پیش بینی خشکسالی با استفاده از مدل تلفیقی شبکه عصبی مصنوعی- موجک و مدل سری زمانیARIMA

نوع مقاله : مقاله پژوهشی

نویسندگان

1 دانشجوی دکتری، گروه مهندسی آب، دانشگاه بوعلی سینا، همدان، ایران.

2 استاد گروه مهندسی آب، دانشگاه بوعلی سینا، همدان، ایران.

3 استادیار گروه مهندسی آب، دانشگاه بوعلی سینا، همدان، ایران.

چکیده

تبدیل موجک یکی از روش­های نوین و بسیار موثر در زمینه تحلیل سیگنال­ها و سری­های زمانی است. در این روش سیگنال شاخص بارش استاندارد (SPI) با استفاده از موجک مادر منتخب تجزیه شده، داده­های حاصل به­عنوان ورودی مدل شبکه عصبی مصنوعی در نظر گرفته شده و یک مدل تلفیقی برای پیش­بینی خشکسالی ارائه می­گردد. در این تحقیق، از شبکه­های عصبی مصنوعی پرسپترون چند لایه (MLP) و تابع پایه‌ای شعاعی ((RBF، سری زمانی ARIMA و هم­چنین شبکه­های عصبی مصنوعی- موجک پرسپترون چند لایه (WA-MLP) و تابع پایه‌ای شعاعی (WA-RBF) برای پیش­بینی استفاده شده است. در این خصوص، از داده‌های بارندگی ایستگاه بیدستان با دوره آماری 44 ساله در حوضه آبریز شور استفاده شد. وضعیت رطوبتی با استفاده از شاخص بارندگی استاندارد شده (SPI) در دوره‌ سه ماهه محاسبه گردید. برای تخمین مقدار SPI در هر بازه زمانی، از مقادیر مربوطه در زمان‌های ماقبل، استفاده شد. نتایج نشان داد مدل WA-MLP با دقت بالاتری (87/0=R2) مقادیر SPI و وضعیت خشکسالی کوتاه مدت را پیش‌بینی می‌کند.

کلیدواژه‌ها

موضوعات


عنوان مقاله [English]

Drought Forecasting Using Artificial Wavelet Neural Network Integrated Model (WA-ANN) and Time Series Model (ARIMA)

نویسندگان [English]

  • mahbobeh younesi 1
  • Nadiya Shahraki 1
  • Safar Marofi 2
  • Hamed Nozari 3
1 Ph.D. Student on Water Resources Engineering, Department of Science and Water Engineering, Faculty of Agriculture, Bu-Ali Sina University, Hamedan, Iran.
2 Professor, Department of Science and Water Engineering, Faculty of Agriculture, Bu-Ali Sina University, Hamedan, Iran.
3 Assistant Professor, Department of Science and Water Engineering, Faculty of Agriculture, Bu-Ali Sina University, Hamedan, Iran.
چکیده [English]

Drought prediction in water resources systems plays an important role in reducing drought damage. In recent decades, Traditional methods including: fitting and mathematical models have been widely used to predict droughts. The combination of wavelet theory and neural networks has led to the expansion of the wavelet-neural networks. The application of the wavelet as training function in the neural network has recently been identified as a substitute method in neural networks. In these models, the position and scale coefficients of the wavelets are optimized in addition to the weights (Thuillard, 2000). Considering the importance of short-term drought prediction in water resources engineering and the nonlinear characteristics of the SPI series of three months, the purpose of this study is to present an Artificial Wavelet Neural Networks integrated model for predicting short-term drought at Bidestan station in Qazvin plain.
In this research, Multi-Layer Perceptron (MLP), Radial Base Function (RBF), ARIMA time series, as well as Artificial Wavelet Neural Networks integrated model and Multi-layer Perceptron (WA-MLP) and Radial Bonding Function (WA- RBF) were used, which is done by analyzing the time series investigated by the wavelet transformation and the entry of these sub-series into an artificial neural network.
According to previous researches on drought prediction, short-term drought prediction (with the definition of a three-month standard rainfall index) using the combined model of Wavelet-Neural Network and comparing its results with artificial neural network and ARIMA time series models has not been compared. In this paper, five short-term drought prediction models have been compared and a better performance model has been introduced.

کلیدواژه‌ها [English]

  • ARIMA
  • Artificial Wavelet Neural Networks
  • Drought
  • Forecasting
  • SPI
1-    Adamowski, J., Fung Chan, H. 2011. Awavelet neural network conjunction model for groundwater level forecasting. Journal of Hydrology. Vol. 407, pp. 28-40.
 
2-    Belayneh, A., Adamowski, J., Khalil and Ozga-Zielinki, B. 2014. Long-term SPI drought forecasting in the Awash River Basin in Ethiopia using wavelet neural network and wavelet support vector regression. Journal of Hydrology. Vol. 508, pp.418-429.
 
3-    Box, G. E. P. and Jenkins, G. M. 1976. Time series analysis forecasting and control, Holden-Day, San Francisco.
 
4-    Box, G. E. P., Jenkins, G. M. and Reinsel, G. C. 1994. Time series analysis, forecasting and control, Prentice Hall, Englewood Cliffs, NJ.
5-    Broomhed, D.S., and Lowe, D. 1988. Multivar iable Functional Interpolation and Adaptive Networks, Complex system.Vol. 2, pp. 321-355.
 
6-    Cannas, B., Fanni, A., See, L., and Sias, G. 2006. Data preprocessing for river flow forecasting using neural network: wavelet transforms and data partitioning. Physics and Chemistry of the Earth. 31(18), pp. 1164-1171.
 
