用户名: 密码: 验证码:
基于支持向量机的长江口及其邻近海域叶绿素a浓度预测模型
详细信息    查看全文 | 推荐本文 |
  • 英文篇名:A Chl-a Prediction Model Based on Support Vector Machine in Yangtze River Estuaries and Its Adjacent Sea Areas
  • 作者:李修竹 ; 苏荣国 ; 张传松 ; 石晓勇
  • 英文作者:LI Xiu-Zhu;SU Rong-Guo;ZHANG Chuan-Song;SHI Xiao-Yong;Laboratory of Marine Chemistry Theory and Technology,Ministry of Education,Ocean University of China;National Marine Hazard Mitigation Service;
  • 关键词:支持向量机 ; 长江口 ; 叶绿素a ; 预测
  • 英文关键词:support vector machine;;Yangtze River Estuary;;Chl-a;;prediction
  • 中文刊名:QDHY
  • 英文刊名:Periodical of Ocean University of China
  • 机构:中国海洋大学化学化工学院;国家海洋局海洋减灾中心;
  • 出版日期:2018-11-23
  • 出版单位:中国海洋大学学报(自然科学版)
  • 年:2019
  • 期:v.49;No.290
  • 基金:国家重点研究发展计划项目(2016YFC1402101;2016YFC1400602)资助~~
  • 语种:中文;
  • 页:QDHY201901009
  • 页数:8
  • CN:01
  • ISSN:37-1414/P
  • 分类号:72-79
摘要
本文基于长江口及其邻近海域2015年3月和7月的现场调查数据,选取水温、盐度、总氮(TN)、总磷(TP)、溶解氧和有色溶解有机物(CDOM)特征吸收系数aCDOM(355)、aCDOM(455)作为输入变量,叶绿素a浓度作为输出变量,应用支持向量机回归(SVR)算法建立模型并预测长江口邻近海域叶绿素a的浓度。结果表明,SVR构建的叶绿素a预测模型得到的预测值和实测值有很好的一致性,在0.01的显著性水平下,训练集和验证集的Pearson相关性系数分别达到0.886和0.840,均方误差MSE分别为0.024 0和0.041 8,能够较为准确预测叶绿素a浓度,研究结果可为我国近海生态环境监测提供技术支持。
        A Chl-aprediction model for Yangtze River Estuaries and its adjacent sea areas is established by using Support Vector Regression(SVR),based on the field investigation data of Yangtze River Estuaries and its adjacent sea areas in March and July 2015.The water temperature,salinity,total nitrogen(TN),total phosphorus(TP),dissolved oxygen,aCDOM(355)and aCDOM(455)were selected as input variables,and the Chl-awas selected as the output variable.The results show that the predicted values using Chl-aprediction model by SVR and measured values are in good agreement.At the significance level of0.01,the Pearson correlation coefficients of the training set and the validation set could reach 0.886 and0.840,and the MSE was 0.024 0 and 0.041 8,respectively.At the same time,the prediction model provides technical support for further research on coastal ecological environment.
引文
[1] Zhu Z Y,Wu Y,Zhang J,et al.Reconstruction of anthropogenic eutrophication in the region off the Changjiang Estuary and central Yellow Sea:From decades to centuries[J].Continental Shelf Research,2014,72(1):152-162.
    [2] Pretty J N,Mason C F,Nedwell D B,et al.Environmental costs of freshwater eutrophication in England and Wales[J].Environmental Science&Technology,2003,37(2):201-208.
    [3] Lee J H W,Huang Y,Dickman M,et al.Neural network modelling of coastal algal blooms[J].Ecological Modelling,2001,159(2):179-201.
    [4] Sivapragasam C,Muttil N,Muthukumar S,et al.Prediction of algal blooms using genetic programming[J].Marine Pollution Bulletin,2010,60(10):1849-55.
    [5]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.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.
    [6]徐子和.多项式回归预测法——论正交设计原理在时序预测中的应用[J].预测,1985(s1):104-108.XU Zihe.Multi-term regression pre-test method-Application of orthogonal Design principle in time Series Prediction[J].Prediction,1985(s1):104-108.
    [7]朱世平,刘载文,王小艺,等.灰色理论与神经网络在水华预测中的应用[J].计算机工程与应用,2011,47(13):231-233.ZHU Shiping,LIU Zaiwen,WANG Xiaoyi,et al.Gray theory and neural network prediction for water bloom[J].Computer Engineering and Applications.2011,47(13):231-233.
    [8] Vapnik V N.The nature of statistical learning theory[J].IEEE Transactions on Neural Networks,1997,8(6):1564-1564.
    [9]陆赛英,葛人峰,刘丽慧.东海陆架水域营养盐的季节变化和物理输运的规律[J].海洋学报,1996,18(5):41-51.LU Saiying,GE Renfeng,LIU Lihui.Seasonal variation and physical transport of nutrients in the waters of the East China Sea shelf[J].Acta Oceanologica Sinica,1996,18(5):41-51.
