Effect of Input Variables Preprocessing in Artificial Neural Network on Monthly Flow Prediction by PCA and Wavelet Transformation

Document Type : Research Paper

Authors

1 Ph.D student of Environmental Engineering, University of Tehran

2 MSc. Student of Water Resources, Faculty of Agriculture, Tarbiat Moddaress University

3 Associate Prof. of Water Resources, Faculty of Agriculture, Tarbiat Moddaress University

4 PhD student of Hydraulic Structures, Faculty of Agriculture, Tarbiat Moddaress University

Abstract

River flow forecast has of long been the focus of attention due to its wide applications in water-related sciences. Development of new models and advanced techniques will bring about drastic changes in the estimation of this dynamic and nonlinear system. In this research, feed-forward Artificial Neural Network (ANN) was used to predict monthly flow. Given the numerous flow forecast variables used in the present study, identification of variables effective in the network was necessary to help obtain improved results. For this purpose, we modeled the flow using the Principal Component Analysis (PCA) technique that reduces the number of input variables to include only the ones effective in ANN (PCA-ANN). PCA was first employed to reduce the number of input variables whereby 18 original variables were changed to 18 new components and the first 8 in the best model were then selected as network inputs. In addition, wavelet transformation was used for preprocessing input variables in the network to develop a model for flow forecasting (WNN). Comparison of the results obtained from the three models (ANN, PCA-ANN, and WNN) indicated the positive effect of preprocessing by wavelet and PCA on input variables. Another finding of the study was that the proposed model (PCA-ANN) had a simpler network architecture, faster training speed, and more satisfactory predicting performance in comparison with ANN and WNN models.

