GYMEE: A Global Field-Scale Crop Yield and ET Mapper in Google Earth Engine Based on Landsat, Weather, and Soil Data

In this study, we used Landsat Earth observations and gridded weather data along with global soil datasets available in Google Engine (GEE) to estimate crop yield at 30 m resolution. We implemented a remote sensing evapotranspiration-based light use efficiency model globally integrated abiotic environmental stressors (temperature, moisture, vapor deficit stressors). The operational (Global Yield Mapper (GYMEE)) was validated against actual for three agricultural schemes different climatic, soil, management conditions located Lebanon, Brazil, Spain. Field-level on wheat, potato, corn 2015–2020 were assessment. performance of GYMEE statistically evaluated through root-mean-square error (RMSE), mean absolute (MAE), bias (MBE), relative (RE), index agreement (d). results showed that the difference between modeled predicted field-level within ±16% analyzed crops both Brazil Lebanon study sites ±15% Spain site (except two fields). performed best wheat low RMSE (0.6 t/ha), MAE (0.5 MBE (?0.06 RE (0.83%). A very good observed all yields, an (d) averaging 0.8 studied sites. shows potential providing estimates yields ±6%. also quantified spatialized moisture stress constraint its impact reducing biomass production. showcasing emphasized fields from revealed 12% can decrease by 17%. comparison 2017 2018 seasons potato culture season lower stresses had higher efficiency, above-ground biomass, 5%, 10%, 9%, respectively. show is high value assessing food