Daily evapotranspiration estimation using limited meteorological data across diverse geographic regions of China
Abstract
Evapotranspiration (ET) is a key component of the water cycle, and accurate estimation of reference crop evapotranspiration (ETo) is essential for irrigation management. To build a precise, lightweight ETo estimation model, this study takes key meteorological factors as inputs and applies machine learning models and hybrid models Crested Porcupine Optimizer kernel extreme learning machine (CPO-KELM), the Dung Beetle Optimizer Algorithm KELM (DBO-KELM), and Particle Swarm Optimization KELM (PSO-KELM) to estimate ETo at 38 meteorological stations across China’s seven major geographical regions. The results indicate that maximum temperature (Tmax), average temperature (Tave), and relative humidity (RH) are the primary factors affecting ETo and were therefore used as model inputs. The standalone kernel extreme learning machine (KELM) model shows acceptable ETo estimation performance, with R2, RMSE, MAE, and NSE ranging from 0.802-0.885, 0.512-0.911, 0.464-0.970, and 0.802-0.885, respectively. Hybrid models outperform the standalone KELM, among which CPO-KELM is the most accurate: its R2, RMSE, MAE, and NSE range from 0.881-0.942, 0.413-1.147, 0.284-0.763, and 0.881-0.942. At the regional scale, the CPO-KELM model exhibits its best performance in the Northeast and North China regions, with R2, RMSE, MAE, and NSE ranging from 0.923-0.936, 0.413-0.511, 0.284-0.358, and 0.923-0.936, respectively. In contrast, its weakest performance is observed in parts of South China and Northwest China, with R2, RMSE, MAE, and NSE ranging from 0.881-0.905, 0.675-1.147, 0.506-0.763, and 0.881-0.905. Compared to standalone KELM, CPO-KELM improves accuracy significantly: R2 and NSE rise by 6.4%-9.9%, while MAE drops by 21.3%-38.8%. Thus, the hybrid CPO-KELM model effectively enhances ETo estimation accuracy across China’s regions. Therefore, the proposed CPO-KELM hybrid model provides a high-accuracy and lightweight alternative for ETo estimation in data-scarce regions, and offers reliable technical support for intelligent water resources management and irrigation optimization across diverse climatic zones in China.
Keywords: ETo, seven major geographical regions, machine learning algorithm, lightweight model
DOI: 10.25165/j.ijabe.20261901.10161
Citation: Chen W X, Wang F, Yu W X C, Shi Y, Zhao X B. Daily evapotranspiration estimation using limited meteorological data across diverse geographic regions of China. Int J Agric & Biol Eng, 2026; 19(1): 241–250.
References
[1] Wu Z J, Cui N B, Zhu B, Zhao L, Wang X K, Hu X T, et al. Improved hargreaves model based on multiple intelligent optimization algorithms to estimate reference crop evapotranspiration in humid areas of southwest China. Atmosphere, 2021; 12（1）: 15.
[2] Xu Y, Xu Y P, Wang Y F, Wu L, Li G, Song S. Spatial and temporal trends of reference crop evapotranspiration and its influential variables in Yangtze River Delta, eastern China. Theoretical and Applied Climatology, 2017; 130: 945–958.
[3] Cunha A C, Gabriel Filho L R A, Tanaka A A, Goes B C, Putti F F. Influence of the estimated global solar radiation on the reference evapotranspiration obtained through the Penman-Monteith FAO 56 method. Agricultural Water Management, 2021; 243: 106491.
[4] He H, Wu Z, Li D D, Zhang T C, Pan F F, Yuan H W, et al. Characteristics of winter wheat evapotranspiration in eastern china and comparative evaluation of applicability of different reference evapotranspiration models. Journal of Soil Science and Plant Nutrition, 2022; 22: 2078–2091.
[5] Zhao L, Xing L W, Wang Y H, Cui N B, Zhou H M, Shi Y, et al. Prediction model for reference crop evapotranspiration based on the back-propagation algorithm with limited factors. Water Resources Management, 2023; 37: 1207–1222.
[6] Yong S L S, Ng J L, Huang Y F, Ang C K. Estimation of reference crop evapotranspiration with three different machine learning models and limited meteorological variables. Agronomy-Basel, 2023; 13（4）: 1048.
[7] Tejada A T, Ella V B, Lampayan R M, Reano C E. Modeling reference crop evapotranspiration using support vector machine （SVM） and extreme learning machine （ELM） in region IV-A, Philippines. Water, 2022; 14（5）: 754.
[8] Bellido-Jimenez J A, Estevez J, Vanschoren J, Garcia-Marin A P. AgroML: an open-source repository to forecast reference evapotranspiration in different geo-climatic conditions using machine learning and transformer-based models. Agronomy-Basel, 2022; 12: 656.
[9] Gong D Z, Hao W P, Gao L L, Feng Y, Cui N B. Extreme learning machine for reference crop evapotranspiration estimation: Model optimization and spatiotemporal assessment across different climates in China. Computers and Electronics in Agriculture, 2021; 187: 106294.
[10] Zhao X B, Li Y Z, Zhao Z H, Xing X G, Feng G H, Bai J Y, et al. Prediction model for daily reference crop evapotranspiration based on hybrid algorithm in semi-arid regions of China. Atmosphere, 2022; 13（6）: 922.
[11] Sebastian J, Raj S K, Shihabudheen K V. Adaptive control of a nonaffine nonlinear system using self-organising kernel extreme learning machine. Isa Transactions, 2024; 146: 567–581.
