Evaluation of Landsat-8 TIRS data recalibrations and land surface temperature split-window algorithms over a homogeneous crop area with different phenological land covers

Successive re-calibrations were implemented in Landsat-8 TIRS data since launch. This paper evaluates the performances of both: (1) these re-calibrations, up to the last calibration update announced for TIRS data in the next Landsat Collection 2; and (2) single-channel (SC) corrections and split-window (SW) algorithms to retrieve land surface temperature (LST) from TIRS data. A robust and accurate multi-year (2014-2019) set of reference ground data were used, which included thermal infrared (TIR) radiance measurements taken along transects in a uniform and thermally homogeneous rice paddy area, but also emissivity measurements for the different ground covers at the site through the year. The calibration results showed significant biases at the site for data after the 2014 reprocessing, but negligible biases and root-mean-square differences (RMSDs) <1.5 K were obtained when using the current TIRS data in Collection 1 (i.e., data after the 2017 reprocessing). The last announced calibration update mainly introduced differences in biases, improving slightly the results for band 10 and presenting a calibration response difference between bands. The SC corrections showed negligible LST biases for both bands and the lowest RMSDs (<1.6 K) when using the band 10 data in the current Collection 1, and the bias disappeared for this band after applying the calibration update. Three of the seventeen different SW equations evaluated in the paper showed negligible biases and LST RMSDs lower than or equal to 0.8 K. These three SW algorithms are mainly recommended for users of the current TIRS data in Collection 1; one of them being that proposed to generate a SW LST product in the future Collection 3. Finally, bias differences around 1.4 K were shown in the results of the SW algorithms after applying the calibration update announced for Collection 2.