Forecasting Monthly Precipitation Using a Hybrid Model of Wavelet Artificial Neural Network and Comparison with Artificial Neural Network

Document Type : Original Article

Authors

1 Ph.D. Student of Water Resources Engineering, Faculty of Water Sciences, Shahid Chamran University of Ahvaz.

2 Asistant Prof, Dep. of Hydrology and Water Resources, Shahid Chamran University of Ahvaz, Iran.

3 Ph.D. Student of Water Resources Engineering, Faculty of Water Sciences, Shahid Chamran University of Ahvaz. Pourhaghiamir@yahoo.com

4 M.Sc. of Agriculture, Deputy Director in planning and development of irrigation and drainage networks Khuzestan Water

Abstract

Doubtlessly the first step in a river management is precipitation prediction of the watershed area. However, considering high-stochastic property of the process, many models are still being developed in order to define such a complex phenomenon in the field of hydrologic engineering. Recently Artificial Neural Network (ANN) is extensively used as a non-linear inter-extrapolator by hydrologists. In the present study, Wavelet Analysis combined with artificial neural network and compared with Artificial Neural Network to predict the precipitation of Varayeneh station in the city of Nahavand. For this purpose, the original time series using wavelet theory decomposed to multi sub-signals.After this these sub-signals are used as input data to Artificial Neural Network to predict monthly Precipitation. The results showed that according to correlation coefficient of 0.92 and mean square error of 0.002 for the hybrid model of Wavelet- Artificial Neural Networks, the performance of this model is better than Artificial Neural Network with correlation coefficient of 0.75 and mean square error of 0.003 and can be used for short and long term precipitation prediction.

Keywords

References

طوفانی، پ.، ا. مساعدی، ا. فاخری فرد.1390. پیش‌بینی بارش با استفاده از نظریه موجک. نشریه آب و خاک (علوم و صنایع کشاورزی) جلد 25، شماره 5، ص 1226-1217.
کماسی، م. 1386. مدل‌سازی بارش- رواناب با استفاده از مدل ترکیبی موجک- شبکه­عصبی­مصنوعی. پایان نامه کارشناسی ارشد، دانشگاه تبریز.
عبقری، ه. 1387. بررسی روش‌های پیش­بینی هوشمند مبتنی بر شبکه های عصبی موجکی و مدل‌های خود همبستگی دبی ماهانه رودخانه. پایانه نامه دکتری آبخیزداری- منابع آب، دانشگاه تهران.
 
 
 
Adamowski, J., K. Sun. 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: 85-91.
Asadi, S., J. Shahrabi, P. Abbaszadeh, S. Tabanmehr. 2013. A New Hybrid Artificial Neural Networks for Precipitation–Runoff Process Modeling. Neurocomputing: 05-23.
Chua, L. H. C., T. S. W. Wong. 2010. Improving event-based Precipitation–runoff modeling using a combined artificial neural network–kinematic wave approach. Journal of Hydrology, 390(1–2): 92-10.
Fofola, G., E.  Kumar.  P (eds). 1995. Wavelet in geophysiscs. Academic New York.
Hamzaçebi, C. 2008. Improving artificial neural networks’ performance in seasonal time series forecasting. Information Sciences, 178(23): 4550-455.
Kisi, O. 2008. Stream flow forecasting using neuro-wavelet technique. Hydrological Pro-cesses, 22: 4142–4152.
Mallat, S. G. 1998. A wavelet tour of signal processing, San Diego.
Nourani, V., M. T. Alami. , M. H. Aminfar .2009. A combined neural-wavelet model for prediction of Ligvanchai watershed precipi-tation. Engineering Applications of Artificial Intelligence, 22(3): 466-472.
Nourani, V., M. Komasi and A. Mano .2009. A Multivariate ANN-Wavelet Approach for Precipitation–Runoff Modeling. Water Resour Manage, 23: 2877–2894.
Nourani, V., Ö. Kisi, M. Komasi. 2011. Two hybrid Artificial Intelligence approaches for modeling Precipitation–runoff process. Journal of Hydrology, 402: 41–59.
Nourani, V., M. Parhizkar. 2013. Conjun-ction of SOM-based feature extraction method and hybrid wavelet-ANN approach for Precipitation–runoff modeling. Journal of Hydroinformatics, 15.3: 829-848
Riad, S., J. Mania, L. Bouchaou, Y. Najjar. 2004. Precipitation-runoff model usingan artificial neural network approach. Mathem- atical and Computer Modelling, 40(7-8): 839-846

Files

Share

How to cite

Statistics