مدلسازی و پیش‌بینی اکسیژن مورد نیاز بیولوژیکی (BOD) با استفاده از ترکیب ماشین بردار پشتیبان با تبدیل موجک

نوع مقاله : مقالات پژوهشی

نویسندگان

1 دانشگاه شهید چمران اهواز

2 دانشگاه بوعلی سینا همدان

چکیده

آلودگی های شیمیایی آب های سطحی یکی از موضوعات جدی است که کیفیت این گونه آب‌ها را تهدید می کند. این مطلب برای آب هایی که به طور مستقیم به مصارف زندگی بشر می رسند اهمیتی چند برابر بخشیده است. یکی از پارامترهایی مهمی که برای سنجش آلودگی آب استفاده می-شود شاخصBOD می باشد. در این مطالعه، توانایی مدل ماشین بردار پشتیبان (SVM) به منظور مدل سازی و پیش بینی اکسیژن مورد نیاز بیولوژیکی (BOD) در رودخانه کارون واقع در غرب کشور ایران مورد ارزیابی قرار گرفت. به منظوربررسی مدل ها به صورت ترکیبی، از تبدیل موجک استفاده شد. بعد از تجزیه پارامترها با تبدیل موجک، با استفاده از روش تجزیه به مولفه های اصلی (PCA) مولفه های مهم تعیین شدند. سپس از این مولفه های مهم به عنوان ورودی به مدل ماشین بردار پشتیبان استفاده شد تا مدل ترکیبی ماشین بردار پشتیبان-موجک (WSVM) حاصل گردید. جهت انجام این تحقیق از سری زمانی ماهانه BODرودخانه کارون در ایستگاه ملاثانی و متغیرهای کمکی اکسیژن محلول (DO)، جریان رودخانه و دمای ماهانه در یک دوره 13ساله (1393-1381) استفاده شد. نتایج بدست آمده حاکی از آن بود که مدل SVM دارای ضریب تبیین 84/0 و جذر میانگین مربعات خطای 0338/0(میلی گرم بر لیتر) می باشد و اعمال تبدیل موجک روی داده‌های ورودی مدل باعث بهبود نتایج تا ضریب تبیین94/0 و جذر میانگین مربعات خطای0210/0(میلی گرم بر لیتر) شد. بنابراین ترکیب ماشین بردار پشتیبان با تبدیل موجک یک ایده جدید برای پیش بینی مقدار BOD رودخانه کارون می باشد. در پایان مقدار BOD برای یک دوره شش ماهه با استفاده از مدل WSVMپیش بینی شد.

کلیدواژه‌ها


عنوان مقاله [English]

Modeling and Forecast Biological Oxygen Demand (BOD) using Combination Support Vector Machine with Wavelet Transform

نویسندگان [English]

  • Abazar Solgi 1
  • Amir Pourhaghi 1
  • Heidar Zarei 1
  • Hadi Ansari 2
1 ShahidChamran University of Ahvaz
2 Bu-Ali SinaUniversity
چکیده [English]

