METODE RANDOM FOREST DAN SUPPORT VECTOR MACHINE UNTUK MONITORING PERUBAHAN TUTUPAN LAHAN DI KECAMATAN KLAPANUNGGAL, KABUPATEN BOGOR

Random Forest and Support Vector Machine Methods for Monitoring Land Cover Change in Klapanunggal District, Bogor Regency

Authors

  • Suwanda
  • Nining Puspaningsih
  • Sri Rahaju

Keywords:

land cover, machine learning, sentinel-2, random forest, support, verctor machine

Abstract

Land cover change is an ongoing phenomenon, making regular monitoring essential. One effective approach to land cover classification is supervised machine learning. This study utilizes Sentinel-2 imagery from 2018 and 2024 to monitor changes in land cover. Classification was conducted using two algorithms—Random Forest (RF) and Support Vector Machine (SVM)—in accordance with the Indonesian National Standard (SNI) 7645:2014 for land cover classification. The results indicate that RF achieved a higher accuracy of 92.73%, compared to 90.91% for SVM. Consequently, RF was selected for further analysis of land cover changes. Negative changes totaled 272.42 ha (2.86%), primarily involving the conversion of rice fields into settlements (114.42 ha or 1.2%). Positive changes amounted to 85.6 ha (0.9%), with the most common being the conversion of shrubs into dryland agriculture (43.5 ha or 0.46%).

Published

2025-06-25

Issue

Section

Articles

How to Cite

METODE RANDOM FOREST DAN SUPPORT VECTOR MACHINE UNTUK MONITORING PERUBAHAN TUTUPAN LAHAN DI KECAMATAN KLAPANUNGGAL, KABUPATEN BOGOR: Random Forest and Support Vector Machine Methods for Monitoring Land Cover Change in Klapanunggal District, Bogor Regency. (2025). Jurnal ForestrIndo, 2(1), 301-314. https://journal.ipb.ac.id/forestrindo-journal/article/view/65237