Reference Evapotranspiration Estimation With kNN and ANN Models Using Different Climate Input Combinations in the Semi-arid Environment
No Thumbnail Available
Files
Date
2021-06-04
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
Ankara Üniversitesi
Abstract
The absolute prediction of reference evapotranspiration (ETo) is an important issue for global water balance. Present study demonstrated the performance of k-Nearest Neighbour (kNN) and Artificial Neural Network (ANN) models for prediction of daily ETo using four combinations of climatic data. The kNN and ANN models were studied four combinations of daily climate data during 1996-2015 in the Middle Anatolia region. The findings of ETo estimation with kNN and ANN models were classed with the FAO Penman Monteith equation. The outcomes of ETo values demonstrated that the kNN had higher performances than the ANN in all combinations. The statistical indicators of the kNN model showed ETo values with MSE, RMSE, MAE, NSE and R2 ranging from 0.541-0.031 mm day-1, 0.735-0.175 mm day-1, 0.547-0.124 mm day-1, 0.937-0.997 and 0.900-0.994 in the testing subset. Thus, the kNN can be used for the prediction of reference evapotranspiration with full and limited input meteorological data.
Description
Keywords
Evapotranspiration, Penman-Monteith, k-Nearest Neighbour