ارزیابی مدل حداقل مربعات ماشین بردار پشتیبان در برآورد تبخیر و مقایسه با مدلهای تجربی

نوع مقاله: مقاله اصلی

نویسندگان

1 کارشناس ارشد، گروه منابع آب، دانشکده منابع طبیعی، دانشگاه بیرجند، بیرجند، ایران

2 دانشیار، گروه مهندسی آب، دانشکده‌ کشاورزی، دانشگاه بیرجند، بیرجند، ایران

3 استادیار، گروه مهندسی آب، دانشکده‌ کشاورزی، دانشگاه بیرجند، بیرجند، ایران

چکیده

در این تحقیق با استفاده از پارامترهای هواشناسی در دشت بیرجند در استان خراسان جنوبی در دوره 16 ساله به ارزیابی عملکرد آزمون گاما و مقایسه دقت مدل‌های حداقل مربعات ماشین­بردار و روش‌های تجربی به‌منظور تخمین میزان تبخیر پرداخته شد.  با استفاده از روش آزمون گاما از میان پارامترهای تأثیرگذار بر تبخیر، پارامترهای بهینه ورودی جهت مدل‌سازی تخمین تبخیر از میان 90 ترکیب معین، تعیین گردید. تعداد 7 ترکیب برتر نسبت به ترکیب‌های دیگر به‌دست آمد، سپس ترکیب بهینه با استفاده از مدل حداقل مربعات ماشین بردار پشتیبان با توابع کرنل مختلف و روش‌های تجربی موردارزیابی قرارگرفتند. نتایج نشان‌دهنده عملکرد مدل LSSVM-poly (چندجمله‌ای)، در ترکیب با متغیرهای دمای کمینه، دمای میانگین، سرعت باد و ساعات آفتابی با شاخص‌های عملکرد (8915/0 R2= و 995/0 RMSE=) نسبت به توابع کرنل و دیگر روش‌های تجربی دارای دقت بالاتری است.

کلیدواژه‌ها

موضوعات


عنوان مقاله [English]

Evaluation of LSSVM Model to Estimation of Evaporation and its Comparison with Empirical Models

نویسندگان [English]

  • Mohadeseh Kavoosi 1
  • Abbas Khasheisiuki 2
  • Mohsen Pourrezabilondi 3
  • Mohammad Hossein Najafi 3
1 M.Sc., Department of Water Resources, Faculty of Natural Resources, Birjand University, Birjand, Iran
2 Associate Prof., Department of Water Engineering, Faculty of Agriculture, Birjand University, Birjand, Iran
3 Assistant Prof., Department of Water Engineering, Faculty of Agriculture, Birjand University, Birjand, Iran
چکیده [English]

In this research, we used the meteorological parameters of Birjand Plain in South Khorasan Province during the 16-year period in order to evaluate the gamma test and to compare the accuracy of the model of least squares of the machine and experimental models to estimate evaporation. Using the gamma test method, among the parameters affecting evaporation, the optimal input parameters were determined for modeling the evapotranspiration from among 90 specified components. Seven superior components were obtained from other combinations. Then, the optimal combination was then evaluated using the least squares model of backup vector with various kernel functions and empirical methods. The results showed that the performance of the LSSVM-poly (polynomial) model, in combination with minimum temperature, average temperature, wind speed and sunny hours with performance indices (R2 = 0.9995 and RMSE = 995) has a higher accuracy compared to the kernel functions and other experimental methods. 

کلیدواژه‌ها [English]

  • Gamma Test
  • evaporation
  • LSSVM
  • Birjand

AbediKoupai J., Islamian V. and Ameri M. )2000(. Compare four methods of estimating evapotranspiration lysimeters in the area of micro-level reference data. Second National Conference on Manage of irrigation and drainage networks, Ahvaz [in Persian].

 

Adl F., Zeinalzadeh V. and Habebzadeh K.)2009(. Estimating reference evapotranspiration using different methods (case study Urmia synoptic station). Second National Conference on Irrigation and Drainage network management, Ahvaz [in Persian].

 

Alizadeh A. (2000). Principles Applied Hydrology. Publication of Imam Reza.No:816. [in Persian]

 Chang F. J., Chang K. Y. and Chang L. C. (2008). Counter-propagation fuzzyneural network for city flood control system. J. Hydrol., 358, 24-34.

