Automatic boosted flood mapping from satellite data. Issue 5 (3rd March 2016)

• Record Type: Journal Article
• Authors: Coltin, Brian; McMichael, Scott; Smith, Trey; Fong, Terrence
• Is Part Of: International journal of remote sensing. Volume 37:Issue 5(2016)
• Page Start: 993
• Page End: 1015
• Publication Date: 2016-03-03
• Subjects: Remote sensing -- Periodicals; Télédétection -- Périodiques; 621.3678
• DOI: 10.1080/01431161.2016.1145366
• Languages: English
• ISSNs: 0143-1161

Abstract

ABSTRACT: Numerous algorithms have been proposed to map floods from Moderate Resolution Imaging Spectroradiometer (MODIS) imagery. However, most require human input to succeed, either to specify a threshold value or to manually annotate training data. We introduce a new algorithm based on Adaboost which effectively maps floods without any human input, allowing for a truly rapid and automatic response. The Adaboost algorithm combines multiple thresholds to achieve results comparable to state-of-the-art algorithms which do require human input. We evaluate Adaboost, as well as numerous previously proposed flood mapping algorithms, on multiple MODIS flood images, as well as on hundreds of non-flood MODIS lake images, demonstrating its effectiveness across a wide variety of conditions.