Performance Assessment of M5 Tree Model and Genetic Programming in Tabriz Station Reference Evapotranspiration Modeling

Subject Areas : Article frome a thesis

Mohammad Taghi Sattari ¹ , Bahram Esmailzadeh ²

1 - عضو هیئت علمی گروه مهندسی آب، دانشکده کشاورزی، دانشگاه تبریز
2 - عضو هیئت علمی گروه مهندسی عمران، دانشگاه آزاد اسلامی، واحد تبریز

Received: 2017-04-15 Accepted : 2017-04-15 Published : 2017-02-19

Keywords: Reference Evapotranspiration, FAO-Penman-Monteith, Genetic Programing, M5 Tree Model,

Abstract :

Evapotranspiration has a main role in water budget assessment and management. In plant water requirements and evapotranspiration volume calculation, firstly reference evapotranspiration (ET₀) have to be computed and then plant water requirements can be estimated using different methods. In this research, firstly the reference evapotranspiration factor was calculated by standard FAO-Penman-Monteith formula via climatic data of Tabriz station, East Azerbaijan province. Climatic parameters include mean, minimum and maximum of air temperature also mean, minimum and maximum of relative humidity, rainfall, wind speed and sunshine hours were considered as an input of genetic programming and M5 tree models to estimation of monthly reference evapotranspiration as an output. Results showed that both of two approaches present exact results (determination coefficient for M5 tree model equal to 0.99 and for GP equal to 0.96) in estimating monthly reference evapotranspiration in Tabriz region, but M5 model tree, provides understandable, applicable and simple linear relations to estimate reference evapotranspiration.

References:

1)                 سامتی م، قهرمان ن و قربانی خ. 1392. کاربرد مدل M5 در برآورد تبخیر- تعرق مرجع در ایستگاه های شیراز و کرمانشاه. پژوهش آب در کشاورزی. 27(3): 289-298.

2)                 ستاری م ت، نهرین ف، عظیمی و.1392. پیش بینی تبخیر-تعرق مرجع روزانه با استفاده از مدل شبکه عصبی مصنوعی و مدل درختی M5 مطالعه موردی: ایستگاه بناب. مجله آبیاری و زهکشی ایران. 7(1): 104-113.

3)                 صمدیان فرد س، دلیر حسن نیا ر. 1394. پیش بینی چریان رودخانه شهرچای در حوضه آبریز دریاچه اورمیه با استفاده از برنامه ریزی ژنتیک و مدل درختی M5. آب و خاک. 29(5): 1190-1206.

4)                 مرادی م الف، رحیمی خوب ع. 1391. برآورد تبخیر و تعرق مرجع با استفاده از تصاویر ماهواره نوا و مدل درختی M5 برای شبکه‌های آبیاری - مطالعه موردی شبکه آبیاری قزوین. 16(62): 123-135.

5)                 Alberg D, Last M and Kandel A, 2012. Knowledge discovery in data streams with regression tree methods. WIREs Data Mining Knowledge Discovery. (2): 69-78.

6)                 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, Italy, 300 pp.

7)                 Blaney H.F, and Criddle W.D, 1950. Determining water requirements in irrigated areas from climatological and irrigation data. Soil Conservation Service Technical Paper 96. 44 pp.

8)                 Ditthakit P, and Chinnarasri CH, 2012. Estimation of pan coefficient using M5 model tree. American journal of environmental sciences 8 (2): 95-103

9)                 Esmaeilzadeh B, and Sattari MT, 2015. Monthly Evapotranspiration Modeling Using Intelligent Systems in Tabriz, Iran. Agricultural Sciense Developments. 4(3): 35-40.

10)             Guven K, Aytek A, Yuce MI and Aksoy H, 2008. Genetic Programming – based empirical model for daily reference evapotranspiration estimation. Clean, 36 (10-11): 905-912.

11)             Hargreaves G.H, and Samani Z.A, 1982. Estimating potential evapotranspiration. J. Irrigation and Drainage Engineering. ASCE, 108(3): 223–230.

12)             Kisi O, and Guven A, 2010. Evapotranspiration modeling using linear genetic programming technique. Journal of Irrigation and Drainage. 136(10): 715-723.

13)             Koza John R, 1992. Genetic Programming: On the Programming of Computers by Means of Natural Selection. Cambridge, MA: The MIT Press.

14)             Pal M, and Deswal S, 2009. M5 model tree based modeling of reference evapotranspiration. Hydrological Process. 23(10): 1437-1443

15)             Quinlan J.R, 1992. Learning with continuous classes. In proceedings AI,92 (Adams & Sterling, Eds), 343-348, Singapore: World Scientific

 

16)             Sattari, M.T, Pal, M., Yürekli, K., Ünlükara, A, 2013. M5 model trees and neural network based modelling of ET0 in Ankara, Turkey. Turkish Journal of Engineering and Environmental Science. 37: 211-219.

17)             Tabatabaee M, Mirshekari M, Sheikh Alipour Z, Tahmasebizade R, 2014. Comparing The Results Of An Empirical Equation And Artificial Intelligence To Calculate Evapotranspiration And Compare Them With The Actual Results (Case Study: Kavar And Doroudzan Weather Stations). Journal of current research in scince. 2(3): 340-345.

18)               Terzi O, 2010. Modeling of daily pan evaporation of Lake Egirdir using data-driven techniques. International Symposium on Innovations in Intelligent Systems and Applications. 320-324. Istanbul. Turkey.