Satellite remote sensing provides data on land surface characteristics, useful for mapping land surface energy fluxes and evapotranspiration (ET). Land-surface temperature (LST) derived from thermal infrared (TIR) satellite data has been reliably used as a remote indicator of ET and surface moisture status. However, TIR imagery usually operates at a coarser resolution than that of shortwave sensors on the same satellite platform, making it sometimes unsuitable for monitoring of field-scale crop conditions. This study applies the data mining sharpener (DMS; Gao et al., 2012) technique to data from the Moderate Resolution Imaging Spectroradiometer (MODIS), which sharpens the 1 km thermal data down to the resolution of the optical data (250-500 m) based on functional LST and reflectance relationships established using a flexible regression tree approach. The DMS approach adopted here has been enhanced/refined for application over irrigated farming areas located in harsh desert environments in Saudi Arabia. The sharpened LST data is input to an integrated modeling system that uses the Atmosphere-Land Exchange Inverse (ALEXI) model and associated flux disaggregation scheme (DisALEXI) in conjunction with model reanalysis data and remotely sensed data from polar orbiting (MODIS) and geostationary (MSG; Meteosat Second Generation) satellite platforms to facilitate daily estimates of evapotranspiration. Results are evaluated against available flux tower observations over irrigated maize near Riyadh in Saudi Arabia. Successful monitoring of field-scale changes in surface fluxes are of importance towards an efficient water use in areas where fresh water resources are scarce and poorly monitored. Gao, F.; Kustas, W.P.; Anderson, M.C. A Data Mining Approach for Sharpening Thermal Satellite Imagery over Land. Remote Sens. 2012, 4, 3287-3319.