Investigation of Artificial Neural Network Based Models and Sensitivity Analysis for Reference Evapotranspiration Estimating

Document Type : Original Article

Authors

1 Assistant professor of Irrigation and Drainage Engineering, Agricultural Engineering Research Institute (AERI), Agricultural Research, Education and Extension Organization (AREEO), Karaj, Iran.

2 Agricultural Engineering Research Institute, AERI

3 Associate professor of Irrigation and Drainage Engineering, Agricultural Engineering Research Institute (AERI), Agricultural Research, Education and Extension Organization (AREEO), Karaj, Iran.

Abstract

Reference evapotranspiration (ETo) is one of the most critical parameters in proper design of irrigation systems. Accurate estimation of ETo leads to reduction of water losses. Due to the ability of Artificial Neural Networks (ANNs) in computational analysis of complex processes, the main objective of this study was to investigate the sensitivity of the ETo trends to key climatic factors in Tehran province using the artificial neural networks, and compare it with the ETo-calculator software results. The ETo was calculated using meteorological data (10-year data of 12 meteorological stations in Tehran province) using the ETo-calculator software. In order to model ETo, a set of inputs to artificial neural networks including the minimum and maximum air temperature (Tmax and Tmin), the minimum and maximum relative humidity (RHmin and RHmax), sunshine hours (n), and wind speed (U2) were considered. After data tagging, by optimizing the number of hidden layers and network algorithms, output values were estimated. The results indicated that artificial neural network is a suitable technique for ETo analysis(R^2≅98% ). The best model for estimation of ETo is feed-forward Multi-Layer Perceptron (MLP) with two hidden layers in its structure (6-11-14-1), Levenberg–Marquardt training algorithm for both hidden and output layers and Linear Tanh and Tanh transfer functions for hidden and output layers, respectively. The sensitivity analysis of the model for input parameters showed that the optimal artificial neural network model and ETo calculator software have the same trend and the Tmax and n are the most effective and least effective parameters in ETo estimation, respectively. Also, based on PCA analysis results the scenario of using of four parameters (Tmax, Tmin, RHmax and U2) as the only inputs to the selected artificial neural network, can estimate ETo with an acceptable accuracy〖(R〗^2≅94% ).

