高级搜索

基于多元线性模型、支持向量机(SVM)模型和地统计方法的地表水溶解性总固体(TDS)估算及其精度对比——以艾比湖流域为例

,  ,  , 

downloadPDF

上一篇

下一篇

王小平, 张飞, 于海洋, KUNG Hsiang-te. 基于多元线性模型、支持向量机(SVM)模型和地统计方法的地表水溶解性总固体(TDS)估算及其精度对比——以艾比湖流域为例[J]. 环境化学, 2017, 36(3): 666-676. doi: 10.7524/j.issn.0254-6108.2017.03.2016070104
引用本文: 王小平, 张飞, 于海洋, KUNG Hsiang-te. 基于多元线性模型、支持向量机(SVM)模型和地统计方法的地表水溶解性总固体(TDS)估算及其精度对比——以艾比湖流域为例[J]. 环境化学, 2017, 36(3): 666-676. doi: 10.7524/j.issn.0254-6108.2017.03.2016070104
shu
WANG Xiaoping, ZHANG Fei, YU Haiyang, KUNG Hsiang-te. Comparison of prediction accuracies of tds in the surface water in Ebinur Lake based on multivariate linear model, SVM model, and geostatistics method[J]. Environmental Chemistry, 2017, 36(3): 666-676. doi: 10.7524/j.issn.0254-6108.2017.03.2016070104
Citation: WANG Xiaoping, ZHANG Fei, YU Haiyang, KUNG Hsiang-te. Comparison of prediction accuracies of tds in the surface water in Ebinur Lake based on multivariate linear model, SVM model, and geostatistics method[J]. Environmental Chemistry, 2017, 36(3): 666-676. doi: 10.7524/j.issn.0254-6108.2017.03.2016070104
shu

基于多元线性模型、支持向量机(SVM)模型和地统计方法的地表水溶解性总固体(TDS)估算及其精度对比——以艾比湖流域为例

  • 1.

    新疆大学资源与环境科学学院, 乌鲁木齐, 830046;

  • 2.

    新疆大学绿洲生态教育部重点实验室, 乌鲁木齐, 830046;

  • 3.

    新疆智慧城市与环境建模普通高校重点实验室, 乌鲁木齐, 830046;

  • 4.

    美国孟菲斯大学地球科学系, 田纳西州 孟菲斯, 38152, 美国

  • 基金项目:

    国家自然科学基金（41361045，41130531）资助.

Comparison of prediction accuracies of tds in the surface water in Ebinur Lake based on multivariate linear model, SVM model, and geostatistics method

  • 1.

    College of Resources and Environment Science, Xinjiang University, Urumqi, 830046, China;

  • 2.

    Key Laboratory of Oasis Ecology, Xinjiang University, Urumqi, 830046, China;

  • 3.

    Key Laboratory of Xinjiang Wisdom City and Environment Modeling, Urumqi, 830046, China;

  • 4.

    Department of Earth Sciences, University of Memphis, Memphis, TN 38152, USA

  • Fund Project: Supported by National Natural Science Foundation of China (41361045, 41130531).

