Performance Evaluation of Artificial Neural Network in Predicting Dissolved Oxygen and Total Phosphorus Concentrations in the Ilam Dam Catchment

Document Type : Research Paper

Authors

1 1M.Sc. Graduate of Civil Engineering, Razi Univ., Kermanshah, Iran

2 2Assist. Prof., Dept. of Civil Eng., Faculty of Eng., Razi Univ., Kermanshah, Iran

3 3B.Sc. of Environmental Health Engineering, Technical and Vocational Training Organization- Ilam, Iran

4 4Assist. Prof., Dept. of Civil Eng., Faculty of Eng., Razi Univ., Kermanshah, Iran

Abstract

In this research, a multi-layer perceptron neural network (MLP-NN) model was used to simulate dissolved oxygen and total phosphorus in the Ilam Dam catchment. The NN model was developed using experimental data from three sub- catchments of Ilam Dam during the 2009-2010 period. Input variables of NN model including water PH, electricital conductivity, total suspended solids, temperature, total phosphorus, sulfate, ammonia, iron and total nitrogen were employed for the dissolved oxygen modeling. Input variables for total phosphorus modeling were temperature and phosphate, which have been measured at one station on the reservoir vicinity at different depths. The performance of the models was assessed by the coefficient of determination, relative error, and sum of squared errors (SSE) indices. The neural network results indicated that all the input variables affected modeling of the dissolved oxygen concentration, while the most effective parameter was the total suspended solids. Phosphate presented the highest impact on the total phosphorus modeling than the temperature. The cofficient of determination values for modeling dissolved oxygen and total phosphorus were 0.813 and 0.940, respectively. The results of NN models were then compared with the two-dimensional, laterally averaged CE-QUAL-W2 model. Based on the results, the multi-layer perceptron model showed more accurate responses than the numerical model in predicting water quality variables. Results also showed that the NN was able to predict the eutrophication process with acceptable accuracy and could be used as a valuable tool for  qualitative management of reservoir water.

Keywords

Main Subjects

References

بی‎نام، ۱۳۸۹. گزارش مطالعات تکمیلی آب شرب سد ایلام. وزارت نیرو، شرکت آب منطقه‎ای ایلام.
ترابیان ع و هاشمی س‎ح، 1381. مد‎‎ل‎سازی آب‎های سطحی: ثابت‎ها، سینتیک‎ها و نرخ‎ها. انتشارات دانشگاه تهران.
علیائی ا، بانژاد ح،  صمدی م‎ت، رحمانی ع و ساقی م‎ح،  1389. ارزیابی کارآیی شبکه عصبی مصنوعی در پیش‎بینی شاخص‎های کیفی(DO, BOD) آب رودخانه دره مرادبیک همدان.  نشریه دانش آب و خاک، جلد 1/20، شماره 3، صفحه‎های 199 تا 210.
کار آموز م و کراچیان ر، 1390. برنامه‎ریزی و مدیریت کیفی سامانه‎های منابع آب. انتشارات دانشگاه صنعتی امیرکبیر. تهران.
نورمحمدی  ده‎بالایی ف، 1391. شبیه‎سازی عددی لایه‎بندی حرارتی و اکسیژن محلول در مخزن سد ایلام. پایان‎نامه کارشناسی ارشد، دانشکده فنی دانشگاه رازی کرمانشاه.
Abdolmaleki ASH, Ahangar AGH and Soltani J, 2013. Artificial neural network (ANN) approach for predicting Cu concenteration in drinking water of Chahnimeh 1 reservoir in sistan-balochistan, Iran. Health Scope 2(1): 31-38.
Ahangar AGH, Soltani J and Abdolmaleki ASH, 2013. Predicting Mn concentration in water reservoir using artificial neural network (Chahnimeh 1 reservoir, Iran). International Journal of Agriculture and Crop Sciences 6(20): 1413-1420.
Cole TM and Wells SA, 2008. CE-QUAL-W2: A Two-Dimensional, Laterally Averaged, Hydrodynamic and Water Quality Model, Version 3.6. Department of Civil and Environmental Engineering, Portland State University, Portland.
Dolling OR and Varas EA, 2002. Artificial neural networks for streamflow prediction. Journal of hydraulic research. 40(5):547-554.
 Emamgholizadeh S, Kashi H, Marofpoor I and Zalaghi E, 2014. Prediction of water quality parameters of karoon river (Iran) by artificial intelligence-based models. International Journal of Environmental Science and Technology 11:645-656.
Heydari M, Olyaie E, Mohebzadeh H and Kisi O, 2013.  Development of a neural network technique for prediction of water quality parameters in the Delaware River, Pennsylvania. Middle- East Journal of Scientific Research.  13(10): 1367-1376.
Kisi O and Ay M, 2012. Comparison of ANN and ANFIS techniques in modeling dissolved oxygen. Sixteenth International Water Technology Conference.IWTC-16 2012, 7-10 May, Istanbul, Turkey.
Kuo JT, Hsieh MH, Lung WS and She N, 2007. Using artificial neural network for reservoir eutrophication prediction. Ecological Modeling 200: 171-177.
Kuo JT, Lung WS, Yang CP, Liu WC, Yang MD and Tang TS, 2006. Eutrophication modelling of reservoirs in Taiwan.  Environmental Modelling and Software 21(6): 829-844.
Liu WC, Chen WB and Kimura N, 2009. Impact of phosphorus load reduction on water quality in a stratified reservoir-eutrophication modeling study. Environmental Monitoring and Assessment 159: 393-406.
Palani S, Liong SY and Tkalich P, 2008. An ANN application for water quality forecasting. Marine Pollution Bulletin 56: 1586-1597.
Rankovic V, Radulovic J, Radojevic I, Ostojic A and Comic L, 2010. Neural network modeling of dissolved oxygen in the Gruza reservoir, Serbia. Ecological Modelling 221(8): 1239–1244.
 
Water and Soil Science
Volume 27, Issue 1
June 2017
Pages 159-172

Files

Share

How to cite

Statistics