پیش بینی پارامترهای کیفی (NO3 ,CL) رودخانه کرج با استفاده از مدل های ترکیبی شبکه عصبی-موجکی، ANN وMLR

نوع مقاله : مقالات پژوهشی

نویسندگان

دانشگاه قم

چکیده

کنترل کیفیت آب رودخانه کرج، به عنوان یکی از مهم ترین منابع تأمین کننده آب از اهمیت بسزایی برخوردار است. پیش بینی پارامترهای کیفی آب، ابزاری سودمند در جهت مدیریت منابع آب می باشد. در این تحقیق، عملکرد مدل‌های شبکه عصبی مصنوعی (ANN)، مدل ترکیبی شبکه
عصبی–موجک (WANN) ورگرسیون خطی چند متغیره (MLR)، در پیش بینی یک ماه آینده یون نیترات و کلراید ایستگاه ورودی آبگیر بیلقان واقع در رودخانه کرج، مورد ارزیابی قرار گرفت. برای این منظور از یک دوره آماری جهت ورودی مدل ها استفاده شد. در مدل ترکیبی WANN سری های زمانی واقعی دبی و پارامتر کیفی مورد نظر (نیترات و کلراید) توسط آنالیز موجک در سطوح مختلف تجزیه شده و به عنوان ورودی ANN به کار گرفته شد. کارایی مدل ها با ضریب تببین (E) و ریشه میانگین مربعات خطا (RMSE) ارزیابی شدند. نتایج حاکی از دقت بالای مدل ترکیبی شبکه
عصبی- موجکی نسبت به دو مدل دیگر بوده است؛ به‌طوریکه مدل ترکیبی شبکه عصبی –موجکی قادر بود میزان RMSE را برای یون نیترات در مقایسه با مدل شبکه عصبی و رگرسیون خطی چند متغیره به ترتیب به مقدار 13/30 درصد و 89/71 درصد و برای یون کلراید، به اندازه 3/31 درصد و 1/57 درصد بهبود بخشد. در ادامه، توانایی هر سه مدل، برای پیش بینی نقاط پیک سری زمانی بررسی شد که مدل ترکیبی WANNپیش بینی بهتری را در مقایسه با دو مدل دیگر در برداشت.

کلیدواژه‌ها


عنوان مقاله [English]

Prediction ofWater Quality Parameters (NO3, CL) in Karaj Riverby Usinga Combinationof Wavelet Neural Network, ANN and MLRModels

نویسندگان [English]

  • T. Rajaee
  • R. Rahimi Benmaran
University of Qom
چکیده [English]

