Improving the Performance of ANN Model, Using Wavelet Transform and PCA Methodfor Modeling and Predict Biochemical Oxygen Demand (BOD)

Document Type : Research Article

Authors

1 Associate Professor of Hydrology and Water Resources, Faculty of Water Sciences Eng. Shahid Chamran University, Ahvaz, Iran.

2 Ph.D. Student of Water Resources Engineering, Faculty of Water Sciences Eng. Shahid Chamran University, Ahvaz, Iran.

Abstract

In recent decades, the developments of artificial intelligence to predict hydrologic models have been widely used. In this study, the ability of artificial neural network(ANN) models for modeling and predict the biological oxygen demand (BOD) is located on the Karun River in West Iran were evaluated. To improve the simulation results, wavelet analysis was used as a hybrid model. BOD index monthly time series Karun River in Mollasani station for 13 years (2002-2014) and the use of auxiliary variables dissolved oxygen (DO), river flows and monthly temperature was simulated. Thebest of inputs of model by the Principal Component Analysis method (PCA) was selected. To evaluate and compare the performance of models, Root Mean Square Error(RMSE) criteria, Coefficient of Determination (R2) and Akaike's Information Criterion (AIC) were used. The results showed that ANN has a margin of error of 0.0412 and the coefficient of determination 0.76 and application of wavelet transform on input data model improves the results to error of 0.0273 and the coefficient of determination 0.89.
 