  • 摘要: 地表水溶解性总固体（TDS）是地表水各组分浓度的总指标，是地表水水化学特性长期演变的最终结果，也是表征水文地球化学作用过程的重要参数，TDS的高低直接影响地表水的含盐量.本研究以艾比湖流域为研究对象，结合实测地表水TDS数据；选用准同步的Landsat OLI数据，首先，利用光谱诊断指数选取与地表水TDS相关性较高的波段，其次，利用地统计方法、多元线性回归模型和支持向量机（SVM）模型对TDS进行预测，并对其结果进行精度比较.结果表明，SVM模型为最优估测模型，拟合决定系数R2为0.97，均方误差（RMSE）为50.59；多元线性回归模型的精度与SVM模型精度较为接近，拟合决定系数R2为0.9，RMSE为66.55；地统计克里格插值法预测精度最低，拟合决定系数R2为0.87，RMSE为95.73.遥感估测SVM模型预测值在大区域能较好地反映出艾比湖流域TDS的总体特征.该模型在水质遥感领域的应用中具有良好的可行性和有效性，其预测结果也与艾比湖流域水体TDS的实际分布相吻合，因此遥感估测SVM模型在水质估测中具有一定的应用潜力.
    Abstract: Total dissolved solids (TDS) of surface water is the total index of concentration of chemical components in surface water, and is an important parameter for the characterization of hydro-geochemical action. TDS directly affects the salinity of surface water. In this study, we chose Ebinur lake watershed as the study area, measured TDS data of the surface water, and analyzed quasi-synchronous Landsat OLI data to select sensitive band. We then used geo-statistics method, multiple linear regression model and SVM model to estimate the TDS of surface water, and compared with field measured TDS. The results show that SVM is the best model for TDS estimation and its coefficient R2 is 0.97, RMSE is 50.59. The accuracy of multiple linear regression model is very close to the SVM model, and the coefficient R2 is 0.9, RMSE is 66.55. The accuracy of Geo-statistical kriging interpolation method is the lowest, and coefficient R2 is 0.87, RMSE is 95.73.The SVM model prediction can better reflect the general characteristics in large area. The estimated results of TDS are in conformity with the actual field TDS data in Ebinur lake. Therefore, the SVM model has a great potential application for water quality prodiction.
  • 加载中
  • [1] 马金珠, 李吉均. 塔里木盆地南缘人类活动干扰下地下水的变化及其生态环境效应[J]. 自然资源学报, 2001, 16(2):134-139.

    MA J Z,LI J J. Impact of human activities on groundwater and the effect on eco-environment in southern Tarim Basin[J]. Journal of Natural Resources, 2001, 16(2):134-139(in Chinese).

    [2] 刘昌明, 陈志恺. 中国水资源现状评价和供需发展趋势分析[M]. 北京:中国水利水电出版社,2001. LIU C M,CHEN Z K. Present evaluation of China water resources and development trend analysis of supply and demand situation[M]. Beijing:China Water Power Press,2001(in Chinese).
    [3] COLLIN M L,MELLOUL A J.Combined land-use and environmental factors for sustainable ground water management[J].Urban Water,2001, 3(3):229-237.
    [4] 王雪蕾,王新新,朱利,等.巢湖流域氮磷面源污染与水华空间分布遥感解析[J].中国环境科学,2015,35(5):1511-1519.

    WANG X L, WANG X X, ZHU L,et al.Spatial analysis on diffuse pollution and algal bloom characteristic with remote sensing in Chao Lake Basin[J].China Environmental Science,2015,35(5):1511-1519(in Chinese).

    [5] 任建华. 黑河流域水资源开发对生态环境的影响[J].水土保持通报, 2005,25(4):92-96.

    REN J H.Effects of water resources exploitation on eco-environment of Heihe River basin[J].Bulletin of Soil and Water Conservation, 2005,25(4):92-96(in Chinese).

    [6] 章光新,邓伟,何岩.洮儿河流域地下水TDS时空变异特征研究[J].水土保持学报,2005,19(2):122-124.

    ZHANG X G, DENG W, HE Y.Characteristics of spatial and temporal variation of TDS of Groundwater in Tao'er River basin[J].Journal of Soil and Water Conservation, 2005,19(2):122-124(in Chinese).

    [7]
    [8] 李东青,梁籍,张立燕.密云库区1991-2011年水质变化趋势研究[J].中国环境科学,2015,35(6):1675-1685.

    LI D Q, LIANG J, ZHANG L Y.The research of water quality trend in the Miyun Reservoir from 1991 to 2011[J].China Environmental Science, 2015,35(6):1675-1685(in Chinese).

    [9] SALAMA R B, OTTO C J, FITZPATRICK R W. Contributions of groundwater conditions to soil and water salinization[J]. Hydrogeology Journal, 1999, 7(1):46-64.
    [10] 烟贯发,杜百利,张冬有,等.松花江哈尔滨段悬浮物含量遥感反演与克里格插值预测精度对比[J].湿地科学, 2015,13(2):180-189.

    YAN G F, DU B L, ZHANG D Y, et al.Comparison of predictionaccuracies of contents of suspended solids by remote sensing inversion and kriging spatial interpolation at harbin section of Songhua River[J].Wetland Science, 2015,13(2):180-189(in Chinese).

    [11] CAMPBELL G, PHINN S R, DEKKER A G, et al. Remote sensing of water quality in an Australian tropical freshwater impoundment using matrix inversion and MERIS images[J]. Remote Sensing of Environment, 2011, 115(9):2402-2414.
    [12] 胡炳清,易鹏,段宁.影响精确界定我国酸雨区空间分布的因素探讨[J].中国环境科学, 2015,35(3):917-924.

    HU B Q, YI P, DUAN N. Study on the influence factors of accurate definition of the spatial distribution of acid rain area in China[J].China Environmental Science, 2015,35(3):917-924(in Chinese).

    [13] ZHANG X Y,SUI Y Y, ZHANG X D, et al.Spatial variability of nutrient properties in black soil of northeast China[J]. Pedosphere,2007,17(1):19-29.
    [14] 竞霞,黄文江,王纪华,等.采用IRS-P6遥感数据监测密云水库水质及评价营养状况[J].农业工程学报,2008,24(增刊):13-17. JING X, HUANG W J, WANG J H,et al. Water quality monitoring and trophic state evaluation in Miyun reservoir based on IRS-P6

    remote sensing data[J]. Transactions of the CSAE, 2008,24(Supp.2):13-17(in Chinese).

    [15] 马媛,师庆东,杨建军.干旱区典型流域土壤微量元素的空间变异特征研究[J].干旱区地理,2006,29(5):682-687.

    MA Y, SHI Q D, YANG J J.Spatial variability of characters of soil trace elements in a watershed of arid area[J].Ari Land Geography,2006,29(5):682-687(in Chinese).

    [16] ZHANG C S, MCGRATH D. Geostatistical and GIS analyses on soil organic carbon concentrations in grassland of southeastern Ireland from two different periods[J]. Geoderma, 2004, 119(3):261-275.
    [17] GLENN N F, CARR J R. The use of geostatistics in relating soil moisture to RADARSAT-1 SAR data obtained over the Great Basin, Nevada, USA[J]. Computers & Geosciences, 2003, 29(5):577-586.
    [18] LI L, LI J, CHENG G. The dynamic monitoring of erhai cyanobacteria based on landsat data[J]. Journal of Water Resources Research, 2016, 5(2):167-173.
    [19] 张晓庆, 李苗, 臧淑英. 扎龙湿地叶绿素a浓度的协同克里格插值[J].中国农学通报, 2013,29(8):160-164.

    ZHANG X Q, LI M, ZANG S Y. Spatial interpolation of the chlorophyll-a concentration in zhalong wetland based on Cokriging[J].Chinese Agricultural Science Bulletin, 2013,29(8):160-164(in Chinese).

    [20] 王水献,王云智, 董新光.焉耆盆地浅层地下水埋深与TDS时空变异及水化学的演化特征[J].灌溉排水学报,2007,26(5)90-93.

    WANG S X, WANG Y Z. DONG X G. The spatio-temporal variation of shallow groundwater TDS depth and It's evolevment characterisitic of water chenistry in Yanqi Basin[J]. Journal of Irrigation and Drainage, 2007,26(5):90-93(in Chinese).

    [21] ZHANG F, TASHPOLAT T, VERNER C,et al. Evaluation of land desertification from 1990 to 2010 and its causes in Ebinur Lake region, Xinjiang China[J]. Environ Earth Sci, 2015,73(9):5731-5745.
    [22] 周梅,张飞,塔西甫拉提·特依拜,等.艾比湖流域水化学指标平面分布特征[J].环境化学,2015,34(9):1694-1702.

