Publications

Chen, D; Zhuang, QF; Zhu, L; Zhang, WJ; Sun, T (2023). Generating Daily Gap-Free MODIS Land Surface Temperature Using the Random Forest Model and Similar Pixels Method. IEEE ACCESS, 11, 103274-103287.

Abstract
The land surface temperature (LST) is one of the vital variables for surface-atmosphere interaction. However, due to the vulnerability of thermal infrared remote sensing to clouds, the MODIS LST products have many observation gaps, which seriously limits their application. In this paper, to make up for the shortage of random forest model in reconstructing images with substantial cloud-cover pixels, a combined random forest (RF) and similar pixels (SP) reconstruction scheme was proposed to generate daily gap-free MODIS/Terra LST product and validated by the automatic weather stations (AWS) data in the Heihe River Basin. First, we used the RF model to reconstruct the images that meet the threshold (the clear-sky pixels percentage is more than 30%). Then, we used a combination of the RF model and the SP method to reconstruct the images that do not meet the threshold. Thus, the daily MODIS LST reconstruction results were obtained. The visual assessment indicated that the reconstructed LST strongly correlates with the original LST and can capture the spatial distribution features of LST-related characteristic variables. Additionally, the validation with in situ observations demonstrated that the method of directly using the RF model performs well with an $\text{R}<^>{2}$ of 0.87, an NSE of 0.87, an RMSE, and a Bias of 4.69 K and 0.08 K, respectively. The RF model and SP method combination still have a good performance with an $\text{R}<^>{2}$ of 0.79, an NSE of 0.76, and an RMSE and Bias of 6.37 K and 0.62 K, respectively.

DOI:
10.1109/ACCESS.2023.3318481

ISSN: