Please wait a minute...
img

官方微信

遥感技术与应用  2014, Vol. 29 Issue (3): 419-427    DOI: doi:10.11873/j.issn.1004-0323.2014.3.0419
模型与反演     
基于SVM模型的妫水河叶绿素a浓度的遥感反演
刘朝相1,2,3,4,宫兆宁1,2,3,4,赵文吉1,2,3,4
(1.首都师范大学资源环境与旅游学院,北京100048;
2.三维信息获取与应用教育部重点实验室,北京100048;
3.资源环境与地理信息系统北京市重点实验室,北京100048;
4.北京市城市环境过程与数字模拟国家重点实验室培育基地,北京100048)
Remote Sensing Retrieval of Chlorophyll\|a Concentration in Beijing Guishuihe River Using Support Vector Machine Model
Liu Chaoxiang1,2,3,4,Gong Zhaoning1,2,3,4,Zhao Wenji1,2,3,4
(1.College of Resource Environment and Tourism,Capital Normal University,Beijing 100048,China;
2.Key Laboratory of 3D Information Acquisition and Application of Ministry of Education,Beijing 100048,China;
3.Key Laboratory of Resources Environment and GIS of Beijing Municipal,Beijing 100048,China;
4.Base of the State Laboratory of Urban Environmental Processes and Digital Modeling,Beijing 100048,China)
 全文: PDF(6102 KB)  
摘要:

以北京市妫水河为研究区,基于2011年9月25日和2012年9月30日的两期叶绿素a浓度实测数据和准同步的环境一号卫星(HJ-1A)多光谱数据,分别构建一元线性和多元支持向量机模型(SVMM),通过决定系数R2和平均相对误差对模型的精度进行检验,用模型进行水体叶绿素a浓度的反演,并分析其时空分布特征。研究表明:在样本数较少的情况下,SVM具有很强的非线性映射能力,能够取得较好的预测结果,更适用于反演叶绿素a浓度。时间分布上,研究区叶绿素a浓度呈增加趋势,均值上升了6.86 μg/L;空间分布上,深水区叶绿素a浓度值低于浅水区,上游高于下游。国产HJ-1A CCD2多光谱数据以其4 d的时间分辨率,在水质动态变化监测方面具有优势。

关键词: 支持向量机模型(SVMM)一元线性模型叶绿素a浓度妫水河HJ-1A多光谱数据    
Abstract:

Chlorophyll\|a concentration is an important indicator of water quality evaluation.Taking the Guishuihe River as a study area,chlorophyll\|a concentration was obtained on 25 September,2011 and 25 September,2012,and two quasi\|synchronous images of HJ\|1A satellite were acquired.This paper presents two linear empirical models and two Support Vector Machine(SVM) models to retrieve chlorophyll\|a concentration of Guishuihe River valley based on in situ collected Chlorophyll\|a concentration data and Multi\|spectral data of HJ\|1A.Determination coefficients and average relative errors are used to assess the accuracy.Models are used to retrieve chlorophyll\|a concentration,and the reasons for distribution characteristicsof chlorophyll\|a concentration in time and spatial are studied.The results show that SVM can obtain a better prediction results in the condition of small sample size for its strong nonlinear mapping ability.SVM model is more suitable for the inversion of chlorophyll a concentration.Compared to 2011,the Mean value of Chlorophyll\|a concentration of Guishuihe River increased 6.8603 μg/L in 2012,which indicated that Chlorophyll\|a concentration of Guishuihe River tends to increase.The spatial distribution of Chlorophyll\|a concentration shows that deep water areas present Chlorophyll\|a concentrations values lower than the shallow water areas,the upstream areas present higher Chlorophyll\|a concentrations values than the downstream areas.Domestic HJ\|1A CCD2 multispectral data demonstrates advantages on the dynamic changes of water quality monitoring for the 4d time resolution.