IntroductionThe water quality is an issue of ongoing concern. Evaluation of the quantity and quality of running waters is considerable in hydro-environmental management.The prediction and control of the quality of Karaj river water, as one of the important needed water supply sources of Tehran, possesses great importance. In this study, Performance of Artificial Neural Network (ANN), Wavelet Neural Network combination (WANN) and multi linear regression (MLR) models, to predict next month the Nitrate (NO3) and Chloride (CL) ions of "gate ofBylaqan sluice" station located in Karaj River has been evaluated.
Materials and MethodsIn this research two separate ANN models for prediction of NO3 and CL has been expanded. Each one of the parameters for prediction (NO3 / CL) has been put related to the past amounts of the same time series (NO3 / CL) and its amounts of Q in past months.From astatisticalperiod of10yearswas usedforthe input of the models. Hence 80% of entire data from (96 initial months of data) as training set, next 10% of data (12 months) and 10% of the end of time series (terminal 12 months) were considered as for validation and test of the models, respectively. In WANNcombination model, the real monthly observed time series of river discharge (Q) and mentioned qualityparameters(NO3 / CL) were decomposed to some sub-time series at different levels by wavelet analysis.Then the decomposed quality parameters to predict and Q time series were used at different levels as inputs to the ANN technique for predicting one-step-ahead Nitrate and Chloride. These time series play various roles in the original time series and the behavior of each is distinct, so the contribution to the original time series varies from each other. In addition, prediction of high NO3 and CL values greater than mean of data that have great importancewere investigated by the models. The capability of the models was evaluated by Coefficient of Efficiency (E) and the Root Mean Square Error (RMSE).An efficiency of one corresponds to an accurate match of forecasted data to the observed data. RMSE indicates the discrepancy between the observed and predicted values
Results Discussion The results indicates that the accuracy and the ability of hybrid model of wavelet neural network had been better than the other two modes; so that hybrid model of Wavelet artificial neural network was able the improve the rate of RMSE for Nitrate ions in comparison with ANN and MLR models respectively, amounting to 30.13% and 71.89%, for chloride ion as much as 31.3% and 57.1%. In the WANN model increasing the decomposition level, in level 1 to Level 3, increases the model’s performance, but increasing the decomposition level, in levels over Level 3, decreases the model’s efficiency, because high decomposition levels lead to a large number of parameters with complex nonlinear relationships in the ANN technique.The WANN model needed 1 to 7 neurons in the hidden layer for the best performance result. In prediction of high NO3 values the amount RMSE for ANN, MLR and WANN models are 1.487, 2.645 and 0.834 ppm, respectively. Also, for CL values the mentioned statistical parameter is 0.990, 3.003 and 0.188 ppm, respectively for models.The results exhibits that the combined model of WANN the forecast was better than the other two models.
Conclusion Wavelet transforms provide useful decompositions of original time series, so that wavelet-transformed data improve the ability of a predicting model by capturing useful information on various resolution levels. The main advantage of this study is that only from the Q and slightly quality of parameter time series are used until the same quality of parameter in one month ahead is predicted. The purpose of entering Q time series with quality of parameter as inputs of models is analysis the efficacy of Q in the accuracy of prediction. owing of the high capability wavelet neural network in the prediction of quality parameters of river's water, this model can be convenient and fast way to be proposed for management of water quality resources and assurance from water quality monitoring results and reduction its costs.

کلیدواژه‌ها [English]

