Main content area

Land Surface Emissivity and temperature retrieval from Landsat-8 satellite data using Support Vector Regression and weighted least squares approach

Saradjian, Mohammad Reza, Jouybari-Moghaddam, Yaser
Remote sensing letters 2019 v.10 no.5 pp. 439-448
Landsat, algorithms, data collection, equations, least squares, radiative transfer, remote sensing, surface temperature
The main purpose of this paper is to develop a method to retrieve the Land Surface Emissivity (LSE) and Land Surface Temperature (LST) simultaneously from Landsat-8 satellite images. LST and LSE can be retrieved from Radiative Transfer Equation (RTE) but estimating LST and LSE from RTE is an undetermined problem. In this study, in order to solve this problem, an approach is proposed which include an equation set of RTE for band10 of Landsat-8 and two additional equations based on the regression relation between the Visible and Near-Infrared (VNIR) bands with mean and difference between LSEs of Landsat-8 thermal bands and then solving the equation set using the iterative weighted least squares approach. The effectiveness of the proposed algorithm was tested using simulated and satellite dataset. For satellite dataset, results show that Root Mean Square Error (RMSE) of LST is 1.72 K and RMSEs of LSEs for bands10 and 11 are 0.0057 and 0.0071, respectively. Also for simulated data, RMSE of LST is 1.16 K and RMSEs of LSEs for bands10 and 11 are 0.0063 and 0.0066, respectively.