 

Dehghanisanij H. T., Yamamoto and V. Rasiah. (2004). Assessment of evapotranspiration estimation models for use in semiarid environments. Agri. Water Manag., 64, 91-106.

 

Frevert, D. K., Hill, R. W. and Braaten, B. C. (1983). Estimation of FAO evapotranspiration coefficient. J. Irrig. Drain. Eng., 109(2), 265-270.

 

Gundekar H. G., Khodke U. M. and Sarkar S. (2008). Evaluation of pan coefficient for reference crop evapotranspiration for semiarid region. J. Irrig. Sci., 26, 169175.

 

Hozhbar H., Moazed H. and Shokrikoochak S. (2015). Estimation of Reference evapotranspiration (ETo) using empirical models, artificial neural network modeling and their comparison with lysimeter data in Urmia Kahrizi station. J. Irrig. Water, 4(15), 13-25 [In Persian].

 

Heidary M., Chalak A. and Khasheisuoki A. (2013). Experimental methods to determine the evaporation in semi-arid climates and mountainous Shiraz Bojnoord. National Conference and irrigation and evaporation of Kerman [in Persian].

 

Irmak S., Haman D. and Jones J. W. (2002). Evaluation of class A pan coefficients for estimating reference evapotranspiration in humid location. J. Irrig. Drain. Eng., 128(3), 153-159.

 

Irmak S. A., Irmak R. G., Allen and Jones J. W. (2003). Solar and net radiation based equations to estimate reference evapotranspiration in humid climates. J. Irrig. Drain. Eng., 129(5), 336-347.

 

Jahanbakhsheasl S., Movaheddanesh A. and Molavy V. (2001). Analysis models for estimating evapotranspiration stations in Tabriz. J. Agric. Know., 51-65 [In Persian].

 

Jensen M. E., Burtnan R. D. and Allen R. G. (1990). Evapotranspiration and irrigation water requirements, ASCE Manuals and Reports on Engineering Practices, No. 70, ASCE, New York.

 

Kumar M., Raghuwanshi N. S., Singh R., Wallender W.W.  and Pruitt W. O. (2002). Estimating evapotranspiration using artificial neural network. J. Irrig. Drain. ASCE, 128(4), 224-233.

 

Landeras G., Ortiz-Barredo A. and Lopez J. J. (2008). Comparison of artificial neural network models and empirical and semiempirical equations for daily reference evapotranspiration estimation in the Basque Country (Northern Spain). J. Agric. Water Manage., 95, 553–565.

 

Rezaei A., Khasheisuoki A. and Shahedi A. (2015). Groundwater level monitoring network design using the least squares support vector machine (LSSVM). Iran Soil Water Res., 45(4), 389-396 [In Persian].

 

Rezaei A., Shahedi A., Khasheisuoki A. and RyahyMdvar H. (2014). Performance evaluation least squares support vector machine model to predict water table. J. Irrig. Drain., 4(7), 510-520 [In Persian].

 

Sabziparvar A. A. and Shadmani M. (2012). Evaluation of pan coefficients from ANN, ANFIS, and empirical methods, for estimation of daily reference. J. Earth Space Phys., 38(1), 229-240 [In Persian].

 

Sabziparvar A. A., Tabari H., Aeini A. and Ghafouri M. (2010). Evaluation of class A pan coefficient models for estimation of reference crop evapotranspiration in cold semi-arid and warm arid climates. Water Resour. Manage., 24(5), 909-920.

 

Shiloh Shah, R. (2007). Support vector machines for classification and regression. MSc Dissertation, Computer Science, McGill University Montreal, Quebes.

 

Snyder R. L. (1992). Equation for evaporation pan to evapotranspiration conversion, J. Irrig. Drain. Eng., 118(6), 977-980.

 

Varkeshi B., ZareAbyaneh H., Marufi A., Sabziparvar F. and Soltani M. (2010). Simulation of reference evapotranspiration using artificial neural method and empirical methods and comparison with experimental Lysimeter data in cold semi-arid climate of Hamedan. J. Soil Water Conserv., 16(4), 79-100.

 

Yazdani V. and Ghahraman B. (2011). Determine the best experimental methods for estimating evaporation from the free surface in paddy fields Amol based on sensitivity analysis and comparison with results of artificial neural network. J. Water Res., 4(7), 47-58 [In Persian].