  • Karaj River
  • linear regression
  • Neural Network
  • Nitrate and Chloride ions
  • Wavelet Analysis
1- Adamowski J., and Chan F.H. 2011. A wavelet neural network conjunction model for groundwater level forecasting. Journal of Hydrology, 407(1- 4): 28–40.
2- Adamowski J., and Sun K. 2010. Development of a coupled wavelet transform and neural network method for flow forecasting of non- perennial rivers in semi- arid watersheds. Journal of Hydrology, 390 (1-2): 85-91.
3- Cannas B., Fanni A., Sias G., Tronei S., and Zedda M.K. 2005.River flow forecasting using neural networks and wavelet analysis. European Geosciences Union, Vienna: Austria, 7: 24–29.
4- Dastorani M.T., Azimi Fashi K.H., Talebi A., and Ekhtesasi M.R. 2012. Estimation of Suspended Sediment Using Artificial Neural Network (Case Study: JamishanWatershed in Kermanshah). Journal of the Watershed Management Resaerch, 3(6):61-74. (in Persian with English Abstract)
5- Eynard J., Grieu S.P., and Polit M. 2011.Wavelet-based multi-resolution analysis and artificial neural networks for forecasting temperature and thermal power consumption.Engineering Applications of Artificial Intelligence, 24:501-516.
6- Fernando A.K., and Kerr T. 2003.Runoff forecasting with artificial neural network model.The 3rd Pacific Conference on stormwater and aquatic resource protection,14-16 May 2003, Auckland, NZ.
7- Han J.G., Ren W.X., and Sun Z.S. 2005. Wavelet packet based damage identification of Beam structures. International. Journal of Solids and Structures, 4: 6610-6627.
8- Heydarizad M., and Mohammadzadeh H. 2012. Investigation of Seasonal and Spatial Variation of Hydrochemical Parameters in Karde River (North of Mashhad). Journal of Water and Soil, 26(5):1161-1170 (in Persian with English Abstract).
9- Imrie C.E., Durucan S., and Korre A. 2000. River flow prediction using artificial neural networks: generalisation beyond the calibration range. Journal of Hydrology, 233(1-4):138-153.
10- Kashefiolasl M., and Zaeimdar M. 2009. Necessity of quality management Jajrood River. Journal of Environmental Science and Technology, 11(2):120-129. (in Persian)
11- Kim T.W., and Valdes J.B. 2003. Nonlinear model for drought forecasting based on a conjunction of wavelet transforms and neural networks. Journal of Hydrology Engineering, ASCE, 8(6):319–28.
12- Kisi O. 2004. Multi-layer perceptrons with Levenberg–Marquardt training algorithm for suspended sediment concentration prediction and estimation. Hydrological Sciences Journal, 49(6):1025–1040.
13- Makhdoum M. 2005. Living in the environment. Tehran: Tehran University Publishings. (in Persian)
14- May D., and Sivakumar M. 2008. Comparision of artificial neural network and regression models in the prediction of urban stormwater quality. Water Environment Research; Water Environment Research, 80(1):4-9.
15- Najah A., El-shafie A., and Karim O.A. 2009.Prediction of Johor River Water Quality Parameters Using Artificial Neural Networks. European Journal of Scientific Research, 422-435.
16- Najah A., El-Shafie A., Karim O.A., Jaafar O., and El-Shafie A.H. 2011. An application of different artificial intelligences techniques for water quality prediction. Journal of the Physical Sciences, 6(22): 5298-5308.
17- Nayak P.C., SatyjiRao Y.R., and Sudheer K.P. 2006.Groundwater level forecasting in a shallow aquifer using artificial neural network approach. Water Resources Management, 20:77-90.
18- Nourani V., Hasanzade Y., Komasi M., and Sharafi A. 2008.Modeling of rainfall - runoff by using wavelet – neural network model.4th National Congress on Civil Engineering.University of Tehran (in Persian).
19- Nourani V., Komasi M., and Mano A. 2009.A multivariate ANN-Wavelet approach for rainfall runoff modeling. Water Resources Management, 23: 2877-2894.
20- Noshadi A., Salemi H., and Ahmadzade M. 2007. Simulation and prediction of some water quality parametersin the Zayanderoud River using artificial neural networks. Journal of the Water and the Wastwater, 64(18):49-65. (in Persian)
21- Palani S., Liong Sh., and Tkalich P. 2008. An ANN application for water quality forecasting. Marine Pollution Bulletin, 56:1586–1597.
22- Rajaee T., NouraniV., Zounemat K.M., and Kisi O. 2011. River suspended sediment load prediction: application of ANN and wavelet conjunction model. Journal of Hydrology Engineering, ASCE, 16(8):613-627.
23- Rajaee T. 2011. Wavelet and ANN combination model for prediction of daily suspended sediment load in rivers. Science of the Total Environment, 409:2917–2928.
24- Safavi H.R. 2010. Prediction of river water quality by adaptive neuro fuzzy inference system (ANFIS). Journal of the Environmental Studies,36(53):1-10. (in Persian)
25- Singh K. P., Basant A., Malik A., and Jain, G. 2009. Artificial Neural Network modelling of the river water quality-A case study. Journal of Ecological Modeling, 220:888-895.
26- Singh R.M. 2012. Wavelet-ANN model for flood events, Advances in Intelligent and Soft Computing, 131: 165-175.
27- Taebi A., and Vashtani M. 2000. Prediction the quality of urban runoff: Methods and Selected Model. Journal of the College of the Engineering,11(2):41-48. (in Persian)
28- Toufani P., Mosaedi A., and Fakheri Fard A. 2011. Prediction of Precipitation Applying Wavelet Network model (Case study: Zarringol stati on, Golestan province, Iran). Journal of Water and Soil, 25(5):1217-1226. )in Persian with English abstract)
29- Wen X., Fang J., Diao M., and Zhang C. 2012. Artificial Neural Network modeling of DissolvedOxygen in the Heihe River, Northwestern China. Environ Monit Assess, 185(5):4361-4371.
CAPTCHA Image