[12] Tian S C, Ma L, Li H X, Tian F Y, Mao J R. Research on a coal seam gas content prediction method based on an improved extreme learning machine. Applied Sciences-Basel, 2023; 13（15）: 8753.
[13] Zhao L, Zhao X B, Li Y Z, Shi Y, Zhou H M, Li X Z, et al. Applicability of hybrid bionic optimization models with kernel-based extreme learning machine algorithm for predicting daily reference evapotranspiration: a case study in arid and semiarid regions, China. Environmental Science and Pollution Research, 2023; 30: 22396–22412.
[14] Fan Y L, Ma Z, Tang W W, Liang J, Xu P F. Using crested porcupine optimizer algorithm and CNN-LSTM-attention model combined with deep learning methods to enhance short-term power forecasting in PV generation. Energies, 2024; 17（14）: 3435.
[15] Zhang Z Q, Zhang L L, Liu D, Sun N, Li M, Faiz M A, et al. Measurement and analysis of regional water-energy-food nexus resilience with an improved hybrid kernel extreme learning machine model based on a dung beetle optimization algorithm. Agricultural Systems, 2024; 218: 103966.
[16] Jia Y, Wang H, Li P C, Su Y J, Wang F C, Huo S Y. Particle swarm optimization algorithm with Gaussian exponential model to predict daily and monthly global solar radiation in Northeast China. Environmental Science and Pollution Research, 2023; 30: 12769–12784.
[17] Fei S W, Liu Y Z. Fault diagnosis method of bearing utilizing GLCM and MBASA-based KELM. Scientific Reports, 2022; 12: 17368.
[18] Ma J, Liang S T, Du Z Y, Chen M. Compound fault diagnosis of rolling bearing based on ALIF-KELM. Mathematical Problems in Engineering, 2021; 2021: 2636302.
[19] Abdel-Basset M, Mohamed R, Abouhawwash M. Crested porcupine optimizer: A new nature-inspired metaheuristic. Knowledge-Based Systems, 2024; 284: 111257.
[20] Liu H J, Zhou R, Zhong X Y, Yao Y, Shan W F, Yuan J, et al. Multi-strategy enhanced crested porcupine optimizer: CAPCPO. Mathematics, 2024; 12（19）: 3080.
[21] Xue J K, Shen B. Dung beetle optimizer: A new meta-heuristic algorithm for global optimization. The Journal of Supercomputing, 2022; 79: 7305–7336.
[22] Kennedy J, Eberhart R. Particle swarm optimization. In Proceedings of the Proceedings of ICNN’95-International conference on neural networks, Perth, WA, Australia: IEEE, 1995; pp.1942–1948. doi: 10.1109/ICNN.1995.488968
[23] Singh A, Kukal M S, Shapiro C A, Snow D D, Irmak S, Iqbal J. Growth phase-specific evaporative demand and nighttime temperatures determine Maize （Zea Mays L.） yield deviations as revealed from a long-term field experiment. Agricultural and Forest Meteorology, 2021; 308–309: 108543. doi: 10.1016/j.agrformet.2021.108543.
[24] Despotovic M, Nedic V, Despotovic D, Cvetanovic S. Review and statistical analysis of different global solar radiation sunshine models. Renewable & Sustainable Energy Reviews, 2015; 52: 1869–1880.
[25] Emeka N, Ikenna O, Okechukwu M, Chinenye A, Emmanuel E. Sensitivity of FAO Penman-Monteith reference evapotranspiration （ETo） to climatic variables under different climate types in Nigeria. Journal of Water and Climate Change, 2021; 12（3）: 858–878.
[26] Heramb P, Ramana Rao K V, Subeesh A, Srivastava A. Predictive modelling of reference evapotranspiration using machine learning models coupled with grey wolf optimizer. Water, 2023; 15（5）: 856.
[27] Wu X J, Wu X M, Huang H C, Zhang F G, Wen Y X. Characterization of pepper ripeness in the field using hyperspectral imaging （HSI） with back propagation （BP） neural network and kernel based extreme learning machine （KELM） models. Analytical Letters, 2024; 57（3）: 409–424.
[28] Suo L M, Liu H L, Ni J, Wang Z W, Zhao R. Sunflower origin identification based on multi-source information fusion technique of kernel extreme learning machine. Agronomy-Basel, 2024; 14（6）: 1320.
[29] Peng S Q, Sun Q Z, Fan L, Zhou J, Zhuo X D. Optimized kernel extreme learning machine using Sine Cosine Algorithm for prediction of unconfined compression strength of MICP cemented soil. Environmental Science and Pollution Research, 2024; 31: 24868–24880.
[30] Wu Z J, Cui N B, Hu X T, Gong D Z, Wang Y S, Feng Y, et al. Optimization of extreme learning machine model with biological heuristic algorithms to estimate daily reference crop evapotranspiration in different climatic regions of China. Journal of Hydrology, 2021; 603: 127028.
[31] Hu J, Ma R, Jiang S Z, Liu Y L, Mao H Y. Prediction of reference crop evapotranspiration in China’s climatic regions using optimized machine learning models. Water, 2024; 16: 3349.
[32] Yang L S, Feng Q, Adamowski J F, Yin Z L, Wen X H, Wu M, et al. Erratum to ‘Spatio-temporal variation of reference evapotranspiration in northwest China based on CORDEX-EA’ [Atmos. Res. 238 （2020） 104868]. Atmospheric Research, 2021; 252: 105425.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 International Journal of Agricultural and Biological Engineering
This work is licensed under a Creative Commons Attribution 4.0 International License.
IJABE is an international peer reviewed, open access journal, adopting Creative Commons Copyright Notices as follows.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
