ارزیابی عملکرد روش‌های ماشین‌بردار پشتیبان و سیستم استنتاج عصبی فازی تطبیقی در پیش‌بینی جریان ماهانه رودخانه‌ها (مطالعه موردی رودخانه‌های نازلو و سزار)

نوع مقاله : مقاله پژوهشی

نویسنده

استادیار گروه هیدرولوژی و مهندسی منابع آب، دانشکده مهندسی علوم آب، دانشگاه شهید چمران اهواز، اهواز، ایران

چکیده

در سال­های اخیر با رشد فناوری، روش­های نوین برای حل مسائل غیرخطی نظیر پیش­بینی جریان رودخانه­ها به صورت قابل ملاحظه­ای توسعه یافته است. از جمله روش­هایی که اخیراً توسط محققان مختلف در این زمینه مورد استفاده قرار گرفته است مدل­های ماشین بردار پشتیبان (SVM) و سیستم استنتاج عصبی فازی تطبیقی (ANFIS) می­باشد. در این مطالعه از روش­های مذکور برای پیش­بینی جریان ماهانه رودخانه­های نازلوچای و سزار در دوره آماری 1395-1335 استفاده شد. در ابتدا الگوهای ورودی در دو حالت الف) استفاده از داده­های جریان و در نظر گرفتن نقش حافظه و ب) تاثیر دادن ترم پریودیک آماده و به مدل­ها معرفی گردید. مدل‌سازی براساس 80 درصد داده‌های تاریخی ثبت شده صورت ‌گرفت (576 ماه) و با 20 (144 ماه) درصد بقیه ارزیابی گردید. عملکرد مدل­های به کار رفته با شاخص­های آماری مجذور میانگین مربعات خطا (RMSE)، نش- ساتکلیف (NS) و میانگین قدر مطلق خطای نسبی (MARE)، مورد بررسی قرار گرفت. نتایج حاصل نشان داد که روش SVM با تابع کرنل RBF بیش­ترین دقت را در پیش­بینی جریان ماهانه هر دو رودخانه داشته و استفاده از ترم پریودیک توانسته است عملکرد آن را به طور قابل ملاحظه­ای افزایش دهد. همچنین کارایی مدل ANFIS نیز با استفاده از ترم پریودیک بهبود یافته و در محل ایستگاه تپیک در الگوی M7 و برای جریان رودخانه سزار با الگوی M6 کمترین خطا را در پیش­بینی جریان داشته است. به طور کلی نتایج این مطالعه نشان داد که روش SVM از عملکرد بهتری نسبت به مدل ANFIS در پیش­بینی جریان برخوردار بوده و انتخاب تابع کرنل مناسب تاثیر مستقیمی بر کارایی آن دارد.

کلیدواژه‌ها

موضوعات


عنوان مقاله [English]

Evaluation of Support Vector Machine and Adaptive Neuro-Fuzzy Inference System Performance in Prediction of Monthly River Flow (Case Study: Nazlu chai and Sezar Rivers)

نویسنده [English]

  • Farshad Ahmadi
Assistant professor, Department of Hydrology and Water Resources Engineering, Faculty of Water Sciences Engineering, Shahid Chamran University of Ahvaz, Ahvaz, Iran
چکیده [English]

In recent years by growing technology, new methods have been substantially developed to solve nonlinear problems such as river flow forecasting. Among the available various methods, Support Vector Machine (SVM) and Adaptive Neuro-Fuzzy Inference System (ANFIS) models have been recently used by many researchers. In this study, these methods were used to predict the monthly flow of NazluChai and Sezar Rivers during 1956-2016 period. Firstly, the data were prepared in two modes: (a) using flow data and considering the role of memory; (b) influencing the periodic term. Modeling was done by 80% of the data (576 months) for training and the remaining 20% (144 months) for testing. The root mean square error (RMSE), Nash-Sutcliffe (NS) and mean absolute relative error (MARE) metrics were used to evaluate the performance of the proposed models. The results showed that the SVM method with the RBF kernel function had the best performance in predicting monthly flow of the studied rivers. In addition, the periodic term significantly increased the prediction accuracy of the SVM-RBF model. Also, the performance of the ANFIS method was improved by using the periodic term and this model had the least error in estimating the monthly flow of the Saesar and Nazlu chi Rivers in M6 and M7 patterns, respectively. In general, the results of this study showed that the SVM method performs better than the ANFIS model in monthly flow prediction and the selection of appropriate kernel function has a direct effect on its efficiency.