    [10]向先全,陶建华.基于模糊识别和遗传神经网络的渤海湾叶绿素a预测研究[J].海洋环境科学,2011,30(2):239-242.XIANG Xianquan,TAO Jianhua.Prediction of Chl-ain Bohai Bay by genetic neural network and fuzzy recognition[J].Marine Environmental Sciences,2011,30(2):239-242.
    [11] Jeffrey S W,Humphrey G F.New spectrophotometric equations for determining chlorophylls a,b,c1and c2in higher plants,algae and natural phytoplankton[J].Biochem Physiol Pflanz BPP,1975.
    [12]王洪礼,王长江,李胜朋.基于支持向量机理论的海水水质富营养化评价研究[J].海洋技术学报,2005,24(1):48-51.WANG Hongli,WANG Changjiang,LI Shengpeng.Eutro phication Evaluation of Seawarter Based on Support Vector Machine[J].Marine Technology,2005,24(1):48-51.
    [13]张成成,陈求稳,徐强,等.基于支持向量基的太湖梁梅湾叶绿素a浓度预测[J].环境科学学报,2013,33(10):2865-2861.Zhang C C,Chen Q W,Xu Q,et al.A chlorophyll-aprediction model for Meiliang bay of Taihu based on Support Vector Machine[J].Acta Scientiae Circumstantiae,2013,33(10):2856-2861.
    [14] Zeng Q,Qin L,Bao L,et al.Critical nutrient thresholds needed to control eutrophication and synergistic interactions between phosphorus and different nitrogen sources[J].Environmental Science&Pollution Research International,2016,23(20):1-12.
    [15]姚云,郑世清,沈志良.利用人工神经网络模型评价胶州湾水域富营养化水平[J].海洋环境科学,2008,27(1):10-12.YAO Yun,ZHENG Shiqing,SHEN Zhiliang.Assessment on eutrphication in Jiaozhou Bay using artificial neural networks(ANN)model[J].Marine Environmental Sciences,2008,27(1):10-12.
    [16] Yang S,Lu W,Chen N,et al.Support vector regression based QSPR for the prediction of some physicochemical properties of alkyl benzenes[J].Journal of Molecular Structure Theochem,2005,719(1):119-127.
    [17]王炜,林命週,马钦忠,等.支持向量机及其在地震预报中的应用前景[J].西北地震学报,2006,28(1):78-84.WANG Wei,LIN Mingzhou,MA Qinzhong,et al.Support vector machines and its application future in earthquake predication[J].Northwestern Seismological Journal,2006,28(1):78-84.
    [18] Chen Y W,Lin C J.Combining SVMs with various feature selection strategies[J].Studies in Fuzziness&Soft Computing,2006,207:315-324.
    [19] Keerthi S S,Lin C J.Asymptotic behaviors of support vector machines with Gaussian kernel[J].Neural Computation,2003,15(7):1667.
    [20]万鹏,王红军,徐小力.局部切空间排列和支持向量机的故障诊断模型[J].仪器仪表学报,2012,33(12):2789-2795.Wan Peng,Wang Hongjun,Xu Xiaoli.Fault diagnosis model based on local tangent space alignment and support vector machine[J].Chinese Journal of Scientific Instrumen,2012,33(12):2789-2795.
    [21] Whitehead R F,Mora S D,Demers S.Interactions of ultravioletB radiation,mixing,and biological activity on photobleaching of natural chromophoric dissolved organic matter:A mesocosm study[J].Limnology&Oceanography,2000,45(2):278-291.
    [22] Stedmon C A,Markager S,Tranvik L,et al.Photochemical production of ammonium and transformation of dissolved organic matter in the Baltic Sea[J].Marine Chemistry,2007,104(3):227-240.
    [23]侯延鹏.营养元素及光照、温度对铜绿微囊藻生长、越冬及复苏的影响研究[D].南昌:南昌大学,2008.HOU Yanpeng.Study on the Impact of Main Nutrients and Strength of Illumination、Temperature on Growth、Over-winter and Recovery of Microcystis Aeruginosa[D].Nanchang:Nanchang University,2008.
    [24]许云峰,马春子,霍守亮,等.以程海为例用支持向量机回归算法预测叶绿素a浓度[J].环境工程技术学报,2012,2(3):207-211.XU Yunfeng,MA Chunzi,HUO Shouliang,et al.Using support vector regression algorithm to predict chlorophyll-a concentrations with chenghai lake for example[J].Journal of Environmental Engineering Technology,2012,2(3):207-211.
    [25]柳小桐.BP神经网络输入层数据归一化研究[J].机械工程与自动化,2010(3):122-123.LIU Xiaotong.Study on data normalization in BP neural network[J].Mechanical Engineering and Automation,2010(3):122-123.
