M5 model trees and neural network based modelling of ET0 in Ankara, Turkey

This paper investigates the potential of back propagation neural network and M5 model tree based regression approaches to model monthly reference evapotranspiration using climatic data of an area around Ankara, Turkey. Input parameters include monthly total sunshine hours, air temperature, relative humidity, wind speed, rainfall, and monthly time index, whereas the reference evapotranspiration calculated by FAO{56 Penman{Monteith was used as an output for both approaches. Mean square error, correlation coe cient, and several other statistics were considered to compare the performance of both modeling approaches. The results suggest a better performance by the neural network approach with this dataset, but M5 model trees, being analogous to piecewise linear functions, provide a simple linear relation for prediction of evapotranspiration for the data ranges used in this study. Di erent scenario analysis with neural networks suggests that rainfall data does not have any in uence in predicting evapotranspiration