    ZHOU M, ZHANG F, TASHPOLAT TIYIP, et al. Spatial distribution of hydro-chemistry characteristics and water quality in Ebinur Lake Basin[J]. Environmental Chemistry,2015,34(9):1694-1702(in Chinese).

    [23] ABDERRAZAK HARTI, RACHID LHISSOU, KAREM CHOKMANI, et al. Spatiotemporal monitoring of soil salinization in irrigated Tadla Plain(Morocco)using satellite spectral indices[J]. International Journal of Applied Earth Observation and Geoinformation, 2016,50:64-73.
    [24] YANG Y H, LIU Y X, ZHOU M X,et al. Landsat 8 OLI image based terrestrial water extraction from heterogeneous backgrounds using a reflectance homogenization approach[J]. Remote Sensing of Environment,2015,171:14-32.
    [25] 樊彦国,李潭潭,李祥昌.基Landsat8的黄河三角洲盐渍化反演[J].山东农业科学,2015,47(2):119-124.

    FAN Y G, LI T T, LI X J. Soil salinization retrieval for the Yellow River delta based on Landsat 8[J].Shandong Agricultural Sciences, 2015,47(2):119-124(in Chinese).

    [26] 吕恕,朱宏.统计数据中异常值的检验方法讨论[J].东北师大学报自然科学版,1993,25(3):27-31.

    LV S, ZHU H. A discussion about the test of outliers in statistical data[J]. Journal of Northeast Normal University, 1993,25(3):27-31(in Chinese).

    [27] 郭亚男,吴泽宁,高建菊.基于主成分分析的支持向量机需水预测模型及其应用[J].中国农村水利水电, 2012(7):76-83. GUO Y N, WU Z Y, GAO J J. Application of support vector machines based on principal component analysis in water demand prediction[J].China's rural water conservancy and hydropower, 2012

    (7):76-83(in Chinese).

    [28] DING J L, YU D L.Monitoring and evaluating spatial variability of soil salinity in dry and wetseasons in the Werigan-Kuqa Oasis,China,using remote sensing and electromagnetic induction instruments[J].Geoderma, 2014, 235-236:316-322.
    [29] 范晓梅,刘高焕,刘红光.基于Kriging和Cokriging方法的黄河三角洲土壤盐渍化评价[J].资源科学,2014,36(2):321-327.

    FAN X M, LIU G H, LIU H G. Evaluating the spatial distribution of soil salinity in the Yellow River delta based on Kriging and Cokriging methods[J]. Resources Science, 2014,36(2):321-327(in Chinese).

    [30] 徐利岗, 周宏飞, 潘锋. 三工河流域山地-绿洲-荒漠系统降水空间变异性研究[J].地理学报, 2016, 71(5):731-742.

    XU L G, ZHOU H F, PAN F.Spatial variability of precipitation for mountain-oasis-desert system in the Sangong River Basin[J]. Acta Geographica Sinica,2016, 71(5):731-742(in Chinese).

    [31] GOTTSCHALK L, BATCHVAROVA B,GRYNING S B, et al. Scale aggregation comparison of flux estimates from XOPEX[J].Agric for Meteorl,1999, 98:103-119.
    [32] 林卉,梁亮,等.基于支持向量机回归算法的叶面指数高光谱遥感反演[J].农业工程学报,2013,29(11):139-146.

    LIN H, LIANG L, et al. Wheat leaf area index inversion with hyperspectral remote sensing based on support vector regression algorithm[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2013, 29(11):139-146(in Chinese).

    [33] 刘双印,徐龙琴,李道亮,等.基于时间相似数据的支持向量机水质溶解氧在线预测[J].农业工程学报,2014,30(3):155-162.

    LIU S Y, XU L Q, LI D L, et al. Online prediction for dissolved oxygen of water quality based on support vector machine with time series similar data[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2014, 30(3):155-162(in Chinese).

  • 加载中
WeChat 点击查看大图
计量
  • 文章访问数:  636
  • HTML全文浏览数:  593
  • PDF下载数:  498
  • 施引文献:  0
出版历程
  • 收稿日期:  2016-07-01
  • 刊出日期:  2017-03-15
王小平, 张飞, 于海洋, KUNG Hsiang-te. 基于多元线性模型、支持向量机(SVM)模型和地统计方法的地表水溶解性总固体(TDS)估算及其精度对比——以艾比湖流域为例[J]. 环境化学, 2017, 36(3): 666-676. doi: 10.7524/j.issn.0254-6108.2017.03.2016070104
引用本文: 王小平, 张飞, 于海洋, KUNG Hsiang-te. 基于多元线性模型、支持向量机(SVM)模型和地统计方法的地表水溶解性总固体(TDS)估算及其精度对比——以艾比湖流域为例[J]. 环境化学, 2017, 36(3): 666-676. doi: 10.7524/j.issn.0254-6108.2017.03.2016070104
shu
WANG Xiaoping, ZHANG Fei, YU Haiyang, KUNG Hsiang-te. Comparison of prediction accuracies of tds in the surface water in Ebinur Lake based on multivariate linear model, SVM model, and geostatistics method[J]. Environmental Chemistry, 2017, 36(3): 666-676. doi: 10.7524/j.issn.0254-6108.2017.03.2016070104
Citation: WANG Xiaoping, ZHANG Fei, YU Haiyang, KUNG Hsiang-te. Comparison of prediction accuracies of tds in the surface water in Ebinur Lake based on multivariate linear model, SVM model, and geostatistics method[J]. Environmental Chemistry, 2017, 36(3): 666-676. doi: 10.7524/j.issn.0254-6108.2017.03.2016070104
shu

基于多元线性模型、支持向量机(SVM)模型和地统计方法的地表水溶解性总固体(TDS)估算及其精度对比——以艾比湖流域为例

  • 1.  新疆大学资源与环境科学学院, 乌鲁木齐, 830046;
  • 2.  新疆大学绿洲生态教育部重点实验室, 乌鲁木齐, 830046;
  • 3.  新疆智慧城市与环境建模普通高校重点实验室, 乌鲁木齐, 830046;
  • 4.  美国孟菲斯大学地球科学系, 田纳西州 孟菲斯, 38152, 美国
  • 收稿日期:  2016-07-01
基金项目:

国家自然科学基金（41361045，41130531）资助.

摘要: 地表水溶解性总固体（TDS）是地表水各组分浓度的总指标，是地表水水化学特性长期演变的最终结果，也是表征水文地球化学作用过程的重要参数，TDS的高低直接影响地表水的含盐量.本研究以艾比湖流域为研究对象，结合实测地表水TDS数据；选用准同步的Landsat OLI数据，首先，利用光谱诊断指数选取与地表水TDS相关性较高的波段，其次，利用地统计方法、多元线性回归模型和支持向量机（SVM）模型对TDS进行预测，并对其结果进行精度比较.结果表明，SVM模型为最优估测模型，拟合决定系数R2为0.97，均方误差（RMSE）为50.59；多元线性回归模型的精度与SVM模型精度较为接近，拟合决定系数R2为0.9，RMSE为66.55；地统计克里格插值法预测精度最低，拟合决定系数R2为0.87，RMSE为95.73.遥感估测SVM模型预测值在大区域能较好地反映出艾比湖流域TDS的总体特征.该模型在水质遥感领域的应用中具有良好的可行性和有效性，其预测结果也与艾比湖流域水体TDS的实际分布相吻合，因此遥感估测SVM模型在水质估测中具有一定的应用潜力.

English Abstract

    全文HTML

参考文献 (33)

返回顶部

目录

/

返回文章
返回

Copyright © 2019 中国科学院生态环境研究中心