부산대학교 도서관

In precision flood monitoring it is important to follow the temporal evolution of an event. Often, however, sufficient temporal coverage of events spanning several days can be attained only by recurring to multi-sensor data, due to different acquisition characteristics and schedules of different types of sensors. We present an example of a successful fusion of data coming from both SAR (COSMO-SkyMed stripmap, 3-m resolution) and optical (RapidEye, multispectral, 5 m-resolution) data, covering a flood event in southern Italy. The data fusion is performed through a Bayesian network approach, a reliable means to infer probabilistic infomation from heterogeneous sources. Results show accordance with independent model-based flood maps reaching accuracies of up to 96%.