Key words: Support Vector Machine Model(SVMM)    A linear model    Chlorophyll-a concentration    Guishuihe River    Multispectral data of HJ-1A satellite
收稿日期: 2013-03-11 出版日期: 2014-06-23
ZTFLH:  X 832  
基金资助:

863计划项目(2012AA12A308),国家青年科学基金项目(41101404),国家基础测绘项目(2011A2001),北京市教委科技计划面上项目(KM201110028013)。

通讯作者: 宫兆宁(1976-),女,山东青岛人,博士,副教授,主要从事湿地遥感监测方面的研究。Email:gongzhn@163.com。    
作者简介: 刘朝相(1987-),男,湖南龙山人,硕士研究生,主要从事内陆水体水色遥感应用研究。Email:liuchaozhuqiu@163.com。
服务  
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章  
刘朝相
宫兆宁
赵文吉

引用本文:

刘朝相,宫兆宁,赵文吉. 基于SVM模型的妫水河叶绿素a浓度的遥感反演[J]. 遥感技术与应用, 2014, 29(3): 419-427.

Liu Chaoxiang,Gong Zhaoning,Zhao Wenji. Remote Sensing Retrieval of Chlorophyll\|a Concentration in Beijing Guishuihe River Using Support Vector Machine Model. Remote Sensing Technology and Application, 2014, 29(3): 419-427.

链接本文:

http://www.rsta.ac.cn/CN/doi:10.11873/j.issn.1004-0323.2014.3.0419        http://www.rsta.ac.cn/CN/Y2014/V29/I3/419

[1]Li Suju,Wu Qian,Wang Xuejun,et al.Correlations between Reflectance Spectra and Contents of Chlorophyll a in Chaohu Lake[J].Journal of Lake Sciences,2002,14(3):228-234.[李素菊,吴倩,王学军,等.巢湖浮游植物叶绿素含量与反射光谱特征的关系[J].湖泊科学,2002,14(3):228-234.]

[2]Zhu Lingya,Wang Shixin,Zhou Yi,et al.Estimation of Suspended Sediment Concentration in Taihu Lake Using MODIS Image Data[J].Advances in Water Science,2007,18(3):444-450.[祝令亚,王世新,周艺,等.应用MODIS 影像估测太湖水体悬浮物浓度[J].水科学进展,2007,18(3):444-450.]

[3]Hu C M,Chen Z Q,Tonya D.Assessment of Estuarine Water-quality Indicators Using MODIS Medium-resolution Bands:Initial Results from Tampa Bay,FL[J].Remote Sensing of Environment,2004,93(3):423-441.

[4]Leif G O,Marvin E B,Patrick L B.A 20-year Landsat Water Clarity Census of Minnesotas 10 000 Lakes[J].Remote Sensing of Environment,2008,112(11):4086-4097.

[5]Anatoly A G,Giorgio D,Wesley M,et al.A Simple Semi-analytical Model for Remote Estimation of Chlorophyll-a in Turbid Waters:Validation[J].Remote Sensing of Environment,2008,112(9):3582-3593.

[6]Daniela G,Anatoly A G,Wesley J M.Remote Estimation of Chl-a Concentration in Turbid Productive Waters-return to a Simple Two-band NIR-red Model?[J].Remote Sensing of Environment,2011,115(12):3479-3490.

[7]Ian M M,Cynthia S L,Steven A S.Combining Lake and Watershed Characteristics with Landsat TM Data for Remote Estimation of Regional Lake Clarity[J].Remote Sensing of Environment,2012,123:109-115.

[8]Wen Jianguang,Xiao Qing,Liu Qinhuo,et al.Extraction of Chlorophyll-a Concentration based on Spectral Unmixing Model in Taihu Lake Water[J].Scientia Geographica Sinica,2007,27(1):92-97.[闻建光,肖青,柳钦火,等.基于混合光谱理论的太湖水体叶绿素a浓度提取[J].地理科学,2007,27(1):92-97.]

[9]Tang S,Chen C,Zhan H,et al.An Appraisal of Surface Chlorophyll Estimation by Satellite Remote Sensing in the South China Sea[J].International Journal of Remote Sensing,2008,29(21),6217-6226.

[10]Catherine O,Peter F,Niklas S,et al.Mapping of the Water Quality of Lake Erken,Sweden,from Imaging Spectrometry and Landsat Thematic Mapper[J].The Science of the Total Environment,2001,268(1-3):139-154.

[11]Le C F,Hu C M,David English,et al.Towards a Long-term Chlorophyll-a Data Record in A Turbid Estuary Using MODIS Observations[J].Progress in Oceanography,2013,109:90-103.

