In this study, wedeveloped a support vector machine-based model for rapidly assessing trophic status of coastal watersby easy-to-measure parameters (aCDOM(255), aCDOM(355), aCDOM(455), turbidity (Tur), chlorophyll a (Chl a) and dissolved oxygen (DO)) with the trophic index (TRIX) serving as a reference.After the optimal penalty parameter C(45.3) and kernel parameter g (0.7) were obtained by Grid Search, the SVM model was established and its classificationaccuracy rate was 92.5% for the training data, 85.0% for the validation dataand 91.8% for the cross-validation. The results indicated that the developed technique could be useful for rapidly assessingthe eutrophication status ofcoastal waters.
孔宪喻, 苏荣国. 基于支持向量机的黄东海富营养化快速评价技术[J]. 中国环境科学, 2016, 36(1): 143-148.
KONG Xian-yu, SU Rong-guo. A support vector machine-basedtechnology for rapidly assessing trophic status of the Yellow Sea and the East China Sea. CHINA ENVIRONMENTAL SCIENCECE, 2016, 36(1): 143-148.
Vollenweider R A, Giovanardi F, Montanari G, et al. Characterization of the trophic conditions of marine coastal waters, with special reference to the NW Adriatic Sea:proposal for a trophic scale, turbidity and generalized water quality index[J]. Environmetrics, 1998,9(3):329-357.
[5]
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.
[6]
Hur J, Cho J. Prediction of BOD, COD, and total nitrogen concentrations in a typical urban river using a fluorescence excitation-emission matrix with PARAFAC and UV absorption indices[J]. Sensors, 2012,12(1):972-986.
[7]
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.
[8]
Vasel J, Praet E. On the use of fluorescence measurements to characterize wastewater[J]. Water Science & Technology, 2002, 45(4/5):109-116.
[9]
Vapnik V. The nature of statistical learning theory[M]. Springer Science & Business Media, 2000.
Hoge F E, Vodacek A, Blough N V. Inherent optical properties of the ocean:retrieval of the absorption coefficient of chromophoric dissolved organic matter from fluorescence measurements[J]. Limnology and Oceanography, 1993,38(7):1394-1402.
[15]
Giovanardi, Vollenweider R A. Trophic conditions of marine coastal waters:experience in applying the Trophic Index TRIX to two areas of the Adriatic and Tyrrhenian seas[J]. Journal of Limnology, 2004,63(2):199-218.
[16]
Parkhomenko A V, Kuftarkova E A, Subbotin A A, et al. Results of hydrochemical monitoring of Sevastopol Black Sea's offshore waters[J]. Journal of Coastal Research, 2003:907-911.
[17]
Vascetta M, Kauppila P, Furman E. Indicating eutrophication for sustainability considerations by the trophic index TRIX:does our Baltic case reveal its usability outside Italian waters[C]//PEER Conference, 17th November. 2004.
[18]
Pettine M, Casentini B, Fazi S, et al. A revisitation of TRIX for trophic status assessment in the light of the European Water Framework Directive:Application to Italian coastal waters[J]. Marine Pollution Bulletin, 2007,54(9):1413-1426.
Cristianini N, Shawe-Taylor J. An introduction to support vector machines and other kernel-based learning methods[M]. Cambridge:Cambridge University Press, 2000.
