نوع مقاله : مقاله پژوهشی

نویسندگان

1 دانشجوی کارشناسی ارشد، مهندسی آب (آبیاری و زهکشی)، دانشگاه ارومیه

2 دانشجوی دکتری مهندسی منابع آب، دانشکده مهندسی آب، دانشگاه ارومیه

3 دانشیار گروه مهندسی آب، دانشگاه ارومیه

4 دانشجوی دکتری مهندسی آب (آبیاری و زهکشی)، دانشگاه ارومیه

چکیده

برآورد دقیق تبخیر- تعرق در اعمال مدیریت بهینۀ منابع آب، ضروری است. تبخیر - تعرق مؤلفه مهمی در توازن آب در مناطق مختلف به شمار می‌رود. مهندسین آب با علم به اینکه چه مقدار از آب آبیاری به مصرف محصول می‌رسد، قادر به محاسبه مهمترین جز آب در سیکل هیدرولوژیک یعنی تبخیر - تعرق خواهند بود. در مطالعه حاضر تبخیر– تعرق روزانه دشت ارومیه با استفاده از داده‌های هواشناسی طی دوره آماری 1390 – 1363 به روش فائو– پنمن– مونتیث محاسبه و مبنای کار قرار گرفت. سپس تبخیر– تعرق با استفاده از سناریوهای مختلف با پارامترهای ورودی متفاوت، با دو مدل MLP و RBF شبکه عصبی محاسبه شد. نتایج نشان دهنده برآورد تبخیر – تعرق روزانه با دقت قابل قبول (985/0RMSE= و 963/0R2= برای شبکه MLP و 537/0RMSE= و 963/0 R2=برای شبکه RBF) با استفاده از تنها سه پارامتر دمای متوسط، ساعت آفتابی و سرعت باد می‌باشند. همچنین با مشاهده و بررسی تمام سناریو‌ها می‌توان گفت که معادله تبخیر - تعرق نسبت به پارامترهای ساعت آفتابی، سرعت باد و دما وابستگی بیشتری دارد. گرچه هر دو شبکه MLPو RBF با دقت بسیار بالایی مقدار تبخیر – تعرق را محاسبه می کنند اما در کل دقت شبکه MLP نسبت به شبکه RBF بیشتر است.

کلیدواژه‌ها

موضوعات

عنوان مقاله [English]

Forecasting evapotranspiration using artificial neural networks with the lowest meteorological data

نویسندگان [English]

  • Tohid Aligolinia 1
  • Negar Rasouli Majd 2
  • Hossein Rezaie 3
  • Anahita Jabbari 4

1 M.Sc. Student of Water Engineering (Irrigation and Drainage), Department of Water Engineering. Urmia University, Urmia, Iran

2 PhD Student of Water Resources Engineering, Department of water Engineering. Urmia University, Urmia, Iran

3 Associate Professor of Water Engineering department, Urmia University

4 PhD Student, Water Engineering (Irrigation and Drainage), Department of Water Engineering. Urmia University, Urmia, Iran

چکیده [English]

Accurate estimating evapotranspiration is crucial for water resource management. Evapotranspiration is an important component in water balance in different areas. Knowing the amount of water consumed per product, water engineers are able to calculate evapotranspiration as the most important component of hydrological cycle. In this study, the daily evapotranspiration of Urmia Plain was calculated using meteorological data during the period of 1984-2011 using FAO - Penman - Monteith as a base method. Then, evapotranspiration was calculated with the help of MLP and RBF neural network models using different scenarios with different input parameters. The results indicated that the daily evapotranspiration could be predicted with acceptable accuracy (RMSE = 0.985 and R2 = 0.963 for MLP network and RMSE = 0.537 and R2 = 0.963 for RBF network) using only three parameters: average temperature, sunshine hours, and wind speed. In general, it can be observed that evapotranspiration equation is more depended on the sunshine hours, wind speed, and temperature. Both MLP and RBF networks could be used for calculating the amount of evapotranspiration with high accuracy, but total accuracy of MLP network is more than RBF network.

کلیدواژه‌ها [English]

  • Eevapotranspiration
  • FAO - Penman – Monteith Method
  • Artificial Neural Networks
  • Urmia Plain
Aladenola O.O. and Madramootoo C.A. (2013). Evaluation of solar radiation estimation methods for reference evapotranspiration estimation in Canada. Theor. Appl. Clim., 118(3), 377-385.
 
Alizadeh A. (2007). Irrigation System Design (Vol.1), Ferdowsi University of Mashhad, Astan-e-QudsRazawi, Mashhad, Iran [in Persian].
 