[12]Tebbs E J,Remedios J J,Harper D M.Remote Sensing of Chlorophyll-a as a Measure of Cyanobacterial Biomass in Lake Bogoria,A Hypertrophic,Saline-alkaline,Flamingo Lake,Using Landsat ETM+[J].Remote Sensing of Environment,2013,135:92-106.

[13]Le C F,Hu C M,David English,et al.Climate-driven Chlorophyll-a Changes in a Turbid Estuary:Observations from Satellites and Implications for Management[J].Remote Sensing of Environment,2013,130:11-24.

[14]Duan H,Zhang Y,Zhang B,et al.Estimation of Chlorophyll-a Concentration and Trophic States for Inland Lakes in Northeast China from Landsat TM Data and Field Spectral Measurements[J].International Journal of Remote Sensing,2008,29(3):767-786.

[15]Geoffrey C,Patrick B,Prasad T.Estimating Chlorophyll Concentration in Lake Malawi from MODIS Satellite Imagery[J].Physics and Chemistry of the Earth,2009,34(13-16):755-760.

[16]Han Xiuzhen,Zhen Wei,Liu Cheng,et al.Estimation of Chlorophyll A Using MERSI and MODIS Images in Taihu Lake,China[J].Geographical Research,2011,30(2):291-300.[韩秀珍,郑伟,刘诚,等.基于MERSI 和MODIS 的太湖水体叶绿素a 含量反演[J].地理研究,2011,30(2):291-300.]

[17]Zhu Jingjing,Chen Jin,Wang Shengqiang,et al.Spatial-temporal Variation of Chlorophyll a Concentration in Lake Dianchi from 2003 to 2009 and Trend Analysis based on MERIS Data[J].Journal of Lake Sciences,2011:23(4):581-590.[朱晶晶,陈晋,王胜强,等.基于MERIS 数据的滇池叶绿素浓度时空变化(2003-2009年)及趋势[J].湖泊科学,2011:23(4):581-590.]

[18]Xia Rui,Li Yunmei,Wu Chuanqing,et al.Spatial Distribution and Variation of Concentration of Suspended Solids in Taihu Lake based on HJ-1 Satellite Data[J].Scientia Geographica Sinica,2011,31(2):198-203.[夏叡,李云梅,吴传庆,等.基于HJ-1号卫星数据的太湖悬浮物浓度空间分布和变异研究[J].地理科学,2011,31(2):198-203.]

[19]Xu Weifan,Li Yunmei,Wang Qiao,et al.Eutrophication Evaluation of Three Lakes and One Reservoir Using CCD Images from the HJ-1 Satellite[J].Acta Scientiae Circumstantiae,2011,31(1):81-93.[徐祎凡,李云梅,王桥,等.基于环境一号卫星多光谱影像数据的三湖一库富营养化状态评价[J].环境科学学报,2011,31(1):81-93.]

[20]Wang Qi,Meng Wei,Ma Yunfeng,et al.On the Inversion Models for Chlorophyll-a Concentration based on the HJ-1 Satellite Images of Dahuofang Reservoir,Liaoning[J].Journal of Safety and Environment,2013,13(4):137-141.[王琦,孟伟,马云峰,等.基于HJ-1卫星的大伙房水叶绿素a 浓度反演模型研究[J].安全与环境学报,2013,13(4):137-142].

[21]Guo Yulong,Li Yunmei,Zhu Li,et al.Research of Hyperspectral Reconstruction based on HJ1A-CCD Data[J].Environmental Science,2013,34(1):69-76.[郭宇龙,李云梅,朱利,等.基于HJ1A-CCD 数据的高光谱影像重构研究[J].环境科学,2013,34(1):69-76.]

[22]Zhang Y Z,Pulliainen J.Application of an Empirical Neural Network to Surface Water Quality Estimation in the Gulf of Finland Using Combined Optical Data and Microwave Data[J].Remote Sensing of Environment,2002,81(2-3):327-336.

[23]Singh K P,Basant N,Gupta S.Support Vector Machines in Water Quality Management[J].Analytica Chimica Acta,2011,703(2):152-162.

