Journal Article

Improved 30‐m Evapotranspiration Estimates Over 145 Eddy Covariance Sites in the Contiguous United States: The Role of ECOSTRESS, Harmonized Landsat Sentinel‐2 Imagery, Climate Reanalysis, and Deep Neural Network Postprocessing

Rashid, Taufiq, Tian, Di

2024

Overview

This study developed and evaluated 30‐m daily evapotranspiration (ET) estimates using the Priestley‐Taylor Jet Propulsion Laboratory (PT‐JPL) model with ECOSTRESS, Moderate MODIS, harmonized Landsat Sentinel‐2 (HLS) imagery, ERA5‐Land reanalysis, and eddy covariance measurements. The new daily 30‐m ET showed significantly improved performance (overall, r = 0.8, RMSE = 1.736, KGE = 0.466) at 145 EC sites over contiguous United States compared to the current 70‐m ECOSTRESS ET (overall, r = 0.485, RMSE = 4.696, KGE = −0.841). A deep neural network postprocessing model trained with ET measurements from EC sites further improved the performance on test sites that were not used for model training (overall, r = 0.842, RMSE = 0.88, KGE = 0.792). The 30‐m ET estimation biases were significantly related to the biases in the upwelling longwave (RUL) and downwelling shortwave radiation (RDS) inputs, with ET estimates driven by MODIS radiation showing higher biases compared to those driven by ERA5‐Land radiation. The error diagnosis using random forest indicates that ET biases tend to be larger under higher ET estimates, and RUL and RDS were the primary contributors to the high bias at the higher ET ranges, with partial dependence plots revealing that the estimation biases tend to be higher under more humid environment, denser vegetation covers, and high net radiation conditions. In conclusion, higher spatial resolution satellite imagery of vegetation characteristics and higher temporal resolution radiation data, combined with continent‐wide EC measurements and deep learning, provided substantial added value for improving ET estimations at the field scale (30‐m). Key Points We developed and evaluated 30‐m evapotranspiration (ET) estimates driven by ECOSTRESS, MODIS, harmonized Landsat Sentinel‐2, and ERA5‐Land data The new 30‐m ET estimates showed significantly improved performance compared to the current 70‐m ECOSTRESS ET over contiguous United States Deep neural network with eddy covariance measurements further improved 30‐m ET estimates at unmeasured locations

• Publisher: John Wiley & Sons, Inc,Wiley
• Subject: Artificial neural networks / Bias / climate / climate reanalysis / Covariance / Deep learning / Downwelling / ECOSTRESS / Eddy covariance / Estimates / Evapotranspiration / Evapotranspiration estimates / Evapotranspiration measurements / Hydrology / Landsat / Landsat satellites / Machine learning / MODIS / Net radiation / Neural networks / Ocean circulation / Plant cover / Propulsion systems / Radiation / Radiation balance / Radiation data / Regions / Remote sensing / satellite data / Satellite imagery / Satellites / Short wave radiation / shortwave radiation / Space stations / Spatial discrimination / Spatial resolution / Temporal resolution / Upwelling / Vegetation / Vortices / water