Big Data of Urban Flooding: Dance with Social Media, Crowdsourcing Data and Artificial Intelligence

Our first big data paper has been published online at Hyper-resolution monitoring of urban flooding with social media and crowdsourcing data

To our knowledge, this is the first paper in the world using computer vision to extract urban flooding data from crowdsourcing photos collected from Smart Phone Apps.

Some highlights:

  • Social media and crowdsourcing can be used to create hyper-resolution flood data.
  • Flood-related tweet volume is found linearly correlated to precipitation departure.
  • Tweet data points are found clustered the most at the metropolitan scale.
  • Crowdsourcing flood photos are processed by computer vision algorithm.
    Recommendations are given to improve the big data based flood monitoring.

Leave a Reply

Your email address will not be published. Required fields are marked *

This site uses Akismet to reduce spam. Learn how your comment data is processed.