜索