Twitter + Citizen Science + AI = improved flood data collection

December 25, 2017 by Grant Hill, University of Dundee
Credit: CC0 Public Domain

Researchers from the University of Dundee are combining Twitter, citizen science and cutting-edge artificial intelligence (AI) techniques to develop an early-warning system for flood-prone communities.

Dr. Roger Wang and his colleagues from the University's School of Science and Engineering have shown how AI can be used to extract data from Twitter and crowdsourced information from mobile phone apps to build up hyper-resolution monitoring of urban flooding. They believe this is the first time that Computer Vision has been applied to flooding issues.

Urban flooding is difficult to monitor due to complexities in data collection and processing. This prevents detailed risk analysis, flooding control, and the validation of numerical models. The Dundee team set about trying to solve this problem by exploring how the latest AI technology can be used to mine social media and apps for the data that users provide.

They found that social media and crowdsourcing can be used to complement datasets based on traditional remote sensing and witness reports. Applying these methods in case studies, they found these methods to be genuinely informative and that AI can play a key role in future flood warning and monitoring systems.

Dr. Wang said, "Sea levels have been rising at an average rate of 3.4mm a year over the past decade. The extremes of today will become the average of the future so coastal cities and countries must take action to protect their land.

"We were particularly interested in the increased incidence of what we call sunny day flooding – flooding that occurs in the absence of any extreme weather event due to the mean sea level being higher.

"The present recording systems – remote satellite sensors, a local sensor network, witness statements and insurance reports – all have their disadvantages. Therefore we were forced to think outside the box and one of the things that occurred to us was how Twitter users provide real-time commentary on floods.

"A tweet can be very informative in terms of flooding data. Key words were our first filter, then we used natural language processing to find out more about severity, location and other information. Computer vision techniques were applied to the data collected from MyCoast, a crowdsourcing app, to automatically identify scenes of flooding from the images that users post.

"We found these big data-based flood monitoring approaches can definitely complement the existing means of and demonstrate great promise for improving monitoring and warnings in future."

Twitter data was streamed over a one-month period in 2015, with the filtering keywords of 'flood', 'inundation', 'dam', 'dike', and 'levee'. More than 7500 tweets were analysed over this time.

MyCoast is a system used by a number of environmental agencies to collect '' data about various coastal hazards or incidents. The system currently contains over 6000 flood photographs, all of which were collected through the mobile app.

The information extracted by AI tools was validated against precipitation data and road closure reports to examine the quality of the data. Flood-related tweets were shown to correlate to precipitation levels, while the crowdsourced data matched strongly with the road closure reports.

The researchers believe a tool like Twitter is more useful for large-scale, inexpensive monitoring, while the crowdsourced data provides rich and customised information at the micro level.

"Computer vision techniques require further refinement to improve recognition of flood situations rather than standard coastal scenes or other environments featuring water," continued Dr. Wang. "We have reached the point of 70% accuracy and we are using the thousands of images available on MyCoast to further improve this.

"Taken together, these tools can be used to monitor the water penetration of urban flooding over a city. This can be then used to improve forecasting models and early warning systems to help residents and authorities prepare for an upcoming flood.

"By combining , citizen science and artificial intelligence in urban flooding research, we hope to generate accurate predictions and provide warnings days in advance."

The research is published in the latest edition of the journal Computers & Geosciences.

Explore further: The continental U.S. is experiencing more flooding, and earlier in the year

Related Stories

New flood risk identified by FIU researcher

December 14, 2017

As South Florida raises groundwater levels to fight salt water intrusion, the threat of flooding from within will only increase, according to Florida International University research.

'King tides' are rising, so groups span globe to monitor it

December 12, 2017

The tide watchers start patrolling whenever the celestial forces align. From coast to coast, hundreds of tide watchers come out with their cameras to record the latest "king tides," brief episodes of tidal flooding that could ...

Scientists counter threat of flooding on coral reef coasts

November 23, 2017

Scientists have developed a computer simulation tool to predict short-term flood hazards on coral-reef-lined coasts and to assess longer-term impacts from climate change. The assessments will give input to estimate societal ...

Recommended for you

Fish-inspired material changes color using nanocolumns

March 20, 2019

Inspired by the flashing colors of the neon tetra fish, researchers have developed a technique for changing the color of a material by manipulating the orientation of nanostructured columns in the material.

Researchers shed new light on the origins of modern humans

March 20, 2019

Researchers from the University of Huddersfield, with colleagues from the University of Cambridge and the University of Minho in Braga, have been using a genetic approach to tackle one of the most intractable questions of ...

One transistor for all purposes

March 20, 2019

In mobiles, fridges, planes – transistors are everywhere. But they often operate only within a restricted current range. LMU physicists have now developed an organic transistor that functions perfectly under both low and ...


Please sign in to add a comment. Registration is free, and takes less than a minute. Read more

Click here to reset your password.
Sign in to get notified via email when new comments are made.