Introduction: Chemical pollution of surface water is one of the serious issues that threaten the quality of water. This would be more important when the surface waters used for human drinking supply. One of the key parameters used to measure water pollution is BOD. Because many variables affect the water quality parameters and a complex nonlinear relationship between them is established conventional methods can not solve the problem of quality management of water resources. For years, the Artificial Intelligence methods were used for prediction of nonlinear time series and a good performance of them has been reported. Recently, the wavelet transform that is a signal processing method, has shown good performance in hydrological modeling and is widely used. Extensive research has been globally provided in use of Artificial Neural Network and Adaptive Neural Fuzzy Inference System models to forecast the BOD. But support vector machine has not yet been extensively studied. For this purpose, in this study the ability of support vector machine to predict the monthly BOD parameter based on the available data, temperature, river flow, DO and BOD was evaluated.
Materials and Methods: SVM was introduced in 1992 by Vapnik that was a Russian mathematician. This method has been built based on the statistical learning theory. In recent years the use of SVM, is highly taken into consideration. SVM was used in applications such as handwriting recognition, face recognition and has good results. Linear SVM is simplest type of SVM, consists of a hyperplane that dataset of positive and negative is separated with maximum distance. The suitable separator has maximum distance from every one of two dataset. So about this machine that its output groups label (here -1 to +1), the aim is to obtain the maximum distance between categories. This is interpreted to have a maximum margin. Wavelet transform is one of methods in the mathematical science that its main idea was given from Fourier transform that was introduced in the nineteenth-century. Overall, concept of wavelet transform for current theory was presented by Morlet and a team under the supervision of Alex Grossman at the Research Center for Theoretical Physics Marcel in France. After the parameters decomposition using wavelet analysis and using principal component analysis (PCA), the main components were determined. These components are then used as input to the support vector machine model to obtain a hybrid model of Wavelet-SVM (WSVM). For this study, a series of monthly of BOD in Karun River in Molasani station and auxiliary variables dissolved oxygen (DO), temperature and monthly river flow in a 13 years period (2002-2014) were used.
Results and Discussion: To run the SVM model, seven different combinations were evaluated. Combination 6 which was contained of 4 parameters including BOD, dissolved oxygen (DO), temperature and monthly river flow with a time lag have best performance. The best structure had RMSE equal to 0.0338 and the coefficient of determination equal to 0.84. For achieving the results of the WSVM, the wavelet transform and input parameters were decomposed to sub-signal, then this sub-signals were studied with Principal component analysis (PCA) method and important components were entered as inputs to SVM model to obtain the hybrid model WSVM. After numerous run this program in certain modes and compare them with each other, the results was obtained. One of the key points about the choice of the mother wavelet is the time series. So, the patterns of the mother wavelet functions that can better adapt to diagram curved of time series can do the mappings operation and therefore will have better results. In this study, according to different wavelet tests and according to the above note, four types of mother wavelet functions Haar, Db2, Db7 and Sym3 were selected.
Conclusions: Compare the results of the monthly modeling indicate that the use of wavelet transforms can increase the performance about 5%. Different structures and sensitivity analysis showed that the most important parameter which used in this study was parameter BOD, and then flow, DO and temperature were important. This means that the most effective BOD and temperature with minimum impact. Also between different kernels types, RBF kernel showed the best performance. So, combined wavelet with support vector machine is a new idea to predict BOD value in the Karun River.

کلیدواژه‌ها [English]

