Remote sensing imagery data presents difficulties when attempting to classify Land Cover and Land Use (LCLU). Since we are now living in the age of ”Big Data”, there is a tremendous increase in the volume of Remote Sensing (RS) measurements used for environmental protection that need interpretation. Deep Learning (DL) approaches have been developed as a current effective modeling tool to recover information from large remote sensing pictures for LCLU identification, allowing them to be used for this pressing problem. For asset preservation and nature conservation, it is crucial to classify data gathered remotely in the geologic domain. In recent years, LCLU classification using remote sensing image data has seen a rise in the use of deep learning techniques. The use of deep learning techniques, such as Convolutional Neural Networks (CNN) and recurrent neural networks, is enough for classifying remote sensing picture data. They propose to use deep CNNs to verify and assess their results using a variety of criteria. This paper presents a comparative study of the different methods used in Land Cover Land Use Classification to find out the best available method based on their accuracy.