Entropy-Based Fusion of Water Indices and DSM Derivatives for Automatic Water Surfaces Extraction and Flood Monitoring

Abstract

Abstract:Reliable water surface extraction is essential for river delineation and flood monitoring. Obtaining such information from fine resolution satellite imagery has attracted much interest for geographic and remote sensing applications. However, those images are often expensive and difficult to acquire. This study proposes a more cost-effective technique, employing freely available Landsat images. Despite its extensive spectrum and robust discrimination capability, Landsat data are normally of medium spatial resolution and, as such, fail to delineate smaller hydrological features. Based on Multivariate Mutual Information (MMI), the Landsat images were fused with Digital Surface Model (DSM) on the spatial domain. Each coinciding pixel would then contain not only rich indices but also intricate topographic attributes, derived from its respective sources. The proposed data fusion ensures robust, precise, and observer-invariable extraction of water surfaces and their branching, while eliminating spurious details. Its merit was demonstrated by effective discrimination of flooded regions from natural rivers for flood monitoring. The assessments we completed suggest improved extraction compared to traditional methods. Compared with manual digitizing, this method also exhibited promising consistency. Extraction using Dempster-Shafer fusion provided a 91.81% F-measure, 93.09% precision, 90.74% recall, and 98.25% accuracy, while using Majority Voting fusion resulted in an 84.91% F-measure, 75.44% precision, 97.37% recall, and 97.21% accuracy.

Internetworking flood disaster mitigation system based on remote sensing and mobile GIS

“…On analysing satellite images, the proposed method exhibited very high detection accuracy (97.15% with Kappa 0.92). This is on par with a work using the same imaging technique but upon similar studied areas (Horkaew and Puttinaovarat, 2017). Its performance was comparable to if not superior than those reported by other independent research on flood detection, e.g.…”

“…It is hence problematic to timely process the satellite data, especially preceding the flooding. This study circumvented this issue by assuming the predefined values from a previous work (Horkaew and Puttinaovarat, 2017), in which the thresholds were automatically calculated by maximizing mutual information (MI) among thematic spectral and topographical layers and validated against supervised delineation. The remaining discrepancies between extracted and actual water bodies, would be rectified by user reports and authorized verification of actual events.…”

“…Nevertheless, it may be drawn from the above surveys that, the success of flood analyses did not depend exclusively on a particular differential expression of water index, but also on a range of other thematic factors, including meteorological and geographical ones. It was reported in the papers (Puttinaovarat et al 2015;Horkaew and Puttinaovarat 2017) that when extracting water bodies from its studied areas in Thailand, NDWI and MNDWI calculated from Landsat-TM and MODIS images gave the most promising results. Examining similar areas, this research, therefore, adopted these indices in the subsequent flood analyses.…”

“…The thresholds of these indices were set for NDWI2 and MNDWI to 0.016 and 0.032, respectively. The values were taken from a study (Horkaew and Puttinaovarat 2017), in which the multivariate mutual information (MMI) were used to find optimal thresholds for automated water surface extraction in similar studied areas. To improve detection accuracy, weighted majority voting was employed in fusing the results obtained from both modalities.…”

Computer Vision and IoT-Based Sensors in Flood Monitoring and Mapping: A Systematic Review

“…The convenient way of acquiring images remotely of any location is through satellites [81]. Horkaew et al [82] employed a cost-effective technique which is based on multivariate mutual information (MMI) and fused the acquired medium spatial resolution image from Landsat with a digital surface model (DSM). The reason for the fusion was to introduce topographic attributes to each coinciding pixel index of an image.…”