2018
DOI: 10.1016/j.cageo.2017.11.008
|View full text |Cite
|
Sign up to set email alerts
|

Hyper-resolution monitoring of urban flooding with social media and crowdsourcing data

Abstract: Hyper-resolution datasets for urban flooding are rare. This problem prevents detailed flooding risk analysis, urban flooding control, and the validation of hyper-resolution numerical models. We employed social media and crowdsourcing data to address this issue. Natural Language Processing and Computer Vision techniques are applied to the data collected from Twitter and MyCoast (a crowdsourcing app). We found these big data based flood monitoring approaches can complement the existing means of flood data collec… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1
1

Citation Types

0
113
0
2

Year Published

2018
2018
2022
2022

Publication Types

Select...
6
3
1

Relationship

0
10

Authors

Journals

citations
Cited by 168 publications
(115 citation statements)
references
References 15 publications
0
113
0
2
Order By: Relevance
“…Examples include the development of accessibility mapping for people with disabilities, water quantity estimation, and estimation of inundated areas. An example where citizens are used as the only data generation agent but both data types are used is where citizen observations transmitted through a dedicated mobile app and Twitter are integrated to show flood extent and water level to assist with disaster management (Wang et al, ).…”
Section: Review Of Crowdsourcing Data Acquisition Methods Usedmentioning
confidence: 99%
“…Examples include the development of accessibility mapping for people with disabilities, water quantity estimation, and estimation of inundated areas. An example where citizens are used as the only data generation agent but both data types are used is where citizen observations transmitted through a dedicated mobile app and Twitter are integrated to show flood extent and water level to assist with disaster management (Wang et al, ).…”
Section: Review Of Crowdsourcing Data Acquisition Methods Usedmentioning
confidence: 99%
“…Previous research has shown that flood extent can be mapped from flood photos by consulting with a DEM (e.g., Gallien et al, 2011), and automation of this process in accordance with the location, orientation, and magnification of photos is needed for real-time NF monitoring based on photographs posted to social media. Social media has emerged as an important platform for two-way communication about flooding between authorities and community members (Feldman et al, 2016;Le Coz et al, 2016;Palen & Hughes, 2018) and can be used to gather information around the severity of floods (Fohringer et al, 2015;Smith et al, 2017;Wang et al, 2018). Flood monitoring efforts have also explored combining social media with remote sensing and unmanned aerial vehicle data (Rosser et al, 2017), although these efforts have been mainly focused on extreme events (Kogan et al, 2015;Middleton et al, 2014).…”
Section: Nf Monitoringmentioning
confidence: 99%
“…In urban areas, the wide availability of smart phones, digital photos and social media provides an opportunity to obtain flood-related information where direct measurements are not available (René et al, 2015), which can support model verification. For example, platforms such as Twitter or crowd-sourcing web portals now carry a wealth of information regarding on-going or past flood events (Smith and Liang, 2013;Wang et al, 2018;Yu et al, 2016). However, most of the applications can only underpin the locations and timing of flooding, and require human labour to extract flood depth or extent information (Fohringer et al, 2015).…”
Section: Introductionmentioning
confidence: 99%