IDEAS home Printed from https://ideas.repec.org/a/eee/agiwat/v324y2026ics0378377426000247.html

Interpretable machine learning workflow for estimating reference crop evapotranspiration in China's five major dry-wet regions using limited meteorological data

Author

Listed:
  • Guan, Ziyu
  • Qin, Changhai
  • Zhao, Yong
  • Qu, Junlin
  • Liu, Rong
  • Liu, Yuan
  • Che, Wenxin
  • Wang, Tao

Abstract

Accurate estimation of reference crop evapotranspiration (ET0) is crucial for improving water use efficiency and the design and operation of agricultural water management systems. Machine learning (ML) can accurately estimate ET0 across different climatic zones in China when meteorological data are limited, but its “black box” nature restricts interpretability. This study developed an interpretable machine learning workflow to enhance ET0 prediction transparency. It utilized four meta-heuristic algorithms and four machine learning algorithms based on meteorological data observed at 2382 stations across five climatic zones in China from 1960 to 2022. Model performance was evaluated using mean absolute error (MAE), root mean square error (RMSE), Nash-Sutcliffe efficiency coefficient (NSE), coefficient of determination (R2), and global performance index (GPI). Results indicate that the XGBoost model optimized by the Grey Wolf Optimization (GWO) algorithm (GWO-XGB) achieved the highest fitting accuracy. Its Mean Absolute Error (MAE), Root Mean Square Error (RMSE), Nash-Sutcliffe efficiency coefficient (NSE), coefficient of determination (R2), and global prediction index (GPI) were 0.087, 0.116, 0.993, 0.993, and 1.783, respectively. Cross-validation across basins revealed that GWO-XGB maintained an R2 above 0.96 on the independent validation dataset, indicating robust stability and generalization of the interpretable machine learning framework in ET0 prediction. SHAP accurately captured underlying hydrological and climatic processes, identifying solar radiation and extreme temperatures as the primary predictors of ET0, while humidity and wind speed exerted lesser influences. This study offers a promising approach for precise ET0 estimation in data-scarce regions, thereby supporting scientific water resource management and achieving water conservation and efficiency goals. The open-source prediction application is available at https://github.com/guangian.

Suggested Citation

  • Guan, Ziyu & Qin, Changhai & Zhao, Yong & Qu, Junlin & Liu, Rong & Liu, Yuan & Che, Wenxin & Wang, Tao, 2026. "Interpretable machine learning workflow for estimating reference crop evapotranspiration in China's five major dry-wet regions using limited meteorological data," Agricultural Water Management, Elsevier, vol. 324(C).
    • Handle: RePEc:eee:agiwat:v:324:y:2026:i:c:s0378377426000247
    DOI: 10.1016/j.agwat.2026.110143
    as

    Download full text from publisher

    File URL: http://www.sciencedirect.com/science/article/pii/S0378377426000247
    Download Restriction: Full text for ScienceDirect subscribers only
    File URL: https://libkey.io/10.1016/j.agwat.2026.110143?utm_source=ideas
    LibKey link: if access is restricted and if your library uses this service, LibKey will redirect you to where you can use your library subscription to access this item
    ---><---

    As the access to this document is restricted, you may want to

    for a different version of it.

