Efficient irrigation management of urban landscapes is critical in arid/semi-arid environments and depends on the reliable estimation of reference evapotranspiration(ETo).However,the available measured climatic data i...Efficient irrigation management of urban landscapes is critical in arid/semi-arid environments and depends on the reliable estimation of reference evapotranspiration(ETo).However,the available measured climatic data in urban areas are typically insufficient to use the standard Penman-Monteith for ETo estimation.Therefore,smart landscape irrigation controllers often use temperature-based ETo models for autonomous irrigation scheduling.This study focuses on developing deep learning temperature-based ETo models and comparing their performance with widely used empirical temperature-based models,including FAO Blaney&Criddle(BC),and Hargreaves&Samani(HS).We also developed a simple free and easy-to-access tool called DeepET for ETo estimation using the best-performing deep learning models developed in this study.Four artificial neural network(ANN)models were developed using raw weather data as inputs and the reconstructed signal obtained from the wavelet transform as inputs.In addition,long short-term memory(LSTM)recurrent neural network(NN)and one-dimensional convolution neural network(CNN)models were developed.A total of 101 active California Irrigation Management Information System(CIMIS)weather stations were selected for this study,with>725,000 data points expanding from 1985 to 2019.The performance of the models was evaluated against the standard CIMIS ETo.When evaluated at the independent sites,the temperature-based DL(Deep Learning)models showed 15–20%lower mean absolute error values than the calibrated HS model.No improvement in the performance of the ANN models was observed using reconstructed signals obtained from the wavelet transform.Our study suggests that DL models offer a promising alternative for more accurate estimations of ETo in urban areas using only temperature as input.The DeepET can be accessed from the Haghverdi Water Management Group website:http://www.ucrwater.com/software-and-tools.html.展开更多
文摘Efficient irrigation management of urban landscapes is critical in arid/semi-arid environments and depends on the reliable estimation of reference evapotranspiration(ETo).However,the available measured climatic data in urban areas are typically insufficient to use the standard Penman-Monteith for ETo estimation.Therefore,smart landscape irrigation controllers often use temperature-based ETo models for autonomous irrigation scheduling.This study focuses on developing deep learning temperature-based ETo models and comparing their performance with widely used empirical temperature-based models,including FAO Blaney&Criddle(BC),and Hargreaves&Samani(HS).We also developed a simple free and easy-to-access tool called DeepET for ETo estimation using the best-performing deep learning models developed in this study.Four artificial neural network(ANN)models were developed using raw weather data as inputs and the reconstructed signal obtained from the wavelet transform as inputs.In addition,long short-term memory(LSTM)recurrent neural network(NN)and one-dimensional convolution neural network(CNN)models were developed.A total of 101 active California Irrigation Management Information System(CIMIS)weather stations were selected for this study,with>725,000 data points expanding from 1985 to 2019.The performance of the models was evaluated against the standard CIMIS ETo.When evaluated at the independent sites,the temperature-based DL(Deep Learning)models showed 15–20%lower mean absolute error values than the calibrated HS model.No improvement in the performance of the ANN models was observed using reconstructed signals obtained from the wavelet transform.Our study suggests that DL models offer a promising alternative for more accurate estimations of ETo in urban areas using only temperature as input.The DeepET can be accessed from the Haghverdi Water Management Group website:http://www.ucrwater.com/software-and-tools.html.
