Monthly Evapotranspiration Modeling in the Absence of Climatic Data Using the Soft Computing Methods in West and Northwest of Iran

Document Type : Research Paper

Authors

• Saman Maroufpour
• Eisa Maroufpoor
• Hadi Sanikhani

Abstract

Evapotranspiration (ET0), a major component of the hydrologic cycle, is important in water resources development and irrigation planning. The ET0 for west and northwest of Iran was estimated using the FAO Penman-Montieth method (FAO-56) as the reference. The performance of four different data-driven methods, namely the Artificial Neural Networks (ANN), Adaptive Neuro Fuzzy Inference System (ANFIS) with grid partition (GP), ANFIS with subtractive clustering (SC), and Gene Expression Programming (GEP) were investigated on the ET0 estimation. Latitude, longitude and altitude of stations, and the periodicity component were used as inputs to the applied models to predict the long-term monthly ET0 using the data from 12 stations in the west and northwest of Iran. The maximum coefficients   of determination (R²) were found to be 0.994, 0.998 and 0.997 for the ANN, ANFIS-GP and ANFIS-SC models at the Sanandaj Station, respectively. The highest R² (0.982) of the GEP model was calculated for the Khoy Station. The root mean squared error ranged 0.311-1.551, 0.368-1.319, 0.450-1.80 and 0.435-0.833 mm/day for the ANN, ANFIS-GP, ANFISSC and GEP models, respectively. The results revealed the high accuracy of the GEP in the prediction of ET0. Therefore, the GEP model can be applied as a simple method in future studies as an alternative to the use of empirical relationships for the ET0 estimation.

Keywords

• Adaptive Neuro-Fuzzy Inference System
• Artificial neural network
• Crop water requirement
• Gene Expression Programming
• Geographical information

20.1001.1.20086377.1396.10.34.4.4

---

References

1)       زارع ابیانه، ح، م.، بیات‌ورکشی، ص.، معروفی، 1390. محاسبه تبخیـر و تعرق واقعی گیاه سیر به روش مدلسازی چندگانه تحـت شـرایط کاشت لایسیمتر. مجله پژوهشهای حفاظت آب و خـاک. 18(2): 212-201.

2)       ستاری، م.ت. ف، نهرین، و، عظیمی. 1392. پیش‌بینی تبخیـر-تعـرق مرجع روزانه با استفاده از مدل شـبکه عصـبی مصـنوعی و مـدل درختی M5 (مطالعه مـوردی : ایسـتگاه بنـاب ). نشـریه آبیـاری و زهکشی ایران 7(1): 113-104.

3)       صیادی ح.، غفاری، ا.ا.، فعالیان، ا.، صدرالدینی، ع.ا. 1388. مقایسه عملکرد شبکه‌های عصبی RBF و MLP در براورد تبخیر و تعرق گیاه مرجع. نشریه دانش آب و خاک 19(1): 12-1.

4)       کریمی، س.، شیری، ج.، ناظمی، ا.ح. 1392. تخمین تبخیر و تعرق گیاه مرجع با استفاده از سیستم‌های هوش مصنوعی (ANN و ANFIS) و معادله‌های تجربی. نشریه دانش آب و خاک. 23(2): 158-139.

5)       فلاح‌قالهری، غ.، موسوی‌بایگی، س.، حبیبی ‌نوخندان،  م. 1388. مقایسۀ نتایج به‌ دست آمده از کاربرد سیستم استنباط فازی ممدانی و شبکه‌های عصبی مصنوعی در پیش‌ بینی بارش فصلی، مطالعۀ موردی: منطقۀ خراسان، مجلۀ تحقیقات منابع آب ایران 5 (2): 52- 40.

6)        Abonyi, J., Andersen, H., Nagy, L. and Szeifert, F. 1999. Inverse fuzzy-process-model based direct adaptive control. Mathematics and Computers in Simulation 51: 119-132.

7)        Allen, R. G., Pereira, L. S., Raes, D. and Smith, M. 1998. Crop evapotranspiration-Guidelines for computing crop water requirements-FAO Irrigation and drainage paper 56. FAO, Rome, 300(9), D05109.

8)        Chiu, S. L. 1994. Fuzzy model identification based on cluster estimation. Journal of Intelligent and Fuzzy Systems 2: 267-278.

9)        Chiu, S. L. 1995. Extracting fuzzy rules for pattern classification by cluster estimation. In Proc. IFSA 95: 273-276.

10)    Ferreira, C. 2001. Algorithm for solving gene expression programming: a new adaptive problems. Complex Systems 13: 87-129.

11)    Jang J.S.R. 1993. ANFIS: Adaptive-network-based fuzzy inference system. IEEE Transactions on Systems, Man and Cybernetic. 23: 665–685.

12)    Jensen, M.E., Burman, R.D, and Allen, R.G. (ed). 1990. Evaportranspiration and irrigation water requirements. ASCE Mauals and Reports on Engineering Practices No 70. Am. Soc. Civil Engrs New York, NY. 442p.

13)    Jia Bing, C., Yu, L. I. U., and Ting-wu, L. E. I. 2004. Prediction of daily reference evapotranspiration using adaptive neurofuzzy inference system. Trans of the Chinese Society of Agricultural Engineering 20: 13-16.

14)    Kennedy, E. P., Condon, M., and Dowling, J. 2003. Torque-ripple minimisation in switched reluctance motors using a neuro-fuzzy control strategy. In Modelling and Simulation 106-109.

15)    Kişi, Ö. 2006. Daily pan evaporation modelling using a neuro-fuzzy computing technique. Journal of Hydrology 329: 636-646.

16)    Russell, S. O., and Campbell, P. F. 1996. Reservoir operating rules with fuzzy programming. Journal of Water Resources Planning and Management 122: 165-170.

17)    Shiri, J., Marti, P., and Singh, V. P. 2014. Evaluation of gene expression programming approaches for estimating daily evaporation through spatial and temporal data scanning. Hydrological Processes 28: 1215-1225.

18)    Tabari, H., Martinez, C., Ezani, A., and Talaee, P. H. 2013. Applicability of support vector machines and adaptive neurofuzzy inference system for modeling potato crop evapotranspiration. Irrigation Science 31: 575-588.

19)    Tayfur, G. 2002. Artificial neural networks for sheet sediment transport. Hydrological Sciences Journal 47: 879-892.

20)     TRajkovic, S., Todorovic, B. and Stankovic, M. 2003. Forecasting of reference evapotranspiration by artificial neural networks. Journal of Irrigation and Drainage Engineering, 129: 454-457.

21)     Traore, S., Wang, Y. M. and Kerh, T. 2010. Artificial neural network for modeling reference evapotranspiration complex process in Sudano-Sahelian zone. Agricultural water management, 97: 707-714.

22)    Wilson G.C., and Banzhaf, W. 2008. A comparison of cartesian genetic programming and linear genetic programming. Lecture Notes in Computer Science 4971: 182-193.

23)    Zhang, X., Kang, S., Zhang, L., and Liu, J. 2010. Spatial variation of climatology monthly crop reference evapotranspiration and sensitivity coefficients in Shiyang River Basin of northwest China. Agricultural Water Management 97: 1506-1516.