Comparison of MODIS surface temperatures to in situ measurements on the Greenland Ice Sheet from 2014 to 2017

Remotely sensed land surface temperature (LST) data, such as the Moderate Resolution Imaging Spectroradiometer (MODIS) LST thermal infrared products, are useful for monitoring surface processes on the Greenland Ice Sheet in remote areas but must be validated to ensure accuracy. Using data from the Programme for Monitoring the Greenland Ice Sheet (PROMICE), we conducted a MODIS LST validation (MOD/MYD11 C6 swath level product) using radiometric in-situ skin temperature records from 2014 to 2017 over 17 PROMICE sites mostly in the ice sheet's ablation zone. There is a significant cold bias in MODIS LST when compared to PROMICE skin temperature, particularly when PROMICE records temperatures below 0 degrees C (mean bias: 2.4 +/- 0.01 degrees C mean +/- standard error, RMSE = 3.2 degrees C). Multiple linear regression analysis reveals the difference between MODIS LST and PROMICE skin temperature is larger at lower temperatures, lower latent heat fluxes and higher specific humidity. Our results confirm the presence of a progressive cold bias in the MODIS LST that should be considered in use of this product, and we identify and corroborate areas for ongoing algorithm development.