7-    Crespo, J. L., and Mora, E. 1993. Drought estimation with neural networks. Advances in Engineering Software.18(3), pp. 167-170.
 
8-    Cybenko, G., 1989. Approximation by super positions of a sigmoid function. Mathematics of Control, Signals and Systems. 2(4), pp. 303-314.
 
9-    Dibike, Y. B., Solomatin, D. P. and Abbot, M. B. 1999. On the encapsulation of numerical- Hydraulic models in artificial neural networks. Journal of Hydraulic Research. 37(2),pp. 147-161.
 
10- Dogan, E., Isik, S., Toluk, T. and Sanaal, M. 2007. Daily stream flow forecasting using artificial neural network,http://www.dsi.gov.tr/english/congress2007/chapter_4/108.pdf.
 
11- Golabi, M. R., Radmanesh, F., Akhondali, A. M. 2013. An investigation of artificial neural network and time series performance in the index standard precipitation drought modeling (Case study: selected stations of Khuzestan Province). Arid Biome Scientific and Research Journal. 3(1), pp. 82-87. (In Persian).
 
12- Hecht- Nielson, R. 1989. Kolmogorov's mapping neural network existence theorem. 1 st IEEE ICNN, vol. 3 San Diego, CA.
 
13- Karayiannis, N. B. and Venetsanopoulos, A. N. 1993. Artificial neural network: Learning algorithms, performance evaluation and application. Kluwer Academic Publisher, Boston.
 
14- Marofi, S., Amir Moradi, K., Parsafar, N. 2013. River flow prediction using artificial neural network and wavelet neural network models (Case study: Barandozchay river). Water and Soil Science. 3(23), pp. 93-103. (In Persian).
 
15- Mason, J. C., Price, R. K. and tem' me. 1996. A neural network model of rainfall-runoff using radial basis functions. Journal of Hydraulic Research. 34(4), pp: 537-548.
 
16- McKee, T. B., Doesken, N. J. and Kleist, J. 1993. The relation of drought frequency and duration to time scales. Preprints, 8th Conference on Applied Climatology, Anaheim, California.
 
17- Mishra, A.k. and Desai, V. R. 2005. Drought forecasting using stochastic models. Stochastic Environmental Research and Risk Assessment. 19 (5), pp. 326-339.
 
18- Mishra, A. K., Desai, V. R. 2006. Drought forecasting using feed-forward recursive neural network. Ecological Modeling.198(1-2),pp. 127-138.
 
19- Modarres, R 2007. Stream flow drought time series forecasting. Stochastic Environmental Research and Risk Assessment. 21 (3), pp. 223-233.
 
 
21- Moosavi, V.,Vafakhah, M., Shirmohammadi, B., and Behnia, N. 2013. A wavelet- ANFIS hybrid model for groundwater level forecasting for different prediction periods. Water Resource Management. 27(5), pp. 1301-1321
 
22- Nakhaei, M., Saberi Nasr, A. 2012. A Combined wavelet-artificial neural network model and its applications to the prediction of groundwater level fluctuations. Geopersia. 2(2), pp. 77-91.
 
23- Niromand, H. 1997. Time Series Analysis- One Variable and Multi Variable Methods. Ferdowsi University Press, Mashhad. (In Persian).
 
24- Nourani, V., Alami, M., and Aminfar, M. 2009. A combined neural- wavelet model for prediction of Lighvanchai watershed precipitation. Engineering Applications of Artificial Intelligence.vol 22, pp. 466-472.
 
25- Polikar, R. 1996. Fundamental concept and an overview of The wavelet theory wavelet tutorial. Rowan University Press, New jersey.
 
26- Prathumchai, K., Honda, K. and Nualchawee, K. 2001.Drought risk evaluation using remote sensing and GIS: A case study in Lopburi Province, 22nd Asian Conference on Remote Sensing. National University of Singapore. Singapore.
 
27- Rajaee, T., Ebrahimi, H. 2013. Modeling of groundwater fluetuations by wavelet transform and dynamic neural network. Water and irrigation mamagement. 4(14), pp.73-87. (In Persian).
 
28- Rajaee, T. 2011. Wavelet and ANN combination model for prediction of daily suspended sediment load in river. Science of the Total Environment. 409(15), pp. 2917-2928.
 
29- Rezaee, A. 2001. Modeling flood and drought using artificial neural networks (ANN). Proceedings of the first national conference in water crisis, Zabool University, Zabol, Iran.
 
30- Shafaee, M., Fakheri Fard, A., Darbandi, S., Ghorbani, N. A. 2013. Predicrion Daily Flow of Vanyar Station Using ANN and Wavelet Hybrid Procedure. Irrigation and Water Engineering. 4 (14), pp. 113-128. (In Persian).
 
31- Sharma, B. R., and Smakhtin, V. U. 2004. Potential of water harvesting as a strategic tool for drought mitigation. International Water Management Institue. Colombo, Sri Lanka.
 
32- Sifuzzaman, M., M.R. Islam, M.Z. Ali. 2009. Application of wavelet transform and its advantages compared to fourier transform. Journal of Physical Sciences. Vol. 13, pp. 121-134.
 
33- Steinmann, A. 2003. Drought Indicators and Triggers: A Stochastic Approach to Evaluation. Journal of the American Water Resources Association (JAWRA). 39 (5), pp: 1217-1233.
 
34- Thuillard, M. 2000. A review of wavelet networks, wavelet, fuzzy wavelet and their application. ESIT. In Presented in Conference, Aachen, Germany.