Improving time upscaling of instantaneous evapotranspiration based on machine learning models

Evapotranspiration (ET) plays a crucial role in the global water and energy cycle. Upscaling instantaneous ET ([Formula: see text]) to daily ET ([Formula: see text]) is vital for thermal-based ET estimation. Conventional methods – such as the constant evaporative fraction method (ConEF), radiation-based method, and evaporative ratio method – often overlook environmental factors, leading to biased estimates of [Formula: see text] from [Formula: see text]. To resolve this issue, this study aimed to assess four machine learning (ML) algorithms—XGBoost, LightGBM, AdaBoost, and Random Forest—to integrate meteorological and remote sensing data for upscaling [Formula: see text] across 88 global flux sites. Each ML model was tested with eight different variable combinations. Results indicated that XGBoost exhibited the best performance, with a root mean square error (RMSE) generally below 13 W [Formula: see text] in estimating [Formula: see text] from [Formula: see text]. The best variable combination simultaneously considers evaporative fraction, available energy, meteorology factors, remote sensing albedo, normalized vegetation index, and leaf area index. Using this combination, the XGBoost model achieved an [Formula: see text] = 0.88 and an RMSE = 12.33 W [Formula: see text], outperforming the ConEF method ([Formula: see text] = 0.71 and RMSE = 18.86 W [Formula: see text]) and its expansions. These findings support the application of ML models in ET upscaling, enabling ET estimation across large spatiotemporal scales.