A Review of Earth or land surface use and cover Classification using the Landsat8 Remote Sensing data for Dehradun Region

In accordance with economic and industrial development, the number of land use or land-cover or (ESU/ESC) deviations has increased tremendously with uncontrolled population growth, particularly in emerging nations in the late 20th and primary 21st periods. In the best efficient way to understand the impact of ESU/ESC and control the effects of land change, ESU/ESC change has become a major concern for ecologists and policymakers to understand how different machine learning classifiers significantly support the estimation of ESU/ESC maps from remote sensing data. Prime purpose of the study is to categorize ESU/ESC applying different machine learning algorithms on the Google Earth Engine platform, specifically using the Random Forest, Support Vector Machine, Classification and Regression Trees to compare the effectiveness of each algorithm using accuracy estimation. Future sustainable development and a knowledge of the dynamics of our changing environment will undoubtedly benefit from ESU/ESC categorization study.