    References listed on IDEAS

    as
    1. Matin Ahooghalandari & Mehdi Khiadani & Mina Esmi Jahromi, 2016. "Developing Equations for Estimating Reference Evapotranspiration in Australia," Water Resources Management: An International Journal, Published for the European Water Resources Association (EWRA), Springer;European Water Resources Association (EWRA), vol. 30(11), pages 3815-3828, September.
    2. Bwambale, Erion & Abagale, Felix K. & Anornu, Geophrey K., 2022. "Smart irrigation monitoring and control strategies for improving water use efficiency in precision agriculture: A review," Agricultural Water Management, Elsevier, vol. 260(C).
    3. Yin, Juan & Deng, Zhen & Ines, Amor V.M. & Wu, Junbin & Rasu, Eeswaran, 2020. "Forecast of short-term daily reference evapotranspiration under limited meteorological variables using a hybrid bi-directional long short-term memory model (Bi-LSTM)," Agricultural Water Management, Elsevier, vol. 242(C).
    4. Zhang, Lei & Zhao, Xin & Zhu, Ge & He, Jun & Chen, Jian & Chen, Zhicheng & Traore, Seydou & Liu, Junguo & Singh, Vijay P., 2023. "Short-term daily reference evapotranspiration forecasting using temperature-based deep learning models in different climate zones in China," Agricultural Water Management, Elsevier, vol. 289(C).
    5. Di Nunno, Fabio & Granata, Francesco, 2023. "Future trends of reference evapotranspiration in Sicily based on CORDEX data and Machine Learning algorithms," Agricultural Water Management, Elsevier, vol. 280(C).
    6. Su, Qiong & Singh, Vijay P. & Karthikeyan, Raghupathy, 2022. "Improved reference evapotranspiration methods for regional irrigation water demand estimation," Agricultural Water Management, Elsevier, vol. 274(C).
    7. Valipour, Mohammad & Khoshkam, Helaleh & Bateni, Sayed M. & Jun, Changhyun & Band, Shahab S., 2023. "Hybrid machine learning and deep learning models for multi-step-ahead daily reference evapotranspiration forecasting in different climate regions across the contiguous United States," Agricultural Water Management, Elsevier, vol. 283(C).
    8. Zhao, Xiaohua & Yang, Haiyi & Yao, Ying & Qi, Hang & Guo, Miao & Su, Yuelong, 2022. "Factors affecting traffic risks on bridge sections of freeways based on partial dependence plots," Physica A: Statistical Mechanics and its Applications, Elsevier, vol. 598(C).
    9. Feng, Yu & Cui, Ningbo & Gong, Daozhi & Zhang, Qingwen & Zhao, Lu, 2017. "Evaluation of random forests and generalized regression neural networks for daily reference evapotranspiration modelling," Agricultural Water Management, Elsevier, vol. 193(C), pages 163-173.
    10. Fan, Junliang & Wu, Lifeng & Zhang, Fucang & Cai, Huanjie & Zeng, Wenzhi & Wang, Xiukang & Zou, Haiyang, 2019. "Empirical and machine learning models for predicting daily global solar radiation from sunshine duration: A review and case study in China," Renewable and Sustainable Energy Reviews, Elsevier, vol. 100(C), pages 186-212.
    11. Yang, Yong & Chen, Rensheng & Han, Chuntan & Liu, Zhangwen, 2021. "Evaluation of 18 models for calculating potential evapotranspiration in different climatic zones of China," Agricultural Water Management, Elsevier, vol. 244(C).
    12. Dong, Juan & Xing, Liwen & Cui, Ningbo & Guo, Li & Liang, Chuan & Zhao, Lu & Wang, Zhihui & Gong, Daozhi, 2024. "Estimating reference crop evapotranspiration using optimized empirical methods with a novel improved Grey Wolf Algorithm in four climatic regions of China," Agricultural Water Management, Elsevier, vol. 291(C).
    13. Pereira, L.S. & Paredes, P. & Jovanovic, N., 2020. "Soil water balance models for determining crop water and irrigation requirements and irrigation scheduling focusing on the FAO56 method and the dual Kc approach," Agricultural Water Management, Elsevier, vol. 241(C).
    14. Bernhard Schauberger & Sotirios Archontoulis & Almut Arneth & Juraj Balkovic & Philippe Ciais & Delphine Deryng & Joshua Elliott & Christian Folberth & Nikolay Khabarov & Christoph Müller & Thomas A. , 2017. "Consistent negative response of US crops to high temperatures in observations and crop models," Nature Communications, Nature, vol. 8(1), pages 1-9, April.
    15. Zhang, Zixiong & Gong, Yicheng & Wang, Zhongjing, 2018. "Accessible remote sensing data based reference evapotranspiration estimation modelling," Agricultural Water Management, Elsevier, vol. 210(C), pages 59-69.
    16. Singh Rawat, Kishan & Kumar Singh, Sudhir & Bala, Anju & Szabó, Szilárd, 2019. "Estimation of crop evapotranspiration through spatial distributed crop coefficient in a semi-arid environment," Agricultural Water Management, Elsevier, vol. 213(C), pages 922-933.
    Full references (including those not matched with items on IDEAS)

