Dissolved Oxygen Prediction Using Support Vector Machine

In this study, Support Vector Machine (SVM) technique was applied to predict the dichotomized value of Dissolved oxygen (DO) from two freshwater lakes namely Chini and Bera Lake (Malaysia). Data sample contained 11 parameters for water quality features from year 2005 until 2009. All data parameters were used to predicate the dissolved oxygen concentration which was dichotomized into 3 different levels (High, Medium, and Low). The input parameters were ranked, and forward selection method was applied to determine the optimum parameters that yield the lowest errors, and highest accuracy. Initial results showed that pH, Water Temperature, and Conductivity are the most important parameters that significantly affect the predication of DO. Then, SVM model was applied using the Anova kernel with those parameters yielded 74% accuracy rate. We concluded that using SVM models to predicate the DO is feasible, and using dichotomized value of DO yields higher prediction accuracy than using precise DO value. Keywords—Dissolved oxygen, Water quality,predication DO, Support Vector Machine.

[1]  Karl Jacobs,et al.  Elements of a decision support system for real-time management of dissolved oxygen in the San Joaquin River Deep Water Ship Channel , 2004, Environ. Model. Softw..

[2]  Mohamed Bouamar,et al.  Evaluation of the performances of ANN and SVM techniques used in water quality classification , 2007, 2007 14th IEEE International Conference on Electronics, Circuits and Systems.

[3]  Mark D. Williams,et al.  Oxygenation of anoxic water in a fluctuating water table system: an experimental and numerical study , 2000 .

[4]  J. Weston,et al.  Support vector regression with ANOVA decomposition kernels , 1999 .

[5]  Ahmed El-Shafie,et al.  An application of different artificial intelligences techniques for water quality prediction , 2011 .

[6]  Ralph Smith,et al.  Limnology—Inland water ecosystems , 2002, Journal of the North American Benthological Society.

[7]  Michael Rabadi,et al.  Kernel Methods for Machine Learning , 2015 .

[8]  Idris Mushrifah,et al.  Water Quality Changes in Chini Lake, Pahang, West Malaysia , 2007, Environmental monitoring and assessment.

[9]  Kelly O. Maloney,et al.  Stream diurnal dissolved oxygen profiles as indicators of in-stream metabolism and disturbance effects: Fort Benning as a case study , 2005 .

[10]  Gunnar Rätsch,et al.  Engineering Support Vector Machine Kerneis That Recognize Translation Initialion Sites , 2000, German Conference on Bioinformatics.

[11]  Muhammed Ernur Akiner,et al.  Pollution evaluation in streams using water quality indices: A case study from Turkey's Sapanca Lake Basin , 2012 .

[12]  Jiang Liangzhong,et al.  Water Quality Prediction Using LS-SVM and Particle Swarm Optimization , 2009, WKDD.

[13]  E. Doğan,et al.  Modeling biological oxygen demand of the Melen River in Turkey using an artificial neural network technique. , 2009, Journal of environmental management.

[14]  Kurt Hornik,et al.  kernlab - An S4 Package for Kernel Methods in R , 2004 .

[15]  Daoyi Chen,et al.  An object-oriented tool for the control of point-source pollution in river systems , 2000, Environ. Model. Softw..

[16]  Guo H. Huang,et al.  An interval-parameter fuzzy nonlinear optimization model for stream water quality management under uncertainty , 2007, Eur. J. Oper. Res..

[17]  Ahmed El-Shafie,et al.  Integrated versus isolated scenario for prediction dissolved oxygen at progression of water quality monitoring stations , 2011 .

[18]  B A Cox,et al.  A review of currently available in-stream water-quality models and their applicability for simulating dissolved oxygen in lowland rivers. , 2003, The Science of the total environment.

[19]  Sven-Olof Ryding,et al.  The control of eutrophication of lakes and reservoirs , 1989 .

[20]  A. Malik,et al.  Artificial neural network modeling of the river water quality—A case study , 2009 .

[21]  R. Thomann,et al.  Principles of surface water quality modeling and control , 1987 .