کلیدواژه‌ها [English]

  • Periodic effect
  • Partial autocorrelation function
  • Membership function
  • Kernel function
Babaei, M., Moeini, R. & Ehsanzadeh, E. (2019). Artificial Neural Network and Support Vector Machine Models for Inflow Prediction of Dam Reservoir (Case Study: Zayandehroud Dam Reservoir). Water Resources Management, 33(6), 2203-2218.
Bafitlhile, T.M. & Li, Z. (2019). Applicability of ε-Support Vector Machine and Artificial Neural Network for Flood Forecasting in Humid, Semi-Humid and Semi-Arid Basins in China. Water, 11(1), 85-96.
Chen, Q. Dai, G. & Liu, H. (2002). Volume of fluid model for turbulence numerical simulation of stepped spillway overflow. Journal of Hydraulic Engineering, 128(7), 683-688.
Chen, S.T. & Yu, P.S. (2007). Real-time probabilistic forecasting of flood stages. Journal of Hydrology, 340(1-2), 63-77.
Dehghani, M., Seifi, A., & Riahi-Madvar, H. (2019). Novel forecasting models for immediate-short-term to long-term influent flow prediction by combining ANFIS and Grey Wolf optimization. Journal of Hydrology.
Falehi, A. D. (2018). MOPSO based TCSC–ANFIS–POD technique: Design, simultaneous scheme, power system oscillations suppression. Journal of Intelligent & Fuzzy Systems, 34(1), 23-34.
Foroudi Khowr, A., Saneie, M. & Azhdari Moghaddam, M. (2017). Comparison of Adaptive Neuro Fuzzy Inference System (ANFIS) and Support Vector Machines (SVM) for discharge capacity prediction of a sharp-crested weirs. Iranian Journal of Irrigation & Drainage, 11(5), 772-784. (In Farsi)
Isazadeh, M., ahmadzadeh, H. & Ghorbani, M. (2016). Assessment of Kernel Functions Performance in River Flow Estimation using Support Vector Machine. Journal of Water and Soil Conservation, 23(3), 69-89.
Jang, J. S. (1993). ANFIS: adaptive-network-based fuzzy inference system. IEEE transactions on systems, man, and cybernetics, 23(3), 665-685. (In Farsi)
Khazaee Poul, A. K., Shourian, M., & Ebrahimi, H. (2019). A Comparative Study of MLR, KNN, ANN and ANFIS Models with Wavelet Transform in Monthly Stream Flow Prediction. Water Resources Management, 1-17.
Kia, I., Emadi, A., Gholami, M. (2019). Rainfall-Runoff Modeling by Adaptive Neuro-Fuzzy Inference System (ANFIS) and Multi-Variable Linear Regression (MLR). Irrigation and Water Engineering, 9(4), 39-51. (In Farsi)
Lohani, A. K., Kumar, R., & Singh, R. D. (2012). Hydrological time series modeling: A comparison between adaptive neuro-fuzzy, neural network and autoregressive techniques. Journal of Hydrology, 442, 23-35.
Mantero, P., Moser, G., & Serpico, S. B. (2005). Partially supervised classification of remote sensing images through SVM-based probability density estimation. IEEE Transactions on Geoscience and Remote Sensing, 43(3), 559-570.
Mozaiyan, M., Akhoond Ali, A., Massah Bavani3, A., Radmanesh, F., Zohrabi, N. (2015). The Impact of Climate Change on Low Flows (Case Study: Sepid Dasht Sezar). Irrigation Sciences and Engineering, 38(2), 1-19. (In Farsi)
Pham, Q. B., Yang, T. C., Kuo, C. M., Tseng, H. W., & Yu, P. S. (2019). Combing Random Forest and Least Square Support Vector Regression for Improving Extreme Rainfall Downscaling. Water, 11(3), 45-59.
Rehana, S. (2019). River Water Temperature Modelling Under Climate Change Using Support Vector Regression. In Hydrology in a Changing World (pp. 171-183). Springer, Cham.
Rezaei, E., Khashei- Siuki, A., Shahidi, A. (2014). Design of Groundwater Level Monitoring Network, Using the Model of Least Squares Support Vector Machine (LS-SVM). Iranian Journal of Soil and Water Research, 45(4), 389-396. (In Farsi)
Riahi-Madvar, H., Dehghani, M., Seifi, A., Salwana, E., Shamshirband, S., Mosavi, A., & Chau, K. W. (2019). Comparative analysis of soft computing techniques RBF, MLP, and ANFIS with MLR and MNLR for predicting grade-control scour hole geometry. Engineering Applications of Computational Fluid Mechanics, 13(1), 529-550.
Shin, K. S., Lee, T. S., & Kim, H. J. (2005). An application of support vector machines in bankruptcy prediction model. Expert systems with applications, 28(1), 127-135.
Vapnik, V.N. (1998). Statistical Learning Theory. Wiley, New York.
Wu, J., Liu, H., Wei, G., Song, T., Zhang, C., & Zhou, H. (2019). Flash Flood Forecasting Using Support Vector Regression Model in a Small Mountainous Catchment. Water, 11(7), 13-27.
Zaini, N., Malek, M. A., Yusoff, M., Mardi, N. H., & Norhisham, S. (2019). Daily River Flow Forecasting with Hybrid Support Vector Machine–Particle Swarm Optimization. In IOP Conference Series: Earth and Environmental Science (Vol. 140, No. 1, p. 012035). IOP Publishing.
Zhou, Y., Guo, S., & Chang, F. J. (2019). Explore an evolutionary recurrent ANFIS for modelling multi-step-ahead flood forecasts. Journal of hydrology, 570, 343-355.