MANGROVE COVERAGE CHANGE DETECTION USING LANDSAT IMAGERIES BASED ON HYBRID CLASSIFICATION IN KEMBUNG RIVER, BENGKALIS ISLAND, RIAU PROVINCE

The l imited scientific information and lack of attention from stakeholders onthe status of mangroves in Kembung R iverfunctioned as a basis of this study. Four series of Landsat data recorded in 1996, 2002, 2010 , and 2013 were used to map mangrove land cover and changes detection. Hybrid classification technique ,a combin ation ofthe object-based and random forest classification s, w ere applied in this study . The result showed that based on hybrid classification , mangrove coverage was detected with in 82.6-88.4% overall accuracy.Change detection analys e s showed that the mangrove area of Kembung River was relatively stable. For nearly two decades, we found mangrove loss about 197.2 h a , gain of 251.1 ha , and unchanged of 2904.9 ha. Changes in mangrove were generally caused by anthropogenic factors such as mangrove replanting, logging, changes over the function of mangroves into the road, embankment, settlement ,shrimp farms , and natural growth. Serious attention from various parties are needed to maintain the existence and sustainabl i lity of mangrove ecosystems in Kembung River.  Keywords: Mangrove, Sungai Kembung, monitoring, Landsat, hybrid classification