Early Warning System for Forest and Land Fires in Sumatra Using Computer Vision and Remote Sensing Data

Satria Dwi Nanda (Department of Informatics Engineering, Faculty of Engineering, Syiah Kuala University, Banda Aceh, Indonesia)
Nur Aisyah Ahmad (Department of Computer Science, Faculty of Computer Science and Information Technology, University of Malaya, Kuala Lumpur, Malaysia)

Journal of Computer Science and Information Technology
Vol. 2 No. 2 (2026): Journal of Computer Science and Information Technology, June 2026

Forest and land fires in Sumatra pose significant environmental, health, and economic challenges. This study aims to develop an early warning system by integrating computer vision and remote sensing data to improve real-time fire detection accuracy. The method utilizes image processing techniques based on YOLO and CNN algorithms, combined with MODIS and Landsat satellite data for hotspot monitoring. Data analysis is conducted using machine learning approaches and multi-source data integration. The results indicate that the proposed system achieves detection accuracy above 90% and provides earlier warnings compared to conventional methods. The integration of drone imagery and satellite data proves effective in detecting fires at an early stage. This research contributes to the advancement of intelligent fire monitoring systems to support disaster mitigation efforts in Indonesia.