Keywords


1- Karunanithi, N., Grenney, W.J., Whitley, D., and Bovee, K. (1994). “Neural networks for river flow prediction.” J. of Computing in Civil Engineeirng, 8 (2), 201-220.
2- Kisi, O. (2004). “River flow modeling using artificial neural networks.” J. of Hydrologic Engineering, 9(1), 60-63.
3- Wang, W., Van Gelder, P. H., Vrijling, J. K., and Ma, J. (2006). “Forecasting daily streamflow using hybrid ANN models.” J. of Hydrology, 324 (1-4), 383-399.
4- Dawson, C.W., and Wilby, R. (1998). “An artificial neural network approach to rainfall-runoff modeling.” J. of Hydrol. Sci., 43, 14-66.
5- Tokar, A.S., and Markus, M. (2000). “Precipitation runoff modeling using artificial neural network and conceptual models.” J. Hydrol. Eng, ASCE., 5, 156-161.
6- ASCE Task Committee. (2000). “Artificial neural network in hydrology.” J. of Hydrologic Engineering, 5, 124-144.
7- Coulibaly, P., Ancti, F., and Bobee, B. (2000). “Daily reservoir inflow forecasting using artificial neural networks with stopped training approach.” J. of Hydrology, 230 (3-4), 244-257.
8-  رستم افشار، ن.، فهمی، ه.، و پیره، ع. (1385). شبیه‌سازی و پیش‌بینی جریان رودخانه‌ها با استفاده از شبکه عصبی و مدل فوریه. م. علمی پژوهشی تحقیقات منابع آب ایران، جلد دوم، 36-44.
9- Yapo, P., Gupta, V.K., and Sorooshian, S. (1996). “Sensitivity of conceptual rainfall-runoff algorithms to errors in input data-case of the GR2M model.” J. of Hydrology, 181 (1-4), 23-48.
10- Zealand, C., Burn, D.H., and Simonovic, S.P. (1999). “Short term streamflow forecasting using artificial neural networks.” J. of Hydrology, 214 (1-4), 32-48.
11- Bowden, G.J., Maier, H.R., and Dandy, G.C. (2005). “Input determination for neural network models in water resources applications. Part 2. Case study: forecasting salinity in a river.” J. of Hydrology, 301 (1-4), 93-107.
12-  Haykin, S., (1999). Neural networks: a comprehensive foundation, 2nd Ed., PrenticeHall.,New Jersey,USA.
13- Zhang, Y.X. (2007). “Artificial neural networks based on principal component analysis input selection for clinical pattern recognition analysis.” Talanta, 73 (1), 68-75.
14- Broadhurst, D., Goodacre, R., Jones, A., Rowland, J.J., and Kell, D.B. (1997). “Genetic algorithms as a method for variable selection in multiple linear regression and partial least squares regression, with applications to pyrolysis mass spectrometry.” Anal. Chim. Acta., 348 (1-3), 71-86.
15- Bowden, G.J., Dandy, G.C., and Maier, H.R., (2005). “Input determination for neural network models in water resources applications. Part1.background and methodology.” J. of Hydrology, 301, 75-92.
16- Zhang, Y., Li, H., Hou, A., and Havel, J. (2006). “Artificial neural networks based on principal component analysis input selection for quantification in overlapped capillary electrophoresis peaks.” Chemometrics and Intelligent Laboratory Systems, 82 (1-2), 165-175.
17- Choi, D.J., and Park, H. (2001). “A hybrid artificial neural network as a software sensor for optimal control of a wastewater treatment process.” Water Res., 35 (16), 3959-3967.
18- Lu, W.Z., Wang, W.J., Wang, X.K., Xu, Z.B., and Leung, A.Y.T. (2003). “Using improved neural network to analyze RSP, NOX and NO2 levels in urban air in Mong Kok, Hong Kong.” Environmental Monitoring and Assessment, 87 (3), 235-254.
19-  نوری، م.، و رهنما، م. ب. (1385). مدل بارندگی-رواناب با استفاده از تئوری موجک و شبکه­های عصبی مصنوعی، مطالعه موردی: هلیل رود. هفتمین کنفرانس بین‌المللی عمران، تهران، ایران.
20- Labat, D., Ababou, R., and Mangin, A. (2000). “Rainfall–runoff relations for karstic springs. Part II: continuous wavelet and discrete orthogonal multiresolution analyses.” J. of Hydrology, 238
(3-4), 149-178.
21- Wang, W., and Ding, J. (2003). “Wavelet network model and Its application to the prediction of hydrology.” Nature and Science, 1 (1), 67-71.
22- Cybenko, G. (1989). “Approximation by superposition of a sigmoidal function.” Math. Control Signals Syst., 2, 303-314.
23- Hornik, K., Stinchcombe, M., and White, H. (1989). “Multilayer feedforward networks are universal approximators.” Neural Networks, 2 (5), 359-366.
24- Zhang, G., Patuwo, B.E., and Hu, M.Y. (1998). “Forecasting with artificial neural networks: the state of the art.” Int. J. Forecasting, 14 (1), 35-62.
25- Jalili-Ghazizade, M., and Noori, R. (2008). “Prediction of municipal solid waste generation by use of artificial neural network: a case study of Mashhad.” Int. J. Environ. Res, 2 (1), 13-22.
26- نوری، ر.، اشرفی، خ.، اژدرپور، ا. (1387). مقایسه کاربرد روش‌های شبکه عصبی مصنوعی و رگرسیون خطی چندمتغیره بر اساس تحلیل ‌مؤلفه‌های اصلی برای پیش‌بینی غلظت میانگین روزانه مونوکسید کربن: مطالعه موردی شهر تهران. م. علمی-پژوهشی فیزیک زمین و فضا، 34، 135-152.
27- Milidiu, R. L., Machado, R. J., and Renteria, R. P. (1999). “Time-series forecasting through wavelets transformation and a mixture of expert models.” Neurocomputing, 28, 145-156.
28- Cannas, B., Fanni, A., See, L., and Sias, G. (2006). “Data preprocessing for river flow forecasting using neural networks: Wavelet transforms and data partitioning.” Physics and Chemistry of the Earth, 31 (18), 1164-1171.
29- Camdevyren, H., Demyr, N., Kanik, A., and Keskyn, S. (2005). “Use of principal component scores in multiple linear regression models for prediction of Chlorophyll-a in reservoirs.” Ecol Modell., 181 (4), 581-589.
30- Manly, B.F.J. (1986). Multivariate statistical methods: A Primer, 2nd Ed., Chapman and Hall,London,UK.
31- Johnson, R.A., Wichern, D.W. (1982). Applied multivariate statistical analysis, 3rd Ed., Prentice-Hall Inc., Englewood Cliffs,USA.
32- Legates, D.R., and McCabe, G.J. (1999). “Evaluating the use of "Goodness-of-fit" measures in hydrologic and hydroclimatic model validation.” Water Resour. Res., 35, 233-241.
33- Davis, J.C. (1986). Statistical and data analysis in geology, 2nd  Ed., John Wiley and Sons,New York.
34- Wackernagel, H. (1995). Multivariate geostatistics. an introduction with applications, 2nd Ed., Springer,New York andLondon.
35- Tabachnick, B.G., Fidell, L.S. (2001). Using multivariate statistics, 3rd Ed., Allyn and Bacon,Boston,London.
36- نوری، ر.، کراچیان، ر.، خدادادی، ا.، شکیبایی‌نیا، ا. (1386). ارزیابی اهمیت ایستگاههای پایش کیفی رودخانه‌ها با استفاده از آنالیزهای مولفه و فاکتور اصلی، مطالعه موردی: رودخانه کارون. م. علمی- پژوهشی آب و فاضلاب، 63 (3)، 60-69.
37- Jain, A., and Indurthy, S.K.V.P. (2003). “Comparative analysis of event based rainfall-runoff modeling techniques-deterministic, statistical, and artificial neural networks.” J. of Hydrologic Engineering, 8 (2), 93-98.
38- Jain, A., Ormsbee, L.E. (2004). “An evaluation of the available techniques for estimating missing fecal coliform data. ” J. Am. Water Resour. Assoc. 40 (6), 1617-1630.
39- Rajurkar, M.P., Kothyarib, U.C., Chaube, U.C. (2004). “Modeling of the daily rainfall-runoff relationship with artificial neural network.” J. of Hydrology, 285 (1-4), 96-113.