A Fuzzy Logic-Based Approach for the Detection of Flooded Vegetation by Means of Synthetic Aperture Radar Data

Abstract

ABSTRACT:In this paper an algorithm designed to map flooded vegetation from synthetic aperture radar (SAR) imagery is introduced. The approach is based on fuzzy logic which enables to deal with the ambiguity of SAR data and to integrate multiple ancillary data containing topographical information, simple hydraulic considerations and land cover information. This allows the exclusion of image elements with a backscatter value similar to flooded vegetation, to significantly reduce misclassification errors. The flooded vegetation mapping procedure is tested on a flood event that occurred in Germany over parts of the Saale catchment on January 2011 using a time series of high resolution TerraSAR-X data covering the time interval from 2009 to 2015. The results show that the analysis of multi-temporal X-band data combined with ancillary data using a fuzzy logic-based approach permits the detection of flooded vegetation areas.

Fuzzy Discretization Technique for Bayesian Flood Disaster Model

“…Although the natural breaks can handle volumes of spatial data, this method required predefined numbers of intervals before the discretization process. There are numerous studies including works by various researchers (Chang & Tsai, 2016;Güçlü & Şen, 2016;Lohani, Kumar, & Singh, 2012;Pulvirenti, Pierdicca, Chini, & Guerriero, 2011;Tsyganskaya et al, 2016) that exploit the concept of fuzzy logic in model development for disaster management analysis. It has been shown that fuzzy logic is extensively applied to analyze complex patterns with high accuracy.…”