Land Use/Land Cover Classification Using Machine Learning and Deep Learning Algorithms for EuroSAT Dataset - A Review

In this paper, we tend to address the challenge of land use and land cover classification exploitation Sentinel-2 satellite pictures. The Sentinel-2 satellite pictures are overtly and freely accessible provided within the Earth observation program, Copernicus. Here, we tend to take into account EuroSAT dataset that's supported Sentinel-2 satellite pictures with 13 spectral bands and consists of ten categories within a total of 27,000 tagged and geo-referenced pictures. The presented model will facilitate the effective classification of land use and land cover. In this paper, we will be presenting the classification using different Machine Learning models like Random Forest, Decision Tree, K-Nearest Neighbour, Support vector machine, Gradient booster using Ensemble classifiers which will be implemented using ensemble classifier. Later, we tend to aim to compare the results of deep learning and machine learning models supported the metrics like accuracy. Finally, the most effective model which will be applied to perform land use and land cover classification was identified and presented to support the new researchers in this field.