黄土丘陵沟壑区土壤养分含量的高光谱预测模型

doi:10.13287/j.1001-9332.201809.010

应用生态学报 ›› 2018, Vol. 29 ›› Issue (9): 2835-2842.doi: 10.13287/j.1001-9332.201809.010

黄土丘陵沟壑区土壤养分含量的高光谱预测模型

张超^1,2,3, 刘咏梅^1,2,3*, 孙亚楠⁴, 王雷^1,3, 刘建红^1,3

¹西北大学城市与环境学院, 西安 710127;
²水利部黄土高原水土流失过程与控制重点实验室, 郑州 450003;
³陕西省地表系统与环境承载力重点实验室, 西安 710127;
⁴西北大学数学学院, 西安 710127

收稿日期:2018-01-29 出版日期:2018-09-20 发布日期:2018-09-20
通讯作者: E-mail: liuym@nwu.edu.cn
作者简介:张超, 男, 1993年生, 硕士研究生.主要从事高光谱遥感与GIS应用研究. E-mail: czhang@stumail.nwu.edu.cn
基金资助:
本文由水利部黄土高原水土流失过程与控制重点实验室开放课题基金项目(2017002)资助

Hyperspectral prediction model of soil nutrient content in the loess hilly-gully region, China.

ZHANG Chao^1,2,3, LIU Yong-mei^1,2,3*, SUN Ya-nan⁴, WANG Lei^1,3, LIU Jian-hong^1,3

¹College of Urban and Environmental Science, Northwest University, Xi’an 710127, China;
²Ministry of Water Resources Key Laboratory of Soil Erosion Process and Control on the Loess Plateau, Zhengzhou 450003, China;
³Shaanxi Key Laboratory of Surface System and Environmental Carrying Capacity, Xi’an 710127, China;
⁴School of Mathematics, Northwest University, Xi’an 710127, China .

Received:2018-01-29 Online:2018-09-20 Published:2018-09-20
Supported by:
This work was supported by the Open Foundation of Key Laboratory of Soil Erosion Process and Control on the Loess Plateau of the Ministry of Water Resources, China (2017002).

摘要/Abstract

摘要： 基于高光谱数据快速准确估算土壤养分含量,可为土壤养分监测及土壤理化参数反演提供优化方法.本研究在陕北黄土丘陵沟壑区选取典型样地,分析土壤养分含量与光谱反射率的定量关系,采用连续投影算法提取其光谱特征波长,利用偏最小二乘法、多元线性回归法、支持向量机法分别对土壤有机质、全氮、全磷、全钾含量进行预测并对比分析,构建该区域土壤养分含量的最优高光谱预测模型.结果表明: 黄土丘陵沟壑区土壤养分含量与光谱反射率在可见光区(400～760 nm)和近红外区(760～1100 nm)相关性较高,相关系数最大值均位于这两个光谱区间.4种土壤养分含量的SPA-SVM模型的普适性好且反演精度高,建模过程简单高效,适用于小数据量试验.本研究结果可为采用机器学习算法构建黄土丘陵沟壑区土壤养分含量高光谱预测模型提供参考.

Abstract: Rapid and accurate estimation of soil nutrient content based on hyperspectral data is an optimal method for the monitoring of soil nutrient and inversion of soil physical and chemical characters. The relationship between soil nutrient content and spectral reflectance was analyzed with soil samples being collected from the loess hilly-gully region of northern Shaanxi Province. The prediction models of the content of soil organic matter, total nitrogen, total phosphorus and total potassium were constructed by the combination of three techniques, including partial least squares (PLS), multiple linear regression (MLR), and support vector machine (SVM). Then, the optimal model was selected by comparison analysis. The results showed good correlations between the content of soil nutrients and spectral reflectance in visible region (400-760 nm) and near infrared region (760-1100 nm). The maximum values of correlation coefficient located in both spectral regions. The SPA-SVM model had the best applicability and highest inversion accuracy for the contents of all soil nutrients, with simple and efficient modeling process. Our results provided a reference for applying machine learning algorithm in the construction of hyperspectral prediction model of soil nutrient content in the loess hilly-gully region.

