点击次数：

DOI码：10.1002/hyp.15091

发表刊物：Hydrological Processes

关键字：Ångström–Prescott formula, global solar radiation, machine learning, penman–Monteith model, reference evapotranspiration

摘要：Accurately estimate reference evapotranspiration (ET0) is essential for regional water management. The FAO recommends coupling the Penman-Monteith (P-M) model with the Ångström-Prescott (A-P) formula as the standard method for ET0 estimation with missing Rs measurements, but its application is usually restricted by the two fundamental coefficients (a and b) of the A-P formula. This study proposed a new method for ET0 estimation with missing Rs by combining machine learning with physical-based P-M models. The benchmark values of the A-P coefficients were first determined at daily, monthly, and yearly scales and further evaluated in Rs and ET0 estimations at 80 national Rs measurement stations in China. Then, three empirical models and four machine learning methods were evaluated in estimating the A-P coefficients. Finally, the optimal estimation method was used to estimate the A-P coefficients for the 839 regular weather stations for ET0 estimation without Rs measurement for China. The results demonstrated a descending trend for the coefficient a from northwest to southeast China, with larger values provided in cold seasons. However, the coefficient b showed an opposite distribution as the coefficient a. Additionally, the A-P coefficients calibrated at the daily scale obtained the best estimation accuracy for both Rs and ET0, and slightly outperformed the monthly and yearly coefficients without significant difference in most cases. The machine learning methods outperformed the empirical methods for estimating the A-P coefficients, especially for the sites with extreme values. This study showed great potential for combining machine learning with physical models in ET0 estimation.

第一作者：Chen Shang

论文类型：期刊论文

期号：38

页面范围：e15091

是否译文：否

发表时间：2024-01-16

收录刊物：SCI