Publications

Aliabad, FA; Zare, M; Malamiri, HG (2021). Comparison of the accuracy of daytime land surface temperature retrieval methods using Landsat 8 images in arid regions. INFRARED PHYSICS & TECHNOLOGY, 115, 103692.

Abstract
Land surface temperature (LST) is a significant parameter in surface and atmospheric systems which can be used to describe the physical processes of energy and water exchange. There are several ways to retrieve land surface temperature using satellite imagery. The purpose of the current study is to compare the accuracy of different LST retrieval algorithms, including 11 types of split-window algorithms, two mono-window algorithms, and three single-channel algorithms. The validation of LST retrieval algorithms was done using temperature-based and cross-validation methods. In this study, 20 images from Landsat 8 satellite related to 2017 and 2018 were used to retrieve LST in different ways. The temperatures obtained from different methods were compared in one day, and the average of LST of the different methods was about 5. different, which indicates the importance of the existing validation methods. Using Sentinel-2 image classification, 20 points in homogeneous areas with pure pixels were selected to measure the LST using a thermometer for land validation. Results showed that in a split window algorithm which was applied on the water vapor image, the RMSE error has been reduced by 2 degrees C. In cross-validation, MODIS LST images were used, and RMSE temporal image was prepared, and classified into five groups including less than 2, 2-3, 3-4 and more than 5 degrees C Comparing the area of each of these groups in different methods showed that MW2 and SW1 methods have less accuracy than the other methods. The SW9 algorithm can retrieve temperature with an error of less than 2. in 80% of the area. The results of cross-validation showed that the SC2 algorithm had the highest accuracy among the algorithms that use a thermal band for LST retrieval with a RMSE spatial of 5.3 degrees C and the SW10 and SW11 have shown the highest accuracy among the algorithms that use two thermal bands with RMSE less than 5 degrees C In general, the algorithms that use atmospheric transmittance coefficients and water vapor as inputs are more accurate than the others.

DOI:
10.1016/j.infrared.2021.103692

ISSN:
1350-4495