Forest mapping in Peninsular Malaysia using Random Forest and Support Vector Machine Classifiers on Google Earth Engine

Forests play a crucial role in maintaining the balance of global ecosystem by sustaining interactions between living and non-living entities. Changes forest areas encompass both growth loss, often driven development activities. Assessing cover its changes is also pivotal issue management. Therefore, this study aims to investigate performance machine learning algorithms, namely Random Forest (RF) Support Vector Machine (SVM), mapping Peninsular Malaysia. Landsat 5 TM 8 OLI images were utilized derive information. The classification process was automated using remote sensing data management platform, Google Earth Engine (GEE). accuracy assessment test Kappa coefficient resulted value 0.7893 for RF algorithm 0.6328 SVM year 2010. Whereas, 2020 yielded 0.7475 0.5893 SVM. However, returned highest values 0.875 (2010) 0.8793 (2020), 0.8116 0.7313 (2020). results implied that performed better land use compared It evident can aid various stakeholders assessing future plans developments without compromising environment. Keywords: (GEE), Landsat, learning, Forest, stratified random,