Premium
Physics‐Constrained Machine Learning of Evapotranspiration
Author(s) -
Zhao Wen Li,
Gentine Pierre,
Reichstein Markus,
Zhang Yao,
Zhou Sha,
Wen Yeqiang,
Lin Changjie,
Li Xi,
Qiu Guo Yu
Publication year - 2019
Publication title -
geophysical research letters
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 2.007
H-Index - 273
eISSN - 1944-8007
pISSN - 0094-8276
DOI - 10.1029/2019gl085291
Subject(s) - evapotranspiration , eddy covariance , atmosphere (unit) , energy budget , physics , water cycle , latent heat , energy balance , vegetation (pathology) , flux (metallurgy) , surface (topology) , tower , sensible heat , atmospheric sciences , meteorology , mathematics , ecosystem , thermodynamics , geometry , ecology , biology , medicine , materials science , civil engineering , pathology , engineering , metallurgy
Estimating ecosystem evapotranspiration (ET) is important to understanding the global water cycle and to study land‐atmosphere interactions. We developed a physics constrained machine learning (ML) model (hybrid model) to estimate latent heat flux (LE), which conserves the surface energy budget. By comparing model predictions with observations at 82 eddy covariance tower sites, our hybrid model shows similar performance to the pure ML model in terms of mean metrics (e.g., mean absolute percent errors) but, importantly, the hybrid model conserves the surface energy balance, while the pure ML model does not. A second key result is that the hybrid model extrapolates much better than the pure ML model, emphasizing the benefits of combining physics with ML for increased generalizations. The hybrid model allows inferring the structural dependence of ET and surface resistance ( r s ), and we find that vegetation height and soil moisture are the main regulators of ET and r s .