Producing high-precision ﬂood maps requires integrating and correctly classifying information coming from heterogeneous sources. Methods to perform such integration have to rely on different knowledge bases. A useful tool to perform this task consists in the use of Bayesian methods to assign probabilities to areas being subject to ﬂood phenomena, fusing a priori information and modeling with data coming from radar or optical imagery. In this chapter we review the use of Bayesian networks, an elegant framework to cast probabilistic descriptions of complex systems, applied to ﬂood monitoring from multi-sensor, multi-temporal remotely sensed and ancillary data.
How to cite: Annarita D’Addabbo, Alberto Reﬁce, Domenico Capolongo, Guido Pasquariello and Salvatore Manfreda, Data Fusion Through Bayesian Methods for Flood Monitoring from Remotely Sensed Data, Springer International Publishing AG 2018, Pages 181 – 208, (doi: https://doi.org/10.1007/978-3-319-63959-8_8), 2018. [pdf]
Accurate ﬂood mapping is important for both planning activities during emergencies and as a support for the successive assessment of damaged areas. A valuable information source for such a procedure can be remote sensing synthetic aperture radar (SAR) imagery. However, ﬂood scenarios are typical examples of complex situations in which different factors have to be considered to provide accurate and robust interpretation of the situation on the ground. For this reason, a data fusion approach of remote sensing data with ancillary information can be particularly useful. In this paper, a Bayesian network is proposed to integrate remotely sensed data, such as multitemporal SAR intensity images and interferometric-SAR coherence data, with geomorphic and other ground information. The methodology is tested on a case study regarding a ﬂood that occurred in the Basilicata region (Italy) on December 2013, monitored using a time series of COSMO-SkyMed data. It is shown that the synergetic use of different information layers can help to detect more precisely the areas affected by the ﬂood, reducing false alarms and missed identiﬁcations which may affect algorithms based on data from a single source. The produced ﬂood maps are compared to data obtained independently from the analysis of optical images; the comparison indicates that the proposed methodology is able to reliably follow the temporal evolution of the phenomenon, assigning high probability to areas most likely to be ﬂooded, in spite of their heterogeneous temporal SAR/InSAR signatures, reaching accuracies of up to 89%.
How to cite: ’Addabbo, A., A. Refice, G. Pasquariello, F. Lovergine, D. Capolongo and S. Manfreda, A Bayesian Network for Flood Detection Combining SAR Imagery and Ancillary Data, IEEE Transactions on Geoscience and Remote Sensing, 54(6), 3612 -3625, (doi: 10.1109/TGRS.2016.2520487), 2016. [pdf]