  • Forecast BOD
  • Hybrid model
  • PCA
  • Karun River
1. Streeter H.W., Phelps E.B. 1925. A study of the pollution and natural purification of the Ohio River, III.Factors concerned in the phenomen a of oxidation andreaeration. Bulletin 146 Public Health Service,Washington,DC,USA.
2. Liu l., Deng L., Yong D., Dong S. 2011. Native biofilm cultured under controllable condition and used in mediated method for BOD measurement. Talanta,84:895-9.
3. Kunwar P., Singh A., Amrita M., Gunja J. 2009. Artificial neural network modeling of the river water quality-A case study. Ecol Model, 220(8):88-95.
4. Xiang S.L., Liu Z.M., Ma L.P. 2006. Study of multivariate linear regression analysis model for ground water quality prediction. Guizhou Science, 24:60-2.
5. Wu H.J., Lin Z.Y., Guo S.L. 2000. The application of artificial neural networks in the resources and environment. Resour Environ Yangtze Basin, 9:237-41.
6. Kisi O. 2008. Stream flow forecasting using neuro-wavelet technique. Hydrological Processes, 22: 4142–52.
7. Nourani V., Kisi Ö., Komasi M. 2011. Two hybrid Artificial Intelligence approaches for modeling rainfall–runoff process. Journal of Hydrology, 402:41–59.
8. Nourani V., Komasi M., Mano A. 2009. A Multivariate ANN-Wavelet Approach for Rainfall–Runoff Modeling. Water Resource Management, 23:2877–94.
9. Alizadeh M.J., Kavianpour M.R. 2015. Development of wavelet-ANN models to predict water quality parameters in Hilo Bay, Pacific Ocean. Marine Pollution Bulletin, 98(1–2):171-8.
10. Solgi A., Nourani V., Pourhaghi A. 2014. Forecasting Daily Precipitation Using Hybrid Model of Wavelet-Artificial Neural Network and Comparison with Adaptive Neuro Fuzzy Inference System (Case Study: Verayneh Station, Nahavand). Advances in Civil Engineering,1-12.
11. Christos S.A., John N.E.P., Vassilios A.T. 2008. An artificial neural network model and design equations for BOD and COD removal prediction in horizontal subsurface flow constructed wetlands. Chemical Engineering Journal,143(1–3):96-110.
12. Najah A., Elshafie A., Karim O., Jaffar O. 2009. Prediction of Johor river water quality parameters using artificial neural networks. European Journal of Scientific Research, 28(4):22-35.
13. Asadollahfardi G., Taklify A., and Ghanbari A. 2012. Application of Artificial Neural Network to Predict TDS in Talkheh Rud River. Journal of Irrigation and Drainage Engineering(ASCE),138(20):363-370.
14. Wen X., Fang J., Diao M., Zhang C. 2013. Artificial neural network modeling of dissolved oxygen in the Heihe River, Northwestern China. Environmental monitoring and assessment, 185(5):4361-71.
15. Parmar K.S., Bhardwaj R. 2013. Wavelet and statistical analysis of river water quality parameters. Applied Mathematics and Computation, 219:10172-82.
16. Jouanneau S., Recoules L., Durand M.J., Boukabache A, .Picot V., Primault Y.2014. Methods for assessing biochemical oxygen demand (BOD): A review. Water Research, 49:62-82.
17. Najah A., Shafie A.E., Kari O.A., Amr H., Shafie E. 2014. Performance of ANFIS versus MLP-NN dissolved oxygen prediction models in water quality monitoring. Environmental Science and Pollution Research, 21(3):1658-70.
18. Ahmed A.A.M., Shah S.M.A. 2015. Application of adaptive neuro-fuzzy inference system (ANFIS) to estimate the biochemical oxygen demand (BOD) of Surma River. Journal of King Saud University - Engineering Sciences.
19. Deng W., Wang G., Zhang X. 2015. A novel hybrid waterquality time series prediction method based on cloud model and fuzzy forecasting. Chemometrics and Intelligent Laboratory Systems, 149(Part A):39-49.
20. Olyaie E., Banejad H., Samadi M.T, Rahmani A.R, and Saghi M.H. 2010. Performance Evaluation of Artificial Neural Networks for Predicting Rivers Water Quality Indices (BOD and DO) in Hamadan Morad Beik River. water and soil science, 20.1(3):200-210(in Persian with English abstract).
21. Parmar K.S., Bhardwaj R. 2012. Analysis of Water Parameters Using Daubechies Wavelet (Level 5) (Db5). American Journal of Mathematics and Statistics, 2(3):57-63.
22. Riad S., Mania J., Bouchaou L., Najjar Y. 2004. Rainfall-runoff model usingan artificial neural network approach. Mathematical and Computer Modelling, 40(7–8):839-46.
23. Solgi A. 2014. Stream flow forecasting using combined Neural Network Wavelet model and comparsion with Adaptive Neuro Fuzzy Inference System and Artificial Neural Network methods(Case Study:GamasyabRiver,Nahavand). MSc.ShahidChamran University of Ahvaz,Iran(in Persian with English abstract).
24. Cortes C., Vapnik V. 1995.Support-VectorNetworks. Machine Learning, 20:273-95.
25. Sujay Raghavendra N., Paresh Chandra D. 2014. Support vector machine applications in the field of hydrology: A review. Applied Soft Computing,19(0):372-86.
26. Schölkopf, B., A. Smola and K.R. Müller. 2005. Kernel principal component analysis. Lecture Notes in Computer Science. 1327: 583-588.
27. Schölkopf, B. and A.J.Smola. 2002. Learning with Kernels. MIT Press, Cambridge, MA.
28. Grossmann A., Morlet J. 1984. Decomposition of hardy function into square integrable wavelets ofconstant shape. SIMA Journal on Mathematical Analysis (SIMA), 5:723-36.
29. Mallat S.G. 1998. A wavelet tour of signal processing. 2, editor: San Diego. 557 p.
30. Fofola-Georgiou E., Kumar P. 1995. Wavelet in geophysiscs.New York: Academic Press.
31. Hutcheson G., and Nick S.1999. The multivariate social scientist: Introductory statistics using generalized linear models. Thousand Oaks, CA,Sage Publications.