Comparison of Regression tree, artificial neural network and Hargrives-Samani in estimation of reference evapotranspiration in semi region

Document Type : Research Paper


1 MSc., Former Graduate of Irrigation and Drainage Engineering Department, Aburaihan Campus, University of Tehran, Tehran, Iran

2 Professor, Irrigation and Drainage Engineering Department, Aburaihan Campus, University of Tehran, Tehran, Iran


The purpose of this study was to evaluate three models of artificial neural networks (ANN), regression trees (M5) and Hargrives-Samani (HG) in estimation of reference evapotranspiration. For this purpose was used climate information of Sistan va Baloochestan, Kerman, Yazd and Khorasan Jonoobi from 1998 to 2008. In addition to effect of wind (U) on evapotranspiration (ET0), estimation of ET0 was done based on wind change in tree groups including U<2.48 m/s (U1), 2.48<U<3.67 m/s (U2) and U>3.67 m/s (U3). The results showed that optimum result of each tree methods was in U1 group. The amount of RMSE and R2 in ANN were 1.41 mm/day and 0.84 respectively, in MS were 1.46 mm/day and 0.83 and in HG were 2.02 mm/day and 0.69. These results showed that both ANN and MS methods are better than HG model. Besides, the run of MS to ANN is easy.


  1. پارسافر ن.، سبزی پرور ع.ا. و آیینی ع (1391) ارزیابی حساسیت معادلة فائو پنمن- مانتیث 56 نسبت به تغییرات سرعت باد در غرب ایران، گزارش کوتاه علمی. پژوهش‌های حفاظت آب و خاک (علوم کشاورزی و منابع طبیعی). 19(1):197-207.
  2. زارع ابیانه ح.، بیات ورکشی م.، معروفی ص.و امیری چایجان ر (1389) ارزیابی سیستم‌های هوشمند مصنوعی در کاهش پارامترهای تخمین تبخیرتعرق گیاه مرجع. آب و خاک (علوم و صنایع کشاورزی). 24 (2): 297-305.
  3. طالبی ع.، پورمحمدی س.و رحیمیان م.ح (1389) بررسی عوامل مؤثر در تبخیر و تعرق مرجع، با استفاده از آنالیز حساسیت معادلۀ فائو پنمن مانتیث مطالعة موردی ایستگاه‌های یزد، طبس و مروست. پژوهش‌های جغرافیای طبیعی. 73: 97-110.
  4. محجوبی ج.واعتمادشهیدی ا (1387) پیش‌بینی پارامترهای امواج ناشی از باد در بندر امیرآباد به‌کمک درخت‌های تصمیم رگرسیونی. چهارمین کنگرۀ ملی مهندسی عمران: 1-6.
  5. Allen  R.G, Pereira  L.S, Raes  D  and Smith  M (1998) Crop evapotranspiration Guidelines for computing crop water requirements. Irrigation and Drainage Paper No.56, FAO, ROME.
  6. Bhattacharya B and Solomatine D.P (2005) Neural networks and M5 model trees in modeling water level–discharge relationship. Neurocomputing. 63: 381-396.
  7. Dawson C.W and Wilby R (1998) An artificial neural network approach to rainfall-runoff modeling. Hydrological Sciences. 43(1): 47-66.
  8. Dibike Y.B and Solomatine D (2001) River Flow Forecasting Using Artificial Neural Networks.  Physics and Chemistry of the Earth, Part B: Hydrology, Oceans and Atmosphere. 26(1): 1-8.
  9. Droogers P and Allen R.G (2002) Estimating reference evapotranspiration under inaccurate data conditions.  Irrigation and Drainage Systems. 16:33–45.
  10. Etemad Shahidi A and Mahjoobi J (2009) Comparison between M5 model tree and neural networks for prediction of significant wave height in Lake Superior. Ocean Engineering. 36(15-16): 1175–1181.
  11. Hagan MT and Menhaj M (1994) Training feedforward networks with the Marquardt algoritm. IEEE Transactions on Neural Networks. 5: 989-993.
  12. Hargreaves G.H and Samani, Z.A (1985) Reference crop evapotranspiration from temperature. Applied Engineering in Agriculture. 1(1): 96–99.
  13. Kisi O (2007) Evapotranspiration modeling from climatic data using a neural computing technique. Hydrological Processes. 21(6):1925-1934.
  14. Muttiah R.S, Srinivasan R and Allen P.M (1997) Prediction of two-year peak stream-discharges using neural networks. the American Water Resources Association. 33(3):513-703.
  15. Pal M and Deswal S (2009) M5 model tree based modeling of reference evapotranspiration. Hydrolgical Processe. 23(2):1437–1443.
  16. RahimiKhoob A (2008) Comparative study of Hargreaves’s and artificial neural network’s Methodologies in estimating reference evapotranspiration in a semiarid environment. Irrigation Science. 26: 253-259.
  17. Solomatine D.P and Dulal  K.N (2003) Model trees as an alternative to neural networks in rainfall-runoff modeling. Hydrological Sience, 48(3): 399-411.
  18. Solomatine D.P and Xue Y (2004) M5 model trees and neural networks: application to floodforecasting in the upper reach of the Huai River in China. Hydrologic Engineering. 9(6): 491-501.
  19. Tan Y and Van Cauwenberghe A  (1999) Naural-network-based –stepahead predictors for nonlinear systems with time delay. Engineering Application ofArtificial Intelligence. 12: 21-25.