Application of the remote sensing technique to monitor landslides of Hualien debris disaster watershed areas

The four-period SPOT satellite images of years 1996, 2002, 2005, and 2007 were used as analyzed materials, and also the relevant map data were coupled to digitize the landslide area layer of Shoufong and Siouguluan watersheds in Hualien County of Taiwan. The changed conditions of two investigated watersheds were examined and their characters of environmental factors were also analyzed through calculating the vegetation recovery ratio (VRR), the increasing collapse ratio (ICR), and the centroid displacement vector of landslide area. The result shows that it is useful to monitor landslide area and then to know their cover changed conditions over a long period of time by utilizing multi-temporal satellite images. Obviously, precipitation is the directly influential factor of causing the happenings of serious collapses, and a large number of occurrences of collapses are triggered by precipitation. The calculations of VRR, ICR, and the centroid displacement vector of landslide area can efficiently quantify the recovery of vegetation and the increasing collapse situation. Finally, the frequency of collapsing increases with increasing elevation and slope. Thus, these influential factors mentioned above have to be paid carefully attention in future developments.