Research & Studies

A Hybrid Neuro-Fuzzy Algorithm for Prediction of Reference Evapotranspiration

This conference paper was written by Amir Mosavi and Mohammad Edalatifar and is available in Laukaitis G. (eds) Recent Advances in Technology Research and Education. 


In this study, a hybrid algorithm of adaptive neuro fuzzy inference system (ANFIS), particle swarm optimization (PSO) and principle component analysis (PCA) is utilized to predict the reference evapotranspiration (ET0). The accuracy of the computational model is evaluated using four statistical tests including Pearson correlation coefficient (r), mean square error (MSE), root mean-square error (RMSE), and coefficient of determination (R2). The results show that the ET0 can be estimated with an acceptable accuracy trough combination of PCA and ANFIS. Moreover, the result indicated that the ANFIS model can be simplified via reducing dimensionality of the input data.


Neuro-Fuzzy, Reference evapotranspiration (ET0), Principle component analysis, Particle swarm optimization, Prediction, Forecasting, ANFIS 

About the Author: