Premium
Artificial neural network models for estimating regional reference evapotranspiration based on climate factors
Author(s) -
Dai Xiaoqin,
Shi Haibin,
Li Yunsheng,
Ouyang Zhu,
Huo Zailin
Publication year - 2008
Publication title -
hydrological processes
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.222
H-Index - 161
eISSN - 1099-1085
pISSN - 0885-6087
DOI - 10.1002/hyp.7153
Subject(s) - evapotranspiration , environmental science , multilinear map , sunshine duration , wind speed , arid , mean squared error , artificial neural network , relative humidity , meteorology , water cycle , hydrology (agriculture) , climatology , statistics , mathematics , geography , computer science , geology , ecology , paleontology , geotechnical engineering , machine learning , pure mathematics , biology
Abstract Evapotranspiration (ET) is one of the basic components of the hydrologic cycle and is essential for estimating irrigation water requirements. In this study, an artificial neural network (ANN) model for reference evapotranspiration (ET 0 ) calculation was investigated. ANNs were trained and tested for arid (west), semi‐arid (middle) and sub‐humid (east) areas of the Inner Mongolia district of China. Three or four climate factors, i.e. air temperature ( T ), relative humidity ( RH ), wind speed ( U ) and duration of sunshine ( N ) from 135 meteorological stations distributed throughout the study area, were used as the inputs of the ANNs. A comparison was conducted between the estimates provided by the ANNs and by multilinear regression (MLR). The results showed that ANNs using the climatic data successfully estimated ET 0 and the ANNs simulated ET 0 better than the MLRs. The ANNs with four inputs were more accurate than those with three inputs. The errors of the ANNs with four inputs were lower (with RMSE of 0·130 mm d −1 , RE of 2·7% and R 2 of 0·986) in the semi‐arid area than in the other two areas, but the errors of the ANNs with three inputs were lower in the sub‐humid area (with RMSE of 0·21 mm d −1 , RE of 5·2% and R 2 of 0·961. For the different seasons, the results indicated that the highest errors occurred in September and the lowest in April for the ANNs with four inputs. Similarly, the errors were higher in September for the ANNs with three inputs. Copyright © 2008 John Wiley & Sons, Ltd.