Estimation of Evapotranspiration Using a Nonparametric Approach Under All Sky: Accuracy Evaluation and Error Analysis

Accurate estimation of regional evapotranspiration (ET) or latent heat flux (latent energy, LE) remains a challenge. On the basis of a nonparametric approach, this study proposed an all-sky algorithm based on moderate-resolution imaging spectroradiometer (MODIS) products and datasets of China Meteorological Administration Land Data Assimilation System (CLDAS). Eddy covariance observations from three nonvegetated sites (desert, Gobi, and village) and three vegetated sites (orchard, vegetable, and wetland) over an arid/semiarid region were used as references to validate the new algorithm. Results showed that the spatial and temporal patterns of LE coincided with desert-oasis ecosystems. Comparison of the retrieved and reference values yielded the following results: R
²
= 0.19-0.63, bias = -129-56 W/m
²
, relative error (RE) = 5%-29%, and root-mean-square error (RMSE) = 95-150 W/m
²
. Remote-sensing-retrieved LE (RSLE) exhibited relatively good accuracy and poor agreement with ground observations at the nonvegetated sites (RE: 5%-23%, R
²
: 0.19-0.40), whereas contradicting scenario occurred at the vegetated sites (RE: 24%-29%, R
²
: 0.46-0.63). In the arid nonvegetated region, the ET error might have been caused by net radiation, soil heat flux, land surface temperature, and air temperature. In the vegetated region, the errors of MODIS and CLDAS products were not the dominant error sources of RSLE. The validation supported the applicability of the proposed algorithm in the arid/semiarid region.