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

Chen, Yunfei; Liu, Zuyu; Long, Ting; Liu, Xiuhua; Gao, Yaowei; Wang, Sibo

doi:10.3390/atmos16050535

This is an early access version, the complete PDF, HTML, and XML versions will be available soon.

Open AccessArticle

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

by

Yunfei Chen

^1,2

,

Zuyu Liu

^1,2,3,

Ting Long

^1,2,3,

Xiuhua Liu

^1,2,3,*

,

Yaowei Gao

^1,2,3 and

Sibo Wang

^1,2,3

¹

School of Water and Environment, Chang’an University, Xi’an 710054, China

²

Key Laboratory of Subsurface Hydrology and Ecological Effect in Arid Region of Ministry of Education, Chang’an University, Xi’an 710054, China

³

Key Laboratory of Eco-hydrology and Water Security in Arid and Semi-arid Regions of Ministry of Water resources, Chang’an University, Xi’an 710054, China

^*

Author to whom correspondence should be addressed.

Atmosphere 2025, 16(5), 535; https://doi.org/10.3390/atmos16050535

Submission received: 18 March 2025 / Revised: 27 April 2025 / Accepted: 28 April 2025 / Published: 30 April 2025

(This article belongs to the Special Issue Challenges in Weather and Climate Modelling: Model Development, Validation, and Perspectives)

Download Versions Notes

Abstract

Accurate reference evapotranspiration (ET_o) 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_o 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_o forecasting. Using a 40-year dataset from a meteorological station, we employ the Penman-Monteith equation to calculate ET_o and systematically compare model performance. Results show that VMD-LSTM and EWT-LSTM achieve the highest accuracy in the testing set (R² = 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 (p > 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_o forecasting in arid regions.

Keywords: reference crop evapotranspiration; hybrid forecasting model; decomposition algorithm; deep learning; arid regions

Share and Cite

MDPI and ACS Style

Chen, Y.; Liu, Z.; Long, T.; Liu, X.; Gao, Y.; Wang, S. Evaluation of Eight Decomposition-Hybrid Models for Short-Term Daily Reference Evapotranspiration Prediction. Atmosphere 2025, 16, 535. https://doi.org/10.3390/atmos16050535

AMA Style

Chen Y, Liu Z, Long T, Liu X, Gao Y, Wang S. Evaluation of Eight Decomposition-Hybrid Models for Short-Term Daily Reference Evapotranspiration Prediction. Atmosphere. 2025; 16(5):535. https://doi.org/10.3390/atmos16050535

Chicago/Turabian Style

Chen, Yunfei, Zuyu Liu, Ting Long, Xiuhua Liu, Yaowei Gao, and Sibo Wang. 2025. "Evaluation of Eight Decomposition-Hybrid Models for Short-Term Daily Reference Evapotranspiration Prediction" Atmosphere 16, no. 5: 535. https://doi.org/10.3390/atmos16050535

APA Style

Chen, Y., Liu, Z., Long, T., Liu, X., Gao, Y., & Wang, S. (2025). Evaluation of Eight Decomposition-Hybrid Models for Short-Term Daily Reference Evapotranspiration Prediction. Atmosphere, 16(5), 535. https://doi.org/10.3390/atmos16050535

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Menu

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

Abstract

Share and Cite

Article Metrics

Article Access Statistics

Further Information

Guidelines

MDPI Initiatives

Follow MDPI