张超, 刘咏梅, 孙亚楠, 王雷, 刘建红. 黄土丘陵沟壑区土壤养分含量的高光谱预测模型[J]. 应用生态学报, 2018, 29(9): 2835-2842.

ZHANG Chao, LIU Yong-mei, SUN Ya-nan, WANG Lei, LIU Jian-hong. Hyperspectral prediction model of soil nutrient content in the loess hilly-gully region, China.[J]. Chinese Journal of Applied Ecology, 2018, 29(9): 2835-2842.

参考文献

[1] Yang Z-J (杨之江), Chen X-M (陈效民), Jing F (景峰), et al. Spatial variability of nutrients and heavy metals in paddy field soils based on GIS and Geostatistics. Chinese Journal of Applied Ecology (应用生态学报), 2018, 29(6): 1893-1901 (in Chinese)
[2] Liu X-Y (刘秀英), Wang L (王力), Chang Q-R (常庆瑞), et al. Prediction of total nitrogen and alkali hydrolysable nitrogen content in loess using hyperspectral data based on correlation analysis and partial least squares regression. Chinese Journal of Applied Ecology (应用生态学报), 2015, 26(7): 2107-2114 (in Chinese)
[3] Li S (李硕), Wang S-Q (汪善勤), Shi Z (史舟). Prediction of vertical distribution of soil nitrogen content in soil profile using spectral imaging technique. Acta Pedologica Sinica (土壤学报), 2015, 52(5): 1014-1023 (in Chinese)
[4] Ramoelo A, Skidmore AK, Cho MA, et al. Non-linear partial least square regression increases the estimation accuracy of grass nitrogen and phosphorus using in situ, hyperspectral and environmental data. ISPRS Journal of Photogrammetry & Remote Sensing, 2013, 82: 27-40
[5] Nowkandeh SM, Noroozi AA, Homaee M. Estimating soil organic matter content from hyperion reflectance images using PLSR, PCR, MinR and SWR models in semi-arid regions of Iran. Environmental Development, 2017, 25: 2211-4645
[6] KovaČevićM, Bajat B, GajicćB. Soil type classification and estimation of soil properties using support vector machines. Geoderma, 2010, 154: 340-347
[7] Rodriguez-Galiano V, Sanchez-Castillo M, Chica-Olmo M, et al. Machine learning predictive models for mineral prospectivity: An evaluation of neural networks, random forest, regression trees and support vector machines. Ore Geology Reviews, 2015, 71: 804-818
[8] Pullanagari RR, Kereszturi G, Yule IJ. Mapping of macro and micro nutrients of mixed pastures using airborne AisaFENIX hyperspectral imagery. ISPRS Journal of Photogrammetry & Remote Sensing, 2016, 117: 1-10
[9] Cui X (崔霞), Song Q-J (宋清洁), Zhang Y-Y (张瑶瑶), et al. Estimation of soil organic carbon content in alpine grassland using hyperspectral data. Acta Prataculturae Sinica (草业学报), 2017, 26(10): 20-29 (in Chinese)
[10] Wang L-W (王莉雯), Wei Y-X (卫亚星). Estimating the total nitrogen and total phosphorus content of wetland soils using hyperspectral models. Acta Ecologica Sinica (生态学报), 2016, 36(16): 5116-5125 (in Chinese)
[11] Thorp KR, Wang G, Bronson KF, et al. Hyperspectral data mining to identify relevant canopy spectral features for estimating durum wheat growth, nitrogen status, and grain yield. Computers & Electronics in Agriculture, 2017, 136: 1-12
[12] Zhang W-L (章文龙), Zeng C-S (曾从盛), Gao D-Z (高灯州), et al. Estimating the soft total phosphorus content based on hyper-spectral remote sensing data in the Min River estuarine wetland. Acta Ecologica Sinica (生态学报), 2015, 35(24): 8085-8093 (in Chinese)