Allen R.G., Pereira L.S., Raes D. and Smith, M. (1998). Crop evapotranspiration – guidelines for computing crop water requirements, Irrigation and drainage paper 56, 300(9), 305.
 
Allen R. G., and Pruitt W. O. (1988). Closure to rational use of the FAO Blany- Criddle formula, J. Irrig. Drain., 114(2), 375-380.
 
Amatya D.M., Skaggs R.W. and Gregory J.D. (1995). Comparison of methods for estimating REF-ET. J. Irrig. Drain., 121(6), 427–435.
 
Baba-Amiri O., Dinpashoh Y. and Asadi E. (2012). Calibration and evaluation of seven radiation-based reference crop evapotranspiration methods at Urmia Lake Basin, Water Soil Sci., 24(3) 143-158 [In Persian].
 
Eslami A. and Gahreman B. (2013). Sensitivity analysis and uncertainty parameters affecting in the estimation of reference evapotranspiration in models with different mathematical structure, Iranian J. Irrig. Drain., 1(7), 68-79 [In Persian].
Kairu, E. N. (1991). A review of methods for estimating evapotranspiration. Geo J., 25)4(, 371-379.
 
Kumar M., Raghuwanshi N.S., Singh R., Wallender W.W. and Pruitt, W.O. (2002). Estimating evapotranspiration using artificial neural network. J. lrrig. Drain., 128(4), 224-233.
 
Kouchakzadeh M. and Bahmani A. (2005). Assessment of artificial neural networks revenue in reducing required parameters for estimation of reference evapotranspiration. J. Agri. Sci., 4, 87-97.
 
Madadizadeh F. (2014). The difference between statistical concepts as standard deviation and standard error and how to correct their report in the medical articles, Iranian J. Med. Edu., 15(44), 353-355 [In Persian].
 
Menhaj M.B. (1998). Artificial neural networks basis, Vol. 1. Tehran, Iran [in Persian].
 
Menhaj M.B. and Seifipour, N. (1998). Application of artificial intelligence in control, Part. 2.  Professor Hesabi Publications, Tehran, Iran [In Persian]. 
 
Odhiambo L.O., Yoder R.E., Yoder D.C. and Hines J.W. (2001). Optimization of fuzzy evaporation model through neural training with input-output examples, Trans. ASAE, 44(6), 1625.
 
Rahimikhoob A., Behbahani M.R. and Fakheri J. (2012). An evaluation of four reference evapotranspiration models in a subtropical climate. Water Resour. Manag., 26(10), 2867-2881.
 
Sattari M. T., Rezazadeh Joudi A. and Nahrein F. (2014). Monthly rainfall prediction using Artificial Neural Networks and M5 model tree (Case Study: Station of Ahar). Phys. Geogr. Res. Quarterly, 46(2), 247-260 [in Persian].
 
Sayyadi H., Oladghaffari A., Faalian A. and Sadraddini A. A. (2009). Comparison of RBF and MLP neural networks. Performance of reference crop evapotranspiration, Water Soil Knowl., (1), 1-12 [In Persian]. 
 
Sentelhas P., Gillespie T. and Santos E.A. (2010). Evaluation of FAO Penman-Monteith and alternative methods for estimating reference evapotranspiration with missing data in southern Ontario, Canada. Agri. Water Manag., (97), 635-644.
 
Shahedi K. and Zarei M. (2011). Assessment of potential evapotranspiration estimation methods in Mazandaran Province. Irrig. Water Eng., 1(3), 12-21 [in Persian].
 
Singh V. P., and Xu C. Y. (1997). Evaluation and generalization of 13 mass transfer equations for determining free water evaporation, Hydrol. Proc., (11), 311-323.
 
Sudheer, K. P., Gosian, A. K. and Ramasarti, K. S. (2003). Estimating actual evapotranspiration from limited climatic data using neural computing technique. J. Irrig. Drain. Eng., 129(3), 214- 218.
 
Ventura F., Spano D., Duce P. and Snyder R. L. (1999). An evaluation of common evapotranspiration equations. Irrig. Sci., (18), 163–170.
 
Zanetti S.S., Sousa E.F., Oliveira V.P.S., Almeida F.T. and Bernardo S. (2007). Estimating evapotranspiration using artificial neural network and minimum climatological data. J. Irrig. Drain. Eng., 133 (2), 83-89.
 
Zhai L., Feng Q., Li Q., and Xu C. Y. (2010). Comparison and modification of equations for calculating evapotranspiration (ET) with data from Gansu province, northwest China. J. Irrig. Drain. Eng., (59), 477- 490.