Evaluation of Eight Decomposition-Hybrid Models for Short-Term Daily Reference Evapotranspiration Prediction

Accurate reference evapotranspiration (ET<sub>o</sub>) prediction is important for water resource management, particularly in arid regions where water availability is highly variable. However, the nonlinear and non-stationary characteristics of ET<sub>o</sub> time series pose...

Full description

Saved in:
Bibliographic Details
Main Authors: Yunfei Chen, Zuyu Liu, Ting Long, Xiuhua Liu, Yaowei Gao, Sibo Wang
Format: Article
Language:English
Published: MDPI AG 2025-04-01
Series:Atmosphere
Subjects:
Online Access:https://www.mdpi.com/2073-4433/16/5/535
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850257661501636608
author Yunfei Chen
Zuyu Liu
Ting Long
Xiuhua Liu
Yaowei Gao
Sibo Wang
author_facet Yunfei Chen
Zuyu Liu
Ting Long
Xiuhua Liu
Yaowei Gao
Sibo Wang
author_sort Yunfei Chen
collection DOAJ
description Accurate reference evapotranspiration (ET<sub>o</sub>) prediction is important for water resource management, particularly in arid regions where water availability is highly variable. However, the nonlinear and non-stationary characteristics of ET<sub>o</sub> time series pose challenges for conventional prediction models. Given this, in this study we evaluate eight decomposition-hybrid models that integrate various decomposition techniques with a long short-term memory (LSTM) network to enhance short-term (5-day, 7-day, and 10-day) ET<sub>o</sub> forecasting. Using a 40-year dataset from a meteorological station, we employ the Penman-Monteith equation to calculate ET<sub>o</sub> and systematically compare model performance. Results show that VMD-LSTM and EWT-LSTM achieve the highest accuracy in the testing set (R<sup>2</sup> = 0.983 and 0.992, respectively) but exhibit reduced robustness in the prediction phase due to excessive high-frequency components. In contrast, EMD-LSTM and ESMD-LSTM demonstrate superior predictive stability, with no significant differences from actual values (<i>p</i> > 0.05). These findings underscore the importance of selecting appropriate decomposition methods to balance high-frequency information and predictive accuracy, offering insights for improving ET<sub>o</sub> forecasting in arid regions.
format Article
id doaj-art-6a325f9622ab4f8bbb4df9e79fa8147f
institution OA Journals
issn 2073-4433
language English
publishDate 2025-04-01
publisher MDPI AG
record_format Article
series Atmosphere
spelling doaj-art-6a325f9622ab4f8bbb4df9e79fa8147f2025-08-20T01:56:20ZengMDPI AGAtmosphere2073-44332025-04-0116553510.3390/atmos16050535Evaluation of Eight Decomposition-Hybrid Models for Short-Term Daily Reference Evapotranspiration PredictionYunfei Chen0Zuyu Liu1Ting Long2Xiuhua Liu3Yaowei Gao4Sibo Wang5School of Water and Environment, Chang’an University, Xi’an 710054, ChinaSchool of Water and Environment, Chang’an University, Xi’an 710054, ChinaSchool of Water and Environment, Chang’an University, Xi’an 710054, ChinaSchool of Water and Environment, Chang’an University, Xi’an 710054, ChinaSchool of Water and Environment, Chang’an University, Xi’an 710054, ChinaSchool of Water and Environment, Chang’an University, Xi’an 710054, ChinaAccurate reference evapotranspiration (ET<sub>o</sub>) prediction is important for water resource management, particularly in arid regions where water availability is highly variable. However, the nonlinear and non-stationary characteristics of ET<sub>o</sub> time series pose challenges for conventional prediction models. Given this, in this study we evaluate eight decomposition-hybrid models that integrate various decomposition techniques with a long short-term memory (LSTM) network to enhance short-term (5-day, 7-day, and 10-day) ET<sub>o</sub> forecasting. Using a 40-year dataset from a meteorological station, we employ the Penman-Monteith equation to calculate ET<sub>o</sub> and systematically compare model performance. Results show that VMD-LSTM and EWT-LSTM achieve the highest accuracy in the testing set (R<sup>2</sup> = 0.983 and 0.992, respectively) but exhibit reduced robustness in the prediction phase due to excessive high-frequency components. In contrast, EMD-LSTM and ESMD-LSTM demonstrate superior predictive stability, with no significant differences from actual values (<i>p</i> > 0.05). These findings underscore the importance of selecting appropriate decomposition methods to balance high-frequency information and predictive accuracy, offering insights for improving ET<sub>o</sub> forecasting in arid regions.https://www.mdpi.com/2073-4433/16/5/535reference crop evapotranspirationhybrid forecasting modeldecomposition algorithmdeep learningarid regions
spellingShingle Yunfei Chen
Zuyu Liu
Ting Long
Xiuhua Liu
Yaowei Gao
Sibo Wang
Evaluation of Eight Decomposition-Hybrid Models for Short-Term Daily Reference Evapotranspiration Prediction
Atmosphere
reference crop evapotranspiration
hybrid forecasting model
decomposition algorithm
deep learning
arid regions
title Evaluation of Eight Decomposition-Hybrid Models for Short-Term Daily Reference Evapotranspiration Prediction
title_full Evaluation of Eight Decomposition-Hybrid Models for Short-Term Daily Reference Evapotranspiration Prediction
title_fullStr Evaluation of Eight Decomposition-Hybrid Models for Short-Term Daily Reference Evapotranspiration Prediction
title_full_unstemmed Evaluation of Eight Decomposition-Hybrid Models for Short-Term Daily Reference Evapotranspiration Prediction
title_short Evaluation of Eight Decomposition-Hybrid Models for Short-Term Daily Reference Evapotranspiration Prediction
title_sort evaluation of eight decomposition hybrid models for short term daily reference evapotranspiration prediction
topic reference crop evapotranspiration
hybrid forecasting model
decomposition algorithm
deep learning
arid regions
url https://www.mdpi.com/2073-4433/16/5/535
work_keys_str_mv AT yunfeichen evaluationofeightdecompositionhybridmodelsforshorttermdailyreferenceevapotranspirationprediction
AT zuyuliu evaluationofeightdecompositionhybridmodelsforshorttermdailyreferenceevapotranspirationprediction
AT tinglong evaluationofeightdecompositionhybridmodelsforshorttermdailyreferenceevapotranspirationprediction
AT xiuhualiu evaluationofeightdecompositionhybridmodelsforshorttermdailyreferenceevapotranspirationprediction
AT yaoweigao evaluationofeightdecompositionhybridmodelsforshorttermdailyreferenceevapotranspirationprediction
AT sibowang evaluationofeightdecompositionhybridmodelsforshorttermdailyreferenceevapotranspirationprediction