[13] Li P (李萍), Zhao G-X (赵庚星), Gao M-X (高明秀), et al. Hyperspectral estimation and remote sen-sing retrieval of soil water regime in the Yellow River delta. Acta Pedologica Sinica (土壤学报), 2015, 52(6): 1262-1272 (in Chinese)
[14] Xie X-Y (谢小燕), Liu Y-M (刘咏梅), Li J-Z (李京忠), et al. Remote sensing estimation of plant litter cover based on the spectra of plant litter-soil mixed scenes. Spectroscopy and Spectral Analysis (光谱学与光谱分析), 2016, 36(7): 2217-2223 (in Chinese)
[15] Fu B-J (傅伯杰), Chen L-D (陈利顶), Ma K-M (马克明). The effect of land use chang on the regional environment in the yangjuangou catchment in the Loess Plateau of China. Acta Geographica Sinica (地理学报), 1999, 54(3): 241-246 (in Chinese)
[16] Lu R-K (鲁如坤). Soil and Agricultural Chemisry Analysis. Beijing: China Agricultural Science and Technology Press, 1999 (in Chinese)
[17] National Soil Survey Office (全国土壤普查办公室). Soils of China. Beijing: China Agriculture Press, 1998 (in Chinese)
[18] Tsai F, Philpot W. Derivative analysis of hyperspectral data. Remote Sensing of Environment, 1998, 66: 41-51
[19] Cao D, Liang Y, Xu Q, et al. A new strategy of outlier detection for QSAR/QSPR. Journal of Computational Chemistry, 2010, 31: 592-602
[20] Zhan X-R (展晓日), Zhu X-R (朱向荣), Shi X-Y (史新元), et al. Determination of hesperidin in tangerine leaf by near-infrared spectroscopy with spxy algorithm for sample subset partitioning and Monte Carlo cross validation. Spectroscopy and Spectral Analysis (光谱学与光谱分析), 2009, 29(4): 964-968 (in Chinese)
[21] Brègman LM. The Method of Successive Projection for Finding a Common Point of Convex Sets [EB/OL]. (2016-01-01) [2017-12-12]. http://xueshu.baidu.com/s?wd=paperuri:(babb866cbc2f5682987985671-e2a5926)&filter=sc_long_sign&sc_ks_para=q%3DThe+method+of+successive+projection+for+finding+a+common+point+of+convex+sets&tn=SE_baiduxueshu_c1gjeupa&ie=utf-8&sc_us=5554069397454421075
[22] Wang Y-Y (王圆圆), Li G-C (李贵才), Zhang L-J (张立军), et al. Retrieval of leaf water content of winter wheat from canopy hyperspectral data using partial least square regression. Spectroscopy and Spectral Analysis (光谱学与光谱分析), 2010, 30(4): 1070-1074 (in Chinese)
[23] Torkashvand AM, Ahmadi A, Nikravesh NL. Prediction of kiwifruit firmness using fruit mineral nutrient concentration by artificial neural network (ANN) and multiple linear regressions (MLR). Journal of Integrative Agriculture, 2017, 16: 1634-1644
[24] Vapnik VN. The Nature of Statistical Learning Theory. New York: Springer, 2000: 138-167
[25] Sha J-M (沙晋明), Chen P-C (陈鹏程), Chen S-L (陈松林). Characteristics analysis of soil spectrum response resulted from organic material. Research of Soil and Water Conservation (水土保持研究), 2003, 10(2): 21-24 (in Chinese)

黄土丘陵沟壑区土壤养分含量的高光谱预测模型

Hyperspectral prediction model of soil nutrient content in the loess hilly-gully region, China.

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 0

编辑推荐

Metrics

本文评价