Near real-time deforestation detection in Malaysia and Indonesia using change vector analysis with three sensors

Malaysia and Indonesia have been affected by deforestation caused in great part by the proliferation of oil palm plantations. To survey this loss of forest, several studies have monitored these southeast Asian nations with satellite remote sensing alert systems. The methods used have shown potential for this approach, but they are limited by imagery with coarse spatial resolution, low revisit times, and cloud cover. The objective of this research is to improve near real-time operational deforestation detection by combining three sensors: Sentinel-1, Sentinel-2 and Landsat-8. We used Change Vector Analysis to detect changes between non-affected forest and images under analysis. The results were validated using 166 plots of undisturbed forest and confirmed deforestation events throughout Sabah Malaysian State, and from 70 points from drone pictures in Sumatra, Indonesia. Sentinel-2 and Landsat-8 yielded sufficient results in terms of accuracy (less than 11% of commission and omission error). Sentinel-1 had lower accuracy (14% of commission error and 28% of omission error), probably resulting from geometric distortions and speckle noise. During the high cloud-cover season optical sensors took about twice the time to detect deforestation compared to Sentinel-1 which was not affected by cloud cover. By combining the three sensors, we detected deforestations about 8days after forest clearing events. Deforestations were only detectable during approximately the first 100days, before bare soils were often coved by legume crop. Our results indicate that near real-time deforestation detection can reveal most events, but the number of false detections could be improved using a multiple event detection process.