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Dong, Juan & Xing, Liwen & Cui, Ningbo & Guo, Li & Liang, Chuan & Zhao, Lu & Wang, Zhihui & Gong, Daozhi, 2024. "Estimating reference crop evapotranspiration using optimized empirical methods with a novel improved Grey Wolf Algorithm in four climatic regions of China," Agricultural Water Management, Elsevier, vol. 291(C).
    2. Dong, Juan & Xing, Liwen & Cui, Ningbo & Zhao, Lu & Guo, Li & Wang, Zhihui & Du, Taisheng & Tan, Mingdong & Gong, Daozhi, 2024. "Estimating reference crop evapotranspiration using improved convolutional bidirectional long short-term memory network by multi-head attention mechanism in the four climatic zones of China," Agricultural Water Management, Elsevier, vol. 292(C).
    3. Zhang, Jia & Ding, Yimin & Zhu, Lei & Wan, Yukuai & Chai, Mingtang & Ding, Pengpeng, 2025. "Estimating and forecasting daily reference crop evapotranspiration in China with temperature-driven deep learning models," Agricultural Water Management, Elsevier, vol. 307(C).
    4. França, Ana Carolina Ferreira & Coelho, Rubens Duarte & da Silva Gundim, Alice & de Oliveira Costa, Jéfferson & Quiloango-Chimarro, Carlos Alberto, 2024. "Effects of different irrigation scheduling methods on physiology, yield, and irrigation water productivity of soybean varieties," Agricultural Water Management, Elsevier, vol. 293(C).
    5. Feng, Yu & Hao, Weiping & Li, Haoru & Cui, Ningbo & Gong, Daozhi & Gao, Lili, 2020. "Machine learning models to quantify and map daily global solar radiation and photovoltaic power," Renewable and Sustainable Energy Reviews, Elsevier, vol. 118(C).
    6. Zhou, Hanmi & Su, Yumin & Ma, Linshuang & Li, Jichen & Lu, Sibo & Chen, Cheng & Xiang, Youzhen & Li, Runze & Peng, Zhe & Huang, Ru, 2026. "Optimizing light gradient boosting machine with the slime mould algorithm for reference evapotranspiration estimation," Agricultural Water Management, Elsevier, vol. 324(C).
    7. Wu, Lifeng & Peng, Youwen & Fan, Junliang & Wang, Yicheng & Huang, Guomin, 2021. "A novel kernel extreme learning machine model coupled with K-means clustering and firefly algorithm for estimating monthly reference evapotranspiration in parallel computation," Agricultural Water Management, Elsevier, vol. 245(C).
    8. Bellido-Jiménez, Juan A. & Estévez, Javier & García-Marín, Amanda P., 2022. "A regional machine learning method to outperform temperature-based reference evapotranspiration estimations in Southern Spain," Agricultural Water Management, Elsevier, vol. 274(C).
    9. Yan, Shicheng & Wu, Lifeng & Fan, Junliang & Zhang, Fucang & Zou, Yufeng & Wu, You, 2021. "A novel hybrid WOA-XGB model for estimating daily reference evapotranspiration using local and external meteorological data: Applications in arid and humid regions of China," Agricultural Water Management, Elsevier, vol. 244(C).
    10. Zehai Gao & Dongzhe Yang & Baojun Li & Zijun Gao & Chengcheng Li, 2025. "Reference Crop Evapotranspiration Prediction Based on Gated Recurrent Unit with Quantum Inspired Multi-head Self-attention Mechanism," Water Resources Management: An International Journal, Published for the European Water Resources Association (EWRA), Springer;European Water Resources Association (EWRA), vol. 39(3), pages 1481-1501, February.
