Academy & Industry Research Collaboration Center (AIRCC)

Volume 12, Number 13, July 2022

Outlier Detection and Reconstruction of Lost Land Surface Temperature Data in Remote Sensing


Muhammad Yasir Adnan, Yong Xue and Richard Self, University of Derby, United Kingdom


In quantitative remote sensing, missing values classified as outliers occur frequently. This is due to technical constraints and the impact of weather on the efficiency of instruments to collect data. In order to deal with these missing values, we offer an Outlier-Search-and-Replace (OSR) algorithm that uses spatial and temporal information for the detection and reconstruction of missing data. The algorithm searches for outlier in the data and reconstruct by finding the best possible match in spatial locations.


Remote Sensing, Missing Data Reconstruction, Outlier, MODIS, Land Surface Temperature.