Open access
Original Paper
Published: 05 October 2026
Comparative Analysis of Machine Learning Classifiers for Remote Sensing Land-Use Classification in Equatorial Watershed Ecosystems
Hendra Wijaya, David Campbell, Tri Wulandari
1. Dept. of Informatics & Geography, Universitas Tadulako, Palu; 2. Remote Sensing Research Center; 3. Dept. of Forestry and Environmental Science.
Abstract
Assessing Random Forest, XGBoost, and Sentinel-2 multispectral transformer networks for tropical forest canopy degradation mapping. Ensemble classifiers attained 96.4% overall classification accuracy across complex cloud-covered terrain.
Keywords:
Remote Sensing, Machine Learning, Random Forest, XGBoost, Sentinel-2, Watershed Monitoring
Publication Details
| Journal | Journal of Science Research & Education |
| Issue | Volume 1, Issue 1 (2026), pp. 37–48 |
| ISSN (Online) | 2988-1021 |
| Publisher | Global Innovation & Academic Press (GIA Press) |
| Peer Review | Double-blind peer reviewed in accordance with COPE ethical guidelines |
| License | Creative Commons Attribution 4.0 International (CC BY 4.0) |
How to Cite (APA 7th Edition)
Hendra Wijaya, David Campbell, Tri Wulandari (2026). Comparative Analysis of Machine Learning Classifiers for Remote Sensing Land-Use Classification in Equatorial Watershed Ecosystems. Journal of Science Research & Education, 1(1), 37–48. https://doi.org/10.59653/jsre.v2i01.2029