Keywords

Main Subjects


 
منابع
[1]       Farhadian M, Haddad O, Seifollahi-Aghmiuni S, Loáiciga H. Assimilative Capacity and Flow Dilution for Water Quality Protection in Rivers. Journal of Hazardous, Toxic, and Radioactive Waste(ASCE). 2014;19(2):04014027-1-8.
[2]       Dogan E, lent Sengorur B, Koklu R. Modeling biological oxygen demand of the Melen River in Turkey using an artificial neural network technique. Journal of Environmental Management. 2009;90:1219-35.
[3]       Chapman D. Water Quality Assessments. ed f, editor. London: Chapman and Hall Ltd; 1992.
[4]       Radwan M, Willems P, El-Sadek A, Berlamont J. Modelling of dissolved oxygen and biochemical oxygen demand in river water using a detailed and simplified model. Int J River Basin Manage. 2003;1(2):97-103.
[5]       Lopes JF, Dias JM, Cardoso AC, Silva CIV. The water quality of the Ria de Aveiro lagoon, Portugal: from the observations to the implementation of a numerical model. Mar Environ Res 2005;60:594-628.
[6]       Delzer GC, McKenzie SW. Fıve-Day Bıochemıcal Oxygen Demand. Edition T, editor. USGS TWRI Book9-A7 U.S. Geological Survey TWRI Book; 1999.
[7]       Suen JP, Eheart JW, Asce M. Evaluation of neural networks for modelling nitrate concentration in rivers. Journal Water Resources Planning Management. 2003;129:505-10.
[8]       Xiang SL, Liu ZM, Ma LP. Study of multivariate linear regression analysis model for ground water quality prediction. Guizhou Sci. 2006;24:60-2.
[9]       Wu HJ, Lin ZY, Guo SL. The application of artificial neural networks in the resources and environment. Resour Environ Yangtze Basin 2000;9:237-241.
[10]    Cobaner M, Unal B, Kisi Ö. Suspended sediment concentration estimation by an adaptive neuro-fuzzy and neural network approaches using hydrometeorological data. Journal of Hydrology. 2009;367:52-61.
[11]    Kişi Ö. Evolutionary fuzzy models for river suspended sediment concentration estimation. Journal of Hydrology. 2009;372(1–4):68-79.
[12]    Ahmed AAM, Shah MA. Application of adaptive neuro-fuzzy inference system (ANFIS) to estimate the biochemical oxygen demand (BOD) of Surma River. Journal of King SaudUniversity - Engineering Sciences. 2015:1-7.
[13]    Sarkara A, Pandeyb P. River Water Quality Modelling using Artificial Neural Network Technique. Aquatic Procedia 2015;4:1070-1077.
[14]    Safavi HR. Prediction of River Water Quality by Adaptive Neuro Fuzzy Ineerence System(ANFIS). Journal of Enviromental Studies 2010;36(53):1-10.
[15]    Christos S A, Papaspyros. J.N.E., Tsihrintzis VA. An artificial neural network model and design equations for BOD and COD removal prediction in horizontal subsurface flow constructed wetlands. Chemical Engineering Journal. 2008;143(1–3):96-110.
[16]    Najah A, Elshafie A, Karim O, Jaffar O. Prediction of Johor river water quality parameters using artificial neural networks. European Journal of Scientific Research 2009;28(3):422-435.
[17]    Asadollahfardi G, Taklify. A, Ghanbari A. Application of Artificial Neural Network to Predict TDS in Talkheh Rud River. Journal of Irrigation and Drainage Engineering(ASCE). 2012;138(4):363–370.
[18]    Wen X, Fang J, Diao M, Zhang C. Artificial neural network modeling of dissolved oxygen in the Heihe River, Northwestern China. Environmental monitoring and assessment 2013;185(5):4361-4371.
[19]    Parmar KS, Bhardwaj R. Wavelet and statistical analysis of river water quality parameters. Applied Mathematics and Computation. 2013;219:10172-10182.
[20]    Jouanneau S, Recoules L, Durand MJ, Boukabache A, Picot V, Primault Y, et al. Methods for assessing biochemical oxygen demand (BOD): A review. Water Research. 2014;49:62-82.
[21]    Liang S, Han S, Sun Z. Parameter optimizationmethod for the water quality dynamic model based on data-driven theory. Marine Pollution Bulletin. 2015;98(1–2):137-147.
[22]    Olyaie E, Banejad H, Samadi MT, AR Rahmani AR, and Saghi MH. Performance Evaluation of Artificial Neural Networks for Predicting Rivers Water Quality Indices (BOD and DO) in Hamadan Morad Beik River. water and soil science. 2010;20.1(3):200-210.
[23]    Bierkens MFB. Modeling water table fluctuations by means of a stochastic differential equation. Journal of Water Resources Research. 1988;34(10):2485-2499.
[24]    Shafaei M, Fakheri Fard A, Darbandi S, and Ghorbani M. Prediction Daily Flow of Vanyar Station Using ANN and Wavelet Hybrid Procedure. Journal of Irrigation & Water Engineering. 2014;4(24):113-29.
[25]    Polikar R. Fundamental Conceptand an Overview of the Wavelet Theory Wavelet Tutorial Rowan university: Glassbord, NJ.08028; 1996.
[26]    Sifuzzaman M, Islam MR, and Ali MZ. Application of Wavelet Transform and its advantages Compared to Fourier Transform. Journal of Physical Sciences. 2009;13:121-134.
[27]    Thuillard M. A review of wavelet networks, wavelets, fuzzy wavelets and their application. ESITin: Presented in Conference,. 2000.
[28]    Okkan U. Wavelet neural network model for reservoir inflow prediction. Scientia Iranica. 2012;19(6):1445–1455.
[29]    Alizadeh MJ, Kavianpour MR. Development of wavelet-ANN models to predict water quality parameters in Hilo Bay, Pacific Ocean. Marine Pollution Bulletin. 2015;98(1–2):171-178.
[30]    Riad S, Mania J, Bouchaou L, Najjar Y. Rainfall-runoff model usinganartificial neural network approach. Mathematical and Computer Modelling. 2004;40(7–8):839-846.
[31]    Solgi A. Stream flow forecasting using combined Neural Network Wavelet model and comparsion with Adaptive Neuro Fuzzy Inference System and Artificial NeuralNetwork methods(Case Study: Gamasyab River, Nahavand). [Persian]. IRAN: Shahid Chamran University of Ahvaz,Iran.; 2014.
[32]    McCulloch WS, Pitts W. A logic calculus of the ideas imminent in nervous activity. Bull Math Biophys. 1943;5:115-33.
[33]    Rosenblatt F. Priciples of Neurodynamics: Perceptrons and the Theory of Brain Mechanics. Spartan1962.
[34]    Gallant SI. Neural Network Learning and Expert Systems: The MIT press; 1993.
[35]    Smith M. Neural Networks for Statistical Modelling. Van Nostrand Reinhold.1994. 235p.
[36]    Singh KP, Basant A, Malik A, Jain G. Artificial neural network modeling of the river water quality-A case study. Ecological Modelling 2009;220:888–895.
[37]    Govindaraju RS. Artificial Neural Networks in Hydrology. II: Hydrologic Applications. Journal of Hydrologic Engineering. 2000;5(2):124-137.
[38]    Apostolopoulou MS, Sotiropoulos DG, Livieris IE, Pintelas P. A memoryless BFGS neural network training algorithm. 7th IEEE International Conference on. 2009:216 - 221.
[39]    Minsky M, Papert S. Perceptrons. Cambridge: MIT Press,; 1969.
[40]    Jones AJ, Tsui A, de Oliveira AG. Neural models of arbitrary chaotic systems: construction and the role of time delayed feedback in control and synchronization.. Complex Int 2002;9:1-9.
[41]    Nourani V, Kisi Ö, KomasiM. Two hybrid Artificial Intelligence approaches for modeling rainfall–runoff process. Journal of Hydrology 2011;402:41–59.
[42]    Mallat SG. A wavelet tour of signal processing. 2, editor: San Diego; 1998. 557 p.
[43]    Hutcheson G, and Nick S. The multivariate social scientist: Introductory statistics using generalized linear models. Thousand Oaks, CA,Sage Publications. 1999.
[44]    Johnson RA, and Wichern DW. Applied multivariate statistical analysis 3rd Ed, editor. Englewood Cliffs, SA1982. 590 p.
[45]    Caliendo C, Parisi A. Principal component analysis applied to crash data on multilane roads. Third international SIIV Congress; 20-22 September; Bari, Italy: ANCONA SIIV 2005. p. 1-7.
[46]    Cattel RB. The scree test for the number ofthe factor. Multivariate Behavioral Research. 1996;1(2):245-76.
[47]    Singh KP, Malik A, Mohan D, Sinha S. Multivariate statistical techniques for the evaluation of spatial and temporal variations in water quality of Gomti River (India) a case study. Water Research. 2004;38(18):3980-3992.
[48]    Nourani V, Komasi M, Mano A. A Multivariate ANN-Wavelet Approach for Rainfall–Runoff Modeling. Water Resour Manage 2009;23:2877–2894.
[49]    Solgi A, Nourani V, Pourhaghi A. Forecasting Daily Precipitation Using Hybrid Model of Wavelet-Artificial Neural Network and Comparison with Adaptive Neuro Fuzzy Inference System (Case Study: Varayneh Station, Nahavand). Advances in Civil Engineering. 2014;2014:1-12.
Volume 3, Issue 4
January 2017
Pages 569-585
  • Receive Date: 10 November 2016
  • Revise Date: 09 December 2016
  • Accept Date: 21 December 2016
  • First Publish Date: 21 December 2016
  • Publish Date: 21 December 2016