    [26]张博.混沌支持向量机风速短期预测及其在pcDuino平台实现[D].太原:中北大学,2014.ZHANG Bo.Study on Short-term Wind Forecasting with ChaoticSupport Vector Machine in PcDuino Platform[D].Taiyuan:North University of China,2014.
    [27]孙甜甜.冲击压路机的厚铺层压实质量检测方法研究[D].太原:太原科技大学,2010.SUN Tiantian.Research on Testing Method of Compaction Quality of Thick Layer of Impact Roller[D].Taiyuan:Taiyuan University of Science and Technology,2010.
    [28]安葳鹏,孙贝.基于分态的煤矿瓦斯浓度预测模型的研究[J].计算机工程与应用,2014,20:233-238.AN Weipeng,SUN Bei.Research of coalmine gas concentration prediction model based on sub-state[J].Computer Engineering and Applications,2014,20:233-238.
    [29] Zhang Y,Li C,Hu X.Content prediction of Chlorophyll-a in seawater based on Fuzzy BP method[C].//IEEE:Eighth International Conference on Fuzzy Systems and Knowledge Discovery,2011:611-615.
    [30] Rocha R R A,Thomaz S M,Carvalho P,et al.Modeling chlorophyll-αand dissolved oxygen concentration in tropical floodplain lakes(ParanáRiver,Brazil)[J].Brazilian Journal of Biology,2009,69(2):491-500.
    [31] Zheng D,Sun J,Wang A,et al.The Simulation of the chlorophyll-A by using the CA-SVM method and its application in Bohai Bay[C].//IEEE:International Conference on Remote Sensing,Environment and Transportation Engineering,2012:1-5.
    [32] Fogg G E.Algal cultures and phytoplankton ecology[J].Quarterly Review of Biology,1976,15(3-4):453-453.
    [33] Ryther J H.Photosynthesis and Fish Production in the Sea[J].Science,1969,166(3901):72-76.
    [34] Rochelle-Newall E J,Fisher T R.Chromophoric dissolved organic matter and dissolved organic carbon in Chesapeake Bay[J].Marine Chemistry,2002,77(1):23-41.
    [35] Massicotte P,Markager S.Using a Gaussian decomposition approach to model absorption spectra of chromophoric dissolved organic matter[J].Marine Chemistry,2016,180:24-32.
    [36] Jrgensen L,Stedmon C A,Kragh T,et al.Global trends in the fluorescence characteristics and distribution of marine dissolved organic matter[J].Marine Chemistry,2011,126(1-4):139-148.
    [37] Bai Y,Su R,Shi X.Assessing the dynamics of chromophoric dissolved organic matter in the southern Yellow Sea by excitation-emission matrix fluorescence and parallel factor analysis(EEMPARAFAC)[J].Continental Shelf Research,2014,88:103-116.
    [38] Kowalczuk P,Zablocka M,Sagan S,et al.Fluorescence measured in situ as a proxy of CDOM absorption and DOC concentration in the Baltic Sea[J].Oceanologia,2010,52(3):431-471.
    [39] Slonecker E T,Jones D K,Pellerin B A.The new Landsat 8potential for remote sensing of colored dissolved organic matter(CDOM)[J].Marine Pollution Bulletin,2016,107(2):518-527.
    [40]刘明亮,张运林,秦伯强.太湖入湖河口和开敞区CDOM吸收和三维荧光特征[J].湖泊科学,2009,21(2):234-241.LIU Mingliang,ZHANG Yunlin,QIN Boqiang.Characterization of absorption and three-dimensional excitation-emission matrix spectra of chromophoric dissolved organic matter at the river inflow and the open area in Lake Taihu[J].Journal of Lake Sciences,2009,21(2):234-241.
    [41]王磊,林丽贞,谢聿原,等.冬季东海及南海北部海域初级生产力和新生产力的初步研究[J].海洋学研究,2012,30(1):59-66.WANG Lei,LIN Lizhen,XIE Yuyuan,et al.A preliminary study on the new productivity and primary of East China Sea and northern South China Sea in winter[J].Journal of Marine Sciences,2012,30(1):59-66.
    [42]暨卫东,黄尚高.福建海岸带海水营养盐消长与温、盐、浮游植物的关系[J].热带海洋学报,1989(2):55-64.JI Weidong,HUANG Shanggao.Relationship between nutrients,salinity and phytoplankton in FUJIAN Coastal Water[J].Journal of Tropical Oceanography,1989(2):55-64.
    [43]崔毅,宋云利,杨琴芳,等.渤海溶解氧的时空变化与环境因子和浮游植物的关系初探[J].渔业科学进展,1993(14):113-118.CUI Yi,SONG Yunli,YANG Qinfang,et al.the temporal and spatial variation of dissolved oxygen and the relationship between phytoplankton and environment factors in BOHAI Sea[J].Progress In Fishery Sciences,1993(14):113-118.

© 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