An extended SW-TES algorithm for land surface temperature and emissivity retrieval from ECOSTRESS thermal infrared data over urban areas

Abstract

Land surface temperature (LST) over urban areas is an essential parameter in the monitoring of urban thermal environment. Urbanization has resulted in a more complex geometric structure of urban surface than natural surface. However, in the conventional LST retrieval algorithms, the impact of urban geometric structure is usually neglected. In this study, an extended algorithm that combines the split-window algorithm (SW) and the temperature and emissivity separation algorithm (TES) was proposed to retrieve LST and land surface emissivity (LSE) over urban areas simultaneously from the ECOsystem Spaceborne Thermal Radiometer Experiment on Space Station (ECOSTRESS) thermal infrared (TIR) data. In the extended SW-TES algorithm with considering urban geometry effect, the brightness temperature at ground level was obtained using the SW algorithm, and the LST and LSE were retrieved simultaneously by using the TES algorithm. The results indicate that LST (LSE) retrieved by the extended SW-TES algorithm with urban geometry effect correction has generally lower (higher) values than that without urban geometry effect correction. The LST differences mostly vary from 0.3 K to 1.2 K, whereas the LSE differences are mainly concentrated between −0.01 and − 0.06. Furthermore, the root mean squared error (RMSE) between LST/LSE retrieved by the extended SW-TES algorithm with urban geometry effect correction and LST/LSE obtained from the ECOSTRESS level-2 LST/LSE product decrease with the increase of sky view factor (SVF). The largest RMSE is approximately 1.6 K for LST and 0.03 for LSE in the SVF of 0.1, which represents an urban pixel surrounded by high buildings within its adjacent pixels. There are no evident differences between LST/LSE retrieved by the extended SW-TES algorithm with urban geometry effect correction using five and three ECOSTRESS TIR bands. The LST differences are mainly concentrated between −0.2 K and 0.2 K, whereas the LSE differences mostly range from 0.001 to 0.004. The findings of this study indicate that it is necessary to consider urban geometry effect for accurate LST and LSE retrieval over urban areas.