TY - JOUR

T1 - Extraction of Pluvial Flood Relevant Volunteered Geographic Information (VGI) by Deep Learning from User Generated Texts and Photos

AU - Feng, Yu

AU - Sester, Monika

N1 - Funding information: Acknowledgments: The authors would like to acknowledge the support from BMBF funded research project “EVUS — Real-Time Prediction of Pluvial Floods and Induced Water Contamination in Urban Areas” (BMBF, 03G0846A). We also gratefully acknowledge the support of NVIDIA Corporation with the donation of a GeForce Titan X GPU used for this research. The publication of this article was funded by the Open Access Fund of the Leibniz Universität Hannover.

PY - 2018/2

Y1 - 2018/2

N2 - In recent years, pluvial floods caused by extreme rainfall events have occurred frequently. Especially in urban areas, they lead to serious damages and endanger the citizens' safety. Therefore, real-Time information about such events is desirable. With the increasing popularity of social media platforms, such as Twitter or Instagram, information provided by voluntary users becomes a valuable source for emergency response. Many applications have been built for disaster detection and flood mapping using crowdsourcing. Most of the applications so far have merely used keyword filtering or classical language processing methods to identify disaster relevant documents based on user generated texts. As the reliability of social media information is often under criticism, the precision of information retrieval plays a significant role for further analyses. Thus, in this paper, high quality eyewitnesses of rainfall and flooding events are retrieved from social media by applying deep learning approaches on user generated texts and photos. Subsequently, events are detected through spatiotemporal clustering and visualized together with these high quality eyewitnesses in a web map application. Analyses and case studies are conducted during flooding events in Paris, London and Berlin.

AB - In recent years, pluvial floods caused by extreme rainfall events have occurred frequently. Especially in urban areas, they lead to serious damages and endanger the citizens' safety. Therefore, real-Time information about such events is desirable. With the increasing popularity of social media platforms, such as Twitter or Instagram, information provided by voluntary users becomes a valuable source for emergency response. Many applications have been built for disaster detection and flood mapping using crowdsourcing. Most of the applications so far have merely used keyword filtering or classical language processing methods to identify disaster relevant documents based on user generated texts. As the reliability of social media information is often under criticism, the precision of information retrieval plays a significant role for further analyses. Thus, in this paper, high quality eyewitnesses of rainfall and flooding events are retrieved from social media by applying deep learning approaches on user generated texts and photos. Subsequently, events are detected through spatiotemporal clustering and visualized together with these high quality eyewitnesses in a web map application. Analyses and case studies are conducted during flooding events in Paris, London and Berlin.

KW - Convolutional neural network

KW - Crowdsourcing

KW - Flood mapping

KW - Multimedia information retrieval

KW - Social media

KW - Transfer learning

KW - Volunteered geographic information

KW - Word embedding

UR - http://www.scopus.com/inward/record.url?scp=85043230454&partnerID=8YFLogxK

U2 - 10.3390/ijgi7020039

DO - 10.3390/ijgi7020039

M3 - Article

AN - SCOPUS:85043230454

VL - 7

JO - ISPRS International Journal of Geo-Information

JF - ISPRS International Journal of Geo-Information

SN - 2220-9964

IS - 2

M1 - 39

ER -