 This paper reviews six machine learning algorithms used for land use slash land cover, LULC, classification. The random forest, RF, algorithm was found to be the most accurate with a Kappa coefficient of 0.89. This result is supported by the receiver operating characteristic ROS curve, index based validation and root mean square error, RMSE. Additionally, the RF algorithm had the highest correlation with normalized differential vegetation index, NDVI, normalized differential built-up index, NDBI, and normalized differential water index, NDWI. These results suggest that the RF algorithm is the most suitable for LULC classification. This article was authored by Swapantalitar, Pankaj Singda, Susad Mahato, and others.