A global database of historic and real-time flood events based on social media

Jens de Bruijn, Hans de Moel, Brenden Jongman, Marleen de Ruiter, Jurjen Wagemaker, J.C.J.H. Aerts

Research output: Contribution to JournalArticleAcademicpeer-review

Abstract

Early event detection and response can significantly reduce the societal impact of floods. Currently, early warning systems rely on gauges, radar data, models and informal local sources. However, the scope and reliability of these systems are limited. Recently, the use of social media for detecting disasters has shown promising results, especially for earthquakes. Here, we present a new database for detecting floods in real-time on a global scale using Twitter. The method was developed using 88 million tweets, from which we derived over 10,000 flood events (i.e., flooding occurring in a country or first order administrative subdivision) across 176 countries in 11 languages in just over four years. Using strict parameters, validation shows that approximately 90% of the events were correctly detected. In countries where the first official language is included, our algorithm detected 63% of events in NatCatSERVICE disaster database at admin 1 level. Moreover, a large number of flood events not included in NatCatSERVICE were detected. All results are publicly available on www.globalfloodmonitor.org.
Original languageEnglish
Article number311
Number of pages1
JournalScientific Data
Volume6
Issue number1
DOIs
Publication statusPublished - 9 Dec 2019

Fingerprint

Social Media
social media
natural disaster
Real-time
event
Disaster
Disasters
disaster
Event Detection
Early Warning
Alarm systems
Flooding
early warning system
Earthquake
Subdivision
official language
Data Model
Radar
twitter
Gages

Cite this

@article{38f8d9eee77e4e44a07d104592966887,
title = "A global database of historic and real-time flood events based on social media",
abstract = "Early event detection and response can significantly reduce the societal impact of floods. Currently, early warning systems rely on gauges, radar data, models and informal local sources. However, the scope and reliability of these systems are limited. Recently, the use of social media for detecting disasters has shown promising results, especially for earthquakes. Here, we present a new database for detecting floods in real-time on a global scale using Twitter. The method was developed using 88 million tweets, from which we derived over 10,000 flood events (i.e., flooding occurring in a country or first order administrative subdivision) across 176 countries in 11 languages in just over four years. Using strict parameters, validation shows that approximately 90{\%} of the events were correctly detected. In countries where the first official language is included, our algorithm detected 63{\%} of events in NatCatSERVICE disaster database at admin 1 level. Moreover, a large number of flood events not included in NatCatSERVICE were detected. All results are publicly available on www.globalfloodmonitor.org.",
author = "{de Bruijn}, Jens and {de Moel}, Hans and Brenden Jongman and {de Ruiter}, Marleen and Jurjen Wagemaker and J.C.J.H. Aerts",
year = "2019",
month = "12",
day = "9",
doi = "https://doi.org/10.1038/s41597-019-0326-9",
language = "English",
volume = "6",
journal = "Scientific Data",
issn = "2052-4463",
publisher = "Nature Publishing Group",
number = "1",

}

A global database of historic and real-time flood events based on social media. / de Bruijn, Jens; de Moel, Hans; Jongman, Brenden; de Ruiter, Marleen; Wagemaker, Jurjen; Aerts, J.C.J.H.

In: Scientific Data, Vol. 6, No. 1, 311, 09.12.2019.

Research output: Contribution to JournalArticleAcademicpeer-review

TY - JOUR

T1 - A global database of historic and real-time flood events based on social media

AU - de Bruijn, Jens

AU - de Moel, Hans

AU - Jongman, Brenden

AU - de Ruiter, Marleen

AU - Wagemaker, Jurjen

AU - Aerts, J.C.J.H.

PY - 2019/12/9

Y1 - 2019/12/9

N2 - Early event detection and response can significantly reduce the societal impact of floods. Currently, early warning systems rely on gauges, radar data, models and informal local sources. However, the scope and reliability of these systems are limited. Recently, the use of social media for detecting disasters has shown promising results, especially for earthquakes. Here, we present a new database for detecting floods in real-time on a global scale using Twitter. The method was developed using 88 million tweets, from which we derived over 10,000 flood events (i.e., flooding occurring in a country or first order administrative subdivision) across 176 countries in 11 languages in just over four years. Using strict parameters, validation shows that approximately 90% of the events were correctly detected. In countries where the first official language is included, our algorithm detected 63% of events in NatCatSERVICE disaster database at admin 1 level. Moreover, a large number of flood events not included in NatCatSERVICE were detected. All results are publicly available on www.globalfloodmonitor.org.

AB - Early event detection and response can significantly reduce the societal impact of floods. Currently, early warning systems rely on gauges, radar data, models and informal local sources. However, the scope and reliability of these systems are limited. Recently, the use of social media for detecting disasters has shown promising results, especially for earthquakes. Here, we present a new database for detecting floods in real-time on a global scale using Twitter. The method was developed using 88 million tweets, from which we derived over 10,000 flood events (i.e., flooding occurring in a country or first order administrative subdivision) across 176 countries in 11 languages in just over four years. Using strict parameters, validation shows that approximately 90% of the events were correctly detected. In countries where the first official language is included, our algorithm detected 63% of events in NatCatSERVICE disaster database at admin 1 level. Moreover, a large number of flood events not included in NatCatSERVICE were detected. All results are publicly available on www.globalfloodmonitor.org.

UR - http://www.scopus.com/inward/record.url?scp=85076339912&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85076339912&partnerID=8YFLogxK

U2 - https://doi.org/10.1038/s41597-019-0326-9

DO - https://doi.org/10.1038/s41597-019-0326-9

M3 - Article

VL - 6

JO - Scientific Data

JF - Scientific Data

SN - 2052-4463

IS - 1

M1 - 311

ER -