SEBALIGEE v2: Global Evapotranspiration Estimation Replacing Hot/Cold Pixels with Machine Learning

Joint Program Report
SEBALIGEE v2: Global Evapotranspiration Estimation Replacing Hot/Cold Pixels with Machine Learning
Mhawej, M., X. Gao, J.M. Reilly and Y. Abunnasr (2022)
Joint Program Report Series, October, 11 p.

Report 362 [Download]

Abstract/Summary:

Abstract: An open source computer algorithm, the Surface Energy Balance Algorithm for Land-Improved (SEBALI), was designed to estimate actual evapotranspiration (ET) at a basin level. In this study, we build on later versions of SEBALI/SEBALIGEE to estimate ET at a 30-m resolution for any scale application using advanced machine learning approaches (SEBALIGEE v2). We evaluate the monthly ET estimated from the new algorithm across several fluxnet sites in US, China, Italy, Belgium, Germany, and France, yielding an Absolute Mean Error (AME) of 0.41 mm/day versus 0.48 mm/day in the original SEBALIGEE. Analyses of the ET in the US indicate that the annual wheat ET decreases significantly between 2013 and 2021 (p < 0.05), accompanied by a significant air temperature increase. Net solar radiation is found to be the most influencing factor on ET of corn and soybeans with R2 values of ~0.72.

Citation:

Mhawej, M., X. Gao, J.M. Reilly and Y. Abunnasr (2022): SEBALIGEE v2: Global Evapotranspiration Estimation Replacing Hot/Cold Pixels with Machine Learning. Joint Program Report Series Report 362, October, 11 p. (http://globalchange.mit.edu/publication/17917)
  • Joint Program Report
SEBALIGEE v2: Global Evapotranspiration Estimation Replacing Hot/Cold Pixels with Machine Learning

Mhawej, M., X. Gao, J.M. Reilly and Y. Abunnasr

Joint Program Report Series

Report 

362
October, 11 p.
2022

Abstract/Summary: 

Abstract: An open source computer algorithm, the Surface Energy Balance Algorithm for Land-Improved (SEBALI), was designed to estimate actual evapotranspiration (ET) at a basin level. In this study, we build on later versions of SEBALI/SEBALIGEE to estimate ET at a 30-m resolution for any scale application using advanced machine learning approaches (SEBALIGEE v2). We evaluate the monthly ET estimated from the new algorithm across several fluxnet sites in US, China, Italy, Belgium, Germany, and France, yielding an Absolute Mean Error (AME) of 0.41 mm/day versus 0.48 mm/day in the original SEBALIGEE. Analyses of the ET in the US indicate that the annual wheat ET decreases significantly between 2013 and 2021 (p < 0.05), accompanied by a significant air temperature increase. Net solar radiation is found to be the most influencing factor on ET of corn and soybeans with R2 values of ~0.72.

[ARTICLE PDF]

Posted to public: 

Thursday, October 20, 2022 - 12:50