    11. Arnesh Telukdarie & Noluthando Gamede & Inderasan Munien & Andre Vermeulen & Uche Onkonkwo, 2023. "The Potential Future Of Agriculture For Small Farms: Supervised Machine-Learning Smart Irrigation Concept For Vegetables," Big Data In Agriculture (BDA), Zibeline International Publishing, vol. 5(2), pages 57-63, July.
    12. Huang, Guomin & Dong, Jianhua & Wu, Lifeng & Luo, Jingwei & Qiu, Rangjian & Cui, Yaokui & Wang, Yicheng, 2025. "A new regional reference evapotranspiration model based on quantile approximation of meteorological variables," Agricultural Water Management, Elsevier, vol. 308(C).
    13. Silva, Simão P. & Valín, M. Isabel & Mendes, Susana & Araujo-Paredes, Claúdio & Cancela, Javier J., 2024. "Water productivity in Vitis vinifera L. cv. Alvarinho using dual crop coefficient approach," Agricultural Water Management, Elsevier, vol. 303(C).
    14. Yuanzhen Zhang & Guofang Wang & Lingzhi Li & Mingjing Huang, 2025. "A Monitoring Method for Agricultural Soil Moisture Using Wireless Sensors and the Biswas Model," Agriculture, MDPI, vol. 15(3), pages 1-18, February.
    15. Kim, Ho-Jun & Chandrasekara, Sewwandhi & Kwon, Hyun-Han & Lima, Carlos & Kim, Tae-woong, 2023. "A novel multi-scale parameter estimation approach to the Hargreaves-Samani equation for estimation of Penman-Monteith reference evapotranspiration," Agricultural Water Management, Elsevier, vol. 275(C).
    16. Abhirup Paria & Arindam Giri & Subrata Dutta & Sarmistha Neogy, 2025. "Smart Irrigation for Coriander Plant: Saving Water with AI and IoT," Water Resources Management: An International Journal, Published for the European Water Resources Association (EWRA), Springer;European Water Resources Association (EWRA), vol. 39(7), pages 3379-3395, May.
    17. Zhang, Lei & Zhao, Xin & Zhu, Ge & He, Jun & Chen, Jian & Chen, Zhicheng & Traore, Seydou & Liu, Junguo & Singh, Vijay P., 2023. "Short-term daily reference evapotranspiration forecasting using temperature-based deep learning models in different climate zones in China," Agricultural Water Management, Elsevier, vol. 289(C).
    18. Bounajra, Afaf & Guemmat, Kamal El & Mansouri, Khalifa & Akef, Fatiha, 2024. "Towards efficient irrigation management at field scale using new technologies: A systematic literature review," Agricultural Water Management, Elsevier, vol. 295(C).
    19. Fan, Junliang & Ma, Xin & Wu, Lifeng & Zhang, Fucang & Yu, Xiang & Zeng, Wenzhi, 2019. "Light Gradient Boosting Machine: An efficient soft computing model for estimating daily reference evapotranspiration with local and external meteorological data," Agricultural Water Management, Elsevier, vol. 225(C).
    20. Valipour, Mohammad & Khoshkam, Helaleh & Bateni, Sayed M. & Jun, Changhyun & Band, Shahab S., 2023. "Hybrid machine learning and deep learning models for multi-step-ahead daily reference evapotranspiration forecasting in different climate regions across the contiguous United States," Agricultural Water Management, Elsevier, vol. 283(C).

    More about this item

    Keywords

    ;
    ;
    ;
    ;
    ;

    Statistics

    Access and download statistics

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:eee:agiwat:v:324:y:2026:i:c:s0378377426000247. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: Catherine Liu (email available below). General contact details of provider: http://www.elsevier.com/locate/agwat .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.