Evapotranspiration Estimation using Six Different Multi-layer PerceptronAlgorithms

Evapotranspiration has a vital importance in water resources planning and management. In this study, the applicability of six different multi-layer perceptron (MLP) algorithms, Quasi-Newton, Conjugate Gradient, Levenberg- Marquardt, One Step Secant, Resilient Back propagation and Scaled Conjugate Gradient algorithms, in modeling reference evapotranspiration (ET0) is investigated. Daily climatic data of solar radiation, air temperature, relative humidity and wind speed from Antalya City are used as inputs to the MLP models to estimate daily ET0 values obtained using FAO 56 Penman Monteith empirical method. The results of the MLP algorithms are compared with those of the multiple linear regression models with respect to root mean square error (RMSE), mean absolute error (MAE), Willmott index of agreement (d) and determination coefficient (R2). The comparison results indicate that the Levenberg-Marquardt is faster and has a better accuracy than the other five training algorithms in modeling ET0. The Levenberg-Marquardt with RMSE = 0.083 mm, MAE = 0.006 mm, d = 0.999 and R2 = 0.999 in test period was found to be superior in modeling daily ET0 than the other algorithms, respectively.

[1]  Narendra Singh Raghuwanshi,et al.  Estimating Evapotranspiration using Artificial Neural Network , 2002 .

[2]  Özgür Kisi,et al.  Long-term monthly evapotranspiration modeling by several data-driven methods without climatic data , 2015, Comput. Electron. Agric..

[3]  Ozgur Kisi,et al.  Applicability of Mamdani and Sugeno fuzzy genetic approaches for modeling reference evapotranspiration , 2013 .

[4]  A. A. Alazba,et al.  Artificial neural networks versus gene expression programming for estimating reference evapotranspiration in arid climate , 2016 .

[5]  N. S. Raghuwanshi,et al.  Artificial neural networks approach in evapotranspiration modeling: a review , 2010, Irrigation Science.

[6]  Ozgur Kisi,et al.  Modeling reference evapotranspiration using three different heuristic regression approaches , 2016 .

[7]  Ozgur Kisi,et al.  Suspended sediment estimation using neuro-fuzzy and neural network approaches/Estimation des matières en suspension par des approches neurofloues et à base de réseau de neurones , 2005 .

[8]  O. Kisi,et al.  SVM, ANFIS, regression and climate based models for reference evapotranspiration modeling using limited climatic data in a semi-arid highland environment , 2012 .

[9]  L. S. Pereira,et al.  A recommendation on standardized surface resistance for hourly calculation of reference ETo by the FAO56 Penman-Monteith method , 2006 .

[10]  Andrew W. Western,et al.  Comparison of hourly and daily reference crop evapotranspiration equations across seasons and climate zones in Australia , 2015 .

[11]  Shahaboddin Shamshirband,et al.  Comparative analysis of reference evapotranspiration equations modelling by extreme learning machine , 2016, Comput. Electron. Agric..

[12]  Tahseen Ahmed Jilani,et al.  A Comparison of First and Second Order Training Algorithms for Artificial Neural Networks , 2007, International Conference on Computational Intelligence.

[13]  Branimir Todorovic,et al.  Forecasting of Reference Evapotranspiration by Artificial Neural Networks , 2003 .

[14]  Slavisa Trajkovic,et al.  Temperature-based approaches for estimating reference evapotranspiration , 2005 .

[15]  Ali Rahimikhoob,et al.  Estimation of evapotranspiration based on only air temperature data using artificial neural networks for a subtropical climate in Iran , 2010 .

[16]  Rabee Rustum,et al.  Neural computing modeling of the reference crop evapotranspiration , 2012, Environ. Model. Softw..

[17]  Hao Yu,et al.  Neural Network Training with Second Order Algorithms , 2012 .

[18]  S. Shukla,et al.  Support vector machine based modeling of evapotranspiration using hydro-climatic variables in a sub-tropical environment , 2015 .

[19]  S. Heddam,et al.  Modeling daily reference evapotranspiration (ET0) in the north of Algeria using generalized regression neural networks (GRNN) and radial basis function neural networks (RBFNN): a comparative study , 2012, Meteorology and Atmospheric Physics.

[20]  Claudio Gandolfi,et al.  Comparison of six evapotranspiration models for a surface irrigated maize agro-ecosystem in Northern Italy , 2013 .

[21]  Yu Feng,et al.  Comparison of ELM, GANN, WNN and empirical models for estimating reference evapotranspiration in humid region of Southwest China , 2016 .

[22]  Ozgur Kisi,et al.  Evapotranspiration modelling from climatic data using a neural computing technique , 2007 .

[23]  G. Hoogenboom,et al.  A comparison of ASCE and FAO-56 reference evapotranspiration for a 15-min time step in humid climate conditions , 2009 .

[24]  Pau Martí,et al.  Assessment of a 4-input artificial neural network for ETo estimation through data set scanning procedures , 2010, Irrigation Science.

[25]  M. Jabloun,et al.  Evaluation of FAO-56 methodology for estimating reference evapotranspiration using limited climatic data Application to Tunisia , 2008 .

[26]  Pau Martí,et al.  Reference evapotranspiration estimation without local climatic data , 2011, Irrigation Science.

[27]  Richard G. Allen,et al.  Prediction Accuracy for Projectwide Evapotranspiration Using Crop Coefficients and Reference Evapotranspiration , 2005 .

[28]  Narendra Singh Raghuwanshi,et al.  Evapotranspiration Modeling Using Second-Order Neural Networks , 2014 .