COMPARISON OF MACHINE LEARNING ALGORITHMS FOR LAND USE AND LAND COVER ANALYSIS USING GOOGLE EARTH ENGINE (CASE STUDY: WANGGU WATERSHED)

Abstract

Human population growth and land use and land cover (LULC) change have always developed side by side. Considering selection of a good Machine Learning (ML) classifier algorithm is needed considering the high estimation of LULC maps based on remote sensing. This study aims to produce a LULC classification of Landsat-8 and Sentinel-2 images by comparing the accuracy performance of three ML algorithms, namely: Classification and Regression Tree (CART), Random Forest (RF), and Support Vector Machine (SVM). Dataset comparison ratios were also explored to find the LULC classification results with the best accuracy. Sentinel-2 is better than Landsat-8 regarding Overall Accuracy (OA) and Coefficient Kappa. The comparison ratio of the training and testing datasets with a good level of accuracy is 70:30 on both images with the average OA Landsat-8 and Sentinel-2 being 92.09% and 94.21%, respectively. The RF algorithm outperforms CART and SVM in both types of satellite imagery. The mean OA of the CART, RF, and SVM classifiers was 92.03%, 94.74%, 83.54% on Landsat-8, 93.14%, 96.15%, and 93.34% on Sentinel-2, respectively.