Analyzing Land Cover Changes over Landsat-7 Data using Google Earth Engine

Abstract

For various decision support systems, the detection of land use and land cover (LULC) change based on remote sensing data is a crucial source of information. Land conservation, sustainable development, and the management of water resources all benefit from the information gathered through the detection of changes in land use and land cover. Therefore, determining the change in land use and land cover detection of Lucknow is a primary issue of this work. Landsat 30 m resolution pictures, remote sensing data, satellite photos, and image processing techniques were used to determine changes in land cover across three dates the years 2005, 2015, and 2021. Built-up, high vegetation, water, and Low Vegetation were the four land cover classes used in the classification. Pre-processing and classification of the images were extensively analyzed, and the accuracy of the results was tested individually using the confusion matrix and kappa coefficient. According to the findings, the overall accuracy was 88.21%, 90.32%, and 92.40% for the years 2005, 2015, and 2021 respectively, with kappa coefficients of 84.02%, 88.32%, and 90.66%. According to this study, the amount of residential and agricultural land in the study area has dramatically expanded over the past 16 years, and high vegetation areas like forest ad dense green fields are decreased.