Reference evapotranspiration estimation with k-Nearest Neighbour and Artificial neural network models using different climate input variables in the semi-arid environment

The absolute prediction of reference evapotranspiration (ETo) is an important issue for global water balance. Present study demonstrated the performance k-Nearest Neighbour (kNN) and Artificial Neural Network (ANN) models daily ETo using four combinations climatic data. kNN ANN were studied climate data during 1996-2015 in Middle Anatolia region. findings estimation with classed FAO Penman Monteith equation. outcomes values that had higher performances than all combinations. statistical indicators model showed MSE, RMSE, MAE, NSE R2 ranging from 0.541-0.031 mm day-1, 0.735-0.175 0.547-0.124 0.937-0.997 0.900-0.994 testing subset. Thus, can be used full limited input meteorological