[24]Jiang Gang,Xiao Jian,Zheng Yongkang,et al.Retrieve the Oceanic Chlorophyll-a Concentration in Case I Water by Support Vector Machine[J].Computer Applications,2005,25(10):2398-2409.[蒋刚,肖建,郑永康,等.基于支持向量机的一类水域叶绿素a浓度反演研究[J].计算机应用,2005,25(10):2398-2409.]

[25]Wang Xili,Zhou Zhaoyong,Yan Junping,et al.Apply GA-SVM to Retrieve Water Quality Parameters of Weihe River from Multispectral Remote Sensing Data[J].Journal of Remote Sensing,2009,13(4):740-744.[汪西莉,周兆永,延军平.应用 GA-SVM 的渭河水质参数多光谱遥感反演[J].遥感学报,2009,13(4):740-744.]

[26]Zhan Haigang,Shi Ping,Chen Chuqun,et al.A Genetic Algorithm for Retrieval of Water Constituents from Ocean Color Remote Sensed Data in Case 2 Waters[J].Journal of Remote Sensing,2004,8(1):31-36.[詹海刚,施平,陈楚群,等.基于遗传算法的二类水体水色遥感反演[J].遥感学报,2004,8(1):31-36.]

[27]Joseph H W,Yan H.Neural Network Modelling of Coastal Algal Blooms[J].Ecological Modelling,2003,159(2-3):179-201.

[28]Yang Daojun,Wang Ran,Shen Gang,et al.SVM and ANN Applied to Evaluation of Lake Eutrophication:A Comparative Study[J].Environmental Science & Technology,2012,35(1):173-177.[杨道军,王冉,沈刚.SVM与ANN在湖泊富营养化评价中的对比研究[J].环境科学与技术,2012,35(1):173-177.]

[29]Pei Hongping,Luo Nina,Jiang Yong.Applications of Back Propagation Neural Network for Predicting the Concentration of Chlorophyll a in West Lake[J].Acta Ecologica Sinica,2004,24(2):246-251.[裴洪平,罗妮娜,蒋勇.利用BP 神经网络方法预测西湖叶绿素a 的浓度[J].生态学报,2004,24(2):246-251.]

[30]Guo Kai,Zhao Wen,Xu Feng,et al.Evaluation and Analysis of Eutrophication in Beijing Part of Guanting Reservoir[J].Journal of Dalian Fisheries University,2009,24(5):454-458.[郭凯,赵文,徐峰,等.官厅水库(北京段) 水体富营养化评价与分析[J].大连水产学院学报,2009,24(5):454-458.]

[31]Liu Hao,Xu Zhixia,Chen Chao,et al.Study on Eutrophication of Guanting Reservoir[J].Water Resources and Power,2011,29(1):13-16.[刘浩,徐志侠,陈超,等.官厅水库库区富营养化评价[J].水电能源科学,2011,29(1):13-16.]

[32]Shi Feng,Wang Xiaochuan,Yu Lei,et al.Thirty Cases of Matlab Neural Network[M].Beijing:Beihang University Press,2004:1-19.[史峰,王小川,郁磊,等.Matlab神经网络30个案例分析[M].北京:北京航空航天大学出版社,2004:1-19.]

[33]Liang Jian.Applications of Support Vector Machine in Water Quality Evaluation and Forecast[D].Hangzhou:Zhejiang University of Technology,2011:1-73.[梁坚.支持向量机在水质评价及预测中的应用研究[D].杭州:浙江工业大学,2011:1-73.]

[34]Wan Neng,Song Lirong,Wang Ruonan,et al.The Spatio-temporal Distribution of Algal Biomass in Dianchi Lake and Its Impact Factors[J].Acta Hydrobiologica Sinica,2008,32(2):184-188.[万能,宋立荣,王若南,等.滇池藻类生物量时空分布及其影响因子[J].水生生物学报,2008,32(2):184-188.]

[35]Dall’Olmo G,Gitelsona A A,Rundquist D C,et al.Assessing the Potential of SeaWiFS and MODIS for Estimating Chlorophyll Concentration in Turbid Productive Waters Using Red and Near Infrared Bands[J].Remote Sensing of Environment,2005,96(2):176-187.

[1] 郑高强,陈芸芝,汪小钦,陈曦. 基于HJ-1卫星CCD数据的厦门海域叶绿素a浓度反演[J]. 遥感技术与应用, 2015, 30(2): 235-241.