<![CDATA[Tropical forest fires pose a serious threat to ecosystem sustainability, particularly in Kalimantan, which is prone to seasonal fires. Early detection is key to prevention efforts, but conventional and satellite-based monitoring methods often face limitations, particularly in identifying small-scale hotspots obscured by forest canopies. This study aims to test the effectiveness of integrating drone technology with thermal sensors in tropical forest monitoring as an early fire detection system. The research method uses a field study design with an experimental approach. Drone flights were conducted over tropical forest areas in Kalimantan, systematically capturing thermal imagery according to a predetermined flight path. Thermal image data were analyzed to identify hotspots, then compared with satellite hotspot data (MODIS and VIIRS). Field validation was also conducted through direct temperature measurements using a portable infrared thermometer. Data analysis involved comparing detection results, accuracy testing, and measuring system sensitivity with a confusion matrix. The results showed that drones with thermal sensors were able to detect more hotspots than satellites, with a higher level of accuracy compared to field validation results. For example, in several study areas, drones successfully identified small hotspots that were not detected by satellites. This confirms that drones with thermal sensors have high sensitivity and can be used as early detection tools for tropical forest fires. In conclusion, the integration of drone technology and thermal sensors has proven effective as a monitoring system that complements satellite-based methods. Further development using big data and machine learning, as well as cross-institutional collaboration, is needed for optimal implementation on a large scale.]]>
Copyrights © 2024
