COMPARISON OF MACHINE LEARNING ALGORITHMS FOR LAND USE AND LAND COVER ANALYSIS USING GOOGLE EARTH ENGINE (CASE STUDY: WANGGU WATERSHED)
DOI:
https://doi.org/10.30536/j.ijreses.2022.v19.a3803Keywords:
Google Earth Engine, Land Use Land Cover, Classification and Regression Tree, Random Forest, Support Vector MachineAbstract
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.
Downloads
Published
Issue
Section
License
Copyright (c) 2022 Author (S)
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
Copyright Notice for the International Journal of Remote Sensing and Earth Sciences (IJReSES)
Copyright Holder: Author(s).
By submitting an article to IJReSES, author(s) agree to the following terms:
1. Grant of Publishing Rights: Authors grant IJReSES the license to publish the article and to identify itself as the original publisher. This includes the right to make the article available in all forms and media.
2. Commercial Rights: Authors grant IJReSES the rights to produce and sell hardcopy volumes of the journal. These volumes may be purchased by libraries, individuals, or other entities.
3. Third-Party Use: Authors agree to allow any third party to freely use the article, provided that the original authors are credited and the article is cited appropriately. This facilitates the dissemination and impact of the work.
4. Creative Commons License: The article is distributed under the Creative Commons Attribution non Commercial Share Alike 4.0 License (CC BY-NC-SA 4.0). This license allows others to distribute, remix, adapt, and build upon the work, even commercially, as long as the original author is credited for the original creation.
5. Associated Published Material: Unless otherwise stated, any associated published material (such as supplementary data, graphics, and multimedia) is distributed under the same CC BY-NC-SA 4.0 License.
By adhering to these terms, authors ensure the wide dissemination and accessibility of their work, contributing to the advancement of knowledge in the fields of remote sensing and earth sciences.
