Improving remote sensing flood assessment using volunteered geographical data

Improving remote sensing flood assessment using volunteered geographical data

A new methodology for the generation of flood hazard maps is presented fusing remote sensing and volunteered geographical data. Water pixels are identified utilizing a machine learning classification of two Landsat remote sensing scenes, acquired before and during the flooding event as well as a dig...

Full description

Bibliographic Details
Main Authors: E. Schnebele, G. Cervone
Format: Article
Language:English
Published: Copernicus Publications 2013-03-01
Series:Natural Hazards and Earth System Sciences
Online Access:http://www.nat-hazards-earth-syst-sci.net/13/669/2013/nhess-13-669-2013.pdf
id doaj-1bd43e85776642ca98bd3b4859ff83ef
record_format Article
spelling doaj-1bd43e85776642ca98bd3b4859ff83ef2020-11-24T20:55:21ZengCopernicus PublicationsNatural Hazards and Earth System Sciences1561-86331684-99812013-03-0113366967710.5194/nhess-13-669-2013Improving remote sensing flood assessment using volunteered geographical dataE. SchnebeleG. CervoneA new methodology for the generation of flood hazard maps is presented fusing remote sensing and volunteered geographical data. Water pixels are identified utilizing a machine learning classification of two Landsat remote sensing scenes, acquired before and during the flooding event as well as a digital elevation model paired with river gage data. A statistical model computes the probability of flooded areas as a function of the number of adjacent pixels classified as water. Volunteered data obtained through Google news, videos and photos are added to modify the contour regions. It is shown that even a small amount of volunteered ground data can dramatically improve results.http://www.nat-hazards-earth-syst-sci.net/13/669/2013/nhess-13-669-2013.pdf
collection DOAJ
language English
format Article
sources DOAJ
author E. Schnebele
G. Cervone
spellingShingle E. Schnebele
G. Cervone
Improving remote sensing flood assessment using volunteered geographical data
Natural Hazards and Earth System Sciences
author_facet E. Schnebele
G. Cervone
author_sort E. Schnebele
title Improving remote sensing flood assessment using volunteered geographical data
title_short Improving remote sensing flood assessment using volunteered geographical data
title_full Improving remote sensing flood assessment using volunteered geographical data
title_fullStr Improving remote sensing flood assessment using volunteered geographical data
title_full_unstemmed Improving remote sensing flood assessment using volunteered geographical data
title_sort improving remote sensing flood assessment using volunteered geographical data
publisher Copernicus Publications
series Natural Hazards and Earth System Sciences
issn 1561-8633
1684-9981
publishDate 2013-03-01
description A new methodology for the generation of flood hazard maps is presented fusing remote sensing and volunteered geographical data. Water pixels are identified utilizing a machine learning classification of two Landsat remote sensing scenes, acquired before and during the flooding event as well as a digital elevation model paired with river gage data. A statistical model computes the probability of flooded areas as a function of the number of adjacent pixels classified as water. Volunteered data obtained through Google news, videos and photos are added to modify the contour regions. It is shown that even a small amount of volunteered ground data can dramatically improve results.
url http://www.nat-hazards-earth-syst-sci.net/13/669/2013/nhess-13-669-2013.pdf
work_keys_str_mv AT eschnebele improvingremotesensingfloodassessmentusingvolunteeredgeographicaldata
AT gcervone improvingremotesensingfloodassessmentusingvolunteeredgeographicaldata
_version_ 1716791697618239488

Similar Items