Keywords


حسینی، س. م. ر.، گنجی خرم­دل، ن. و خبت­آبادی فراهانی، ا. ح. 1395. ارزیابی مدل­های تجربی و هوشمند در تخمین تبخیر و تعرق مرجع در شرایط حداقل داده­های اقلیمی؛ مطالعه موردی شهرکرد. فصلنامه علمی پژوهشی مهندسی آبیاری و آب. 7 (25): 141-128.
دین­پژوه، ی. و شریفی، ع. ر. 1392. حساسیت تبخیر و تعرق گیاه مرجع به تغییر در پارامترهای هواشناسی (مطالعه موردی: سنندج و سبزوار). نشریه دانش آب و خاک. 23 (3): 25-42.
قمرنیا، ه .و سلطانی، ن. 1397. بررسی کارآیی روش­های تجربی برآورد تبخیر-تعرق مرجع (بر پایه تشت تبخیر) در اقلیم­های مختلف (مطالعه موردی ایران). تحقیقات منابع آب ایران. 14(4): 193-174.
محمدرضاپور، ا. 1396. پیش­بینی تبخیر -تعرق پتانسیل ماهانه با استفاده از مدل­های ماشین­بردار پشتیبان، برنامه­ریزی ژنتیک و سیستم استنتاج عصبی-فازی. فصلنامه علمی پژوهشی مهندسی آبیاری و آب. 7 (27): 150-135.
نورانی، و. و سیاح­فرد، م. 1392. آنالیز حساسیت داده­های ورودی به شبکه عصبی مصنوعی به منظور برآورد مقدار تبخیر روزانه. مجله آب و فاضلاب. 3: 100-88.
یزدانی، م.، دستجردی، ج.، مهدوی، م. و  سلطانی، س. 1390. بررسی کارآیی شبکه­های عصبی پرسپترون چند لایه و زمان تأخیری در برآورد جریان­های سطحی حوزه آبخیز زاینده­رود. مجله علمی-پژوهشی علوم و مهندسی آبخیزداری ایران. 16: 62-53.
Adnan, M., Ahsan, M., Rehman, A. and Nazir, M. 2017. Estimating evapotranspiration using machine learning techniques. International Journal of Advanced Computer Science and Applications. 8 (9): 108-113.
Antonopoulos, V. and Antonopoulos, A. 2017. Daily reference evapotranspiration estimates by artificial neural networks technique and empirical equations using limited input climate variables. Computers and Electronics in Agriculture. 132: 86-96.
Chauhan, S. and Shrivastava, R.K. 2008. Performance evaluation of reference evapotranspiration estimation using climate based methods and artificial neural networks. Water Resources Management. 23(5): 825-1023.
Deo, R. and Sahin, M. 2015. Application of the artificial neural network model for prediction of monthly standardized precipitation and evapotranspiration index using hydro-meteorological parameters and climate indices in eastern Australia. Atmospheric Research. 162: 65-81.
 Huo, Z., Feng, S., Kang, S. and Dai, X. 2012. Artificial neural network models for reference evapotranspiration in an arid area of northwest China. Journal of Arid Environments. 82: 81-90.
 Laaboudi, A., Mouhouche, B. and Draoui, B. 2012. Neural network approach to reference evapotranspiration modeling from limited climatic data in arid regions. International Journal of Biometeorology. 56: 831–841.
Liu, Q., Yang, Z., Cui, B. and Sun, T. 2010. The temporal trends of reference evapotranspiration and its sensitivity to key meteorological variables in the Yellow River basin, China. Hydrological Processes. 24: 2171-2181.
 Mohamed, H., Wahed, A. and Snyder, R. L. 2008. Simple equation reference evapotranspiration from evaporation pans surrounded by fallow soil. Journal of Irrigation and Drainage Engineering, ASCE. 134 (4): 425-429.
 Mosaedi, A., Ghabaei-Sough, M., Sadeghi, H., Mooshakian, Y. and Bannayan, M. 2016. Sensitivity analysis of monthly reference crop evapotranspiration trends in Iran: a qualitative approach. Theoretical and Applied Climatology. 128 (3): 857-873.
 Pereira, A. R., Villanova, N., Pereira, A. S. and Baebieri, V. A. 1995. A model for the class-A pan coefficient. Agricultural Water Management. 76, 75–82.
 Raes, D. (2012). The ETo calculator, evapotranspiration from a reference surface. Reference Manual. Version 3.2. FAO. Rome, Italy.
 Raghuwanshi, N. S. and Wallender, W. W. 1998. Converting from pan evaporation to evapotranspiration. Journal of Irrigation and Drainage Engineering, ASCE. 124 (5): 275-277.
 Snyder, R. L. 1992. Equation for evaporation pan to evapotranspiration conversions. Journal of Irrigation and Drainage Engineering, ASCE. 118(6): 977–980.
 Tayfur, G. and Singh, V. P. 2005. Predicting longitudinal dispersion coefficient in natural streams by artificial neural network. Journal of Hydraulic Engineering. ASCE. 131 (11): 991–1000.
 Wang S., Lian, J., Peng, Y., Hu, B. and Chen, H. 2019. Generalized reference evapotranspiration models with limited climatic data based on random forest and gene expression programming in Guangxi, China. Agricultural Water Management. 221: 220-230.
 Yesilnacar, M. I., Sahinkaya, E., Naz, M. and Ozkaya, B. 2008. Neural network prediction of nitrate in groundwater of Harran plain, Turkey. Environmental Geology. 56: 19-25.
 Zeinolabedini-Rezaabad, M., Ghazanfari, S. and Salajegheh, M. 2020. ANFIS modeling with ICA, BBO, TLBO, and IWO optimization algorithms and sensitivity analysis for predicting daily reference evapotranspiration. Journal of Hydrologic Engineering.  25 (8): 20-33.
 Zhang, X., Kang, S., Zhang, L. and Lu, 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.