Simulation and Comparison of Potential Evapotranspiration by Artificial Neural Networks, ANFIS (Fuzzy Neural Network) and Decision Making M5 (Case Study; Synaptic Station of Shiraz)

Document Type : Technical Note (5 pages)

Authors

1 M.Sc. Student of Irrigation and Drainage, Faculty of Water Sciences Engineering, Shahid Chamran University of Ahvaz, Ahvaz, Iran.

2 Ph. D. Student of Irrigation and Drainage, Faculty of Water Sciences Engineering, Shahid Chamran University of Ahvaz, Ahvaz, Iran.

3 Assistance Professor, Department of Irrigation and Drainage, Faculty of Water Sciences Engineering, Shahid Chamran University of Ahvaz, Ahvaz, Iran.

4 Assistant Professor of Nature Engineering Department, Agricultural Sciences and Natural Resources University of Khuzestan.

Abstract

The proper estimation of evapotranspiration in designing, managing irrigation and drainage systems is very important. One of the methods of estimation of evapotranspiration, which is widely used in solving these problems and its prediction, are Neuro-Fuzzy Methods (ANFIS), Artificial Neural Networks (ANNs) and decision making tree M5. The purpose of this study was to evaluate the efficiency of the mentioned methods in estimating the reference evapotranspiration in the Shiraz meteorological station. For this purpose, the 5 yearly climatic data of the station were selected as inputs of the models. To implement artificial neural network model, Nero fuzzy model and decision tree M5 were used respectively from Qnet2000, MATLAB and WEKA software. In order to evaluate the results of these models, the mean squared error (RMSE), coefficient of determination (R2) and the criterion of the mean power of relative error (MAE) were used. The results of Artificial Neural Network model and ANFIS model with the help of statistical indices R2, RMSE and MAE were 0.0999, 0.099, 0.0500 and 0.0999, 0.051, and0.01119, respectively the accuracy of both models in simulation is high. Also, the correlation coefficient (R2), RMSE and MAE of decision tree model were calculated to be 0.7064, 0.0935 and 0.0414 respectively, which indicates the proper performance of the M5 tree model in predicting the reference evapotranspiration rate.

Keywords

Main Subjects

References

Abedi Koupai J, Amiri MJ, Eslamian SS (2009) Comparison of artificial neural network and physically based models for estimating of reference evapotranspiration in greenhouse. Australian Journal of Basic and Applied Sciences 3(3):2528-2535 (In Persian)
Behnia M, Akbari Valani H, Bameri M, Jabalbarezi B, Eskandari Damaneh H (2017) Potential assessment of ANNs and Adaptive Neuro Fuzzy Inference Systems (ANFIS) for simulating soil temperature at different soil profile depths. International Journal of Advanced Biological and Biomedical Research 6(1):416-423
Ghatfan A, Ammar Badia Y H and Alaa A S (2017) Estimation of reference evapotranspiration based on only temperature data using artificial neural network. American Journal of Innovative Research and Applied Sciences 157-162
Hosseini SMR, Ganji Khoram Del N, Farahani AH (2016) Estimating daily evapotranspiration by M5 decision tree and artificial neural network. Journal of Applied Research of Water Sciences 3(2):35-44 (In Persian)
Khoshnevisan B, Rafiee S, Omid M, Mousazadeh H (2014) Development of an intelligent system based on ANFIS for predicting wheat grain yield on the basis of energy inputs. Information Processing in Agriculture 14-22
Mohammadpur S, Rouhani H, Ghorbani Vaghei H, Seyediyan M, Fath Abadi A (2016) Modeling of sediment concentration due to elasticity of sharps using neuro-fuzzy system in semi-arid region. Iranian Natural Resources Journal Posture and Watershed Management 70(1) (In Persian)
Mosaedi A, Ghobayi Sogh M (2011) Estimation of daily evaporation from evaporation pan using a nerve-fuzzy comparative inference system. Iran Water Investigation Journal 5(8):170-161
Piri J, Ansari H (2012) Daily pan evaporation modelling with ANFIS and NNARX. Iran Agricultural Research Printed in the Islamic Republic of Iran Shiraz University 311(2):51-64 (In Persian)
Sameti M, Ghahraman N, Ghorbani KH (2013) Application of M5 model for estimation of reference evapotranspiration at stations in Shiraz and Kermanshah. Journal of Water Research in Agriculture 27(3):289-298 (In Persian)
Shabani A, Sepaskhah AR, Bahrami M, Razaghi F (2017) Neural network method and computational methods for more accurate estimation of reference evapotranspiration. Iran-Water Resources Research 13(1):152-162 (In Persian)
Sharifiyan H, Ghorbani KH (2014) Improve the estimation of potential evapotranspiration using the correction coefficient using the model M5 decision tree. Journal of Irrigation and Drainage 8(1):53-61 (In Persian)
Terzi Ö (2007) Data mining approach for estimation evaporation from free water surface. Applied Sciences 7(4):593-596
Zorati Pur A (2016) Comparison of the efficiency of neuro-fuzz method, artificial neural network and statistical models in estimating the suspended sediment of the river (Upstream of Taleghan plain). Journal of Rang and Watershed Management (Natural Resources of Iran) 69(1):65-78 (In Persian)
Iran-Water Resources Research
Volume 15, Issue 1
February 2019
Pages 365-371

Files

History

  • Receive Date: 07 April 2018
  • Revise Date: 11 November 2018
  • Accept Date: 16 November 2018

Share

How to cite

Statistics