Bayesian-optimized machine learning boosts actual evapotranspiration prediction in water-stressed agricultural regions of China

The accurate estimation of actual evapotranspiration (AET) is crucial for sustainable water resource management, especially in water-scarce and agriculturally intensive regions like Beijing and Tianjin, China. Traditional methods for AET estimation, whether empirical or physically based, often face...

Full description

Saved in:
Bibliographic Details
Published in:Scientific reports Vol. 15; no. 1; pp. 37548 - 18
Main Authors: Elbeltagi, Ahmed, Srivastava, Aman, Cao, Xinchun, Gautam, Vinay Kumar, Zerouali, Bilel, Aslam, Muhammad Rizwan, Salem, Ali, Emami, Hojjat, Elsadek, Elsayed Ahmed
Format: Journal Article
Language:English
Published: London Nature Publishing Group UK 28.10.2025
Nature Publishing Group
Nature Portfolio
Subjects:
704/106/242
704/106/694
704/172/4081
704/242
Agricultural hydrology
Agricultural water management
Artificial intelligence
Bayesian analysis
Bayesian optimization
Climate change
Climate data modeling
Data-driven evapotranspiration
Datasets
Drought
Environmental monitoring
Evapotranspiration
Humanities and Social Sciences
Irrigation scheduling
Learning algorithms
Machine learning
Mathematical models
multidisciplinary
Neural networks
Resource management
Science
Science (multidisciplinary)
Solar radiation
Vapor pressure
Water management
Water resources management
Wind speed
Beijing China
China
Data-driven evapotranspiration
Agricultural hydrology
Irrigation scheduling
Bayesian optimization
Climate data modeling
Agricultural water management
ISSN:2045-2322, 2045-2322
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The accurate estimation of actual evapotranspiration (AET) is crucial for sustainable water resource management, especially in water-scarce and agriculturally intensive regions like Beijing and Tianjin, China. Traditional methods for AET estimation, whether empirical or physically based, often face limitations due to high data requirements, limited scalability, and sensitivity to input uncertainties. This creates a critical research gap in providing reliable AET predictions under data-limited conditions. To address this, we evaluated the efficacy of integrating four advanced machine learning (ML) models: Support Vector Machine (SVM), Gaussian Process Regression (GPR), Ensemble Tree, and Neural Network, with Bayesian hyperparameter optimization for AET modeling using the high-resolution TerraClimate dataset spanning 1958–2022. Key meteorological variables, including maximum and minimum temperature (T max and T min ), solar radiation (SR), wind speed (WS), vapor pressure deficit (VPD), and precipitation (PPT), were selected through rigorous correlation and multicollinearity analyses. Model performance was assessed using the coefficient of determination (R 2 ), mean squared error (MSE), root mean squared error (RMSE), and mean absolute error (MAE) on a 75:25 train-test split. Results demonstrate that the optimizable GPR model achieved the highest predictive accuracy (RMSE = 5.54, R 2  = 0.98 on test data), outperforming other ML approaches and traditional empirical models. PPT, T min , and T max emerged as the most influential predictors for AET. Our findings reveal that ML models, particularly when optimized via Bayesian techniques, yield a robust, scalable, and data-efficient alternative for AET estimation in regions with limited meteorological records. This study establishes a new benchmark for AET modeling, with significant implications for irrigation scheduling, drought monitoring, and integrated water management in the North China Plain and comparable agro-ecological regions.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:2045-2322
2045-2322
DOI:10.1038/s41598-025-22130-y