Saturday November 17, 2018
Home Lead Story With the aid ...

With the aid of Twitter and AI, researchers to develop flood warning system

In a study, published in the journal Computers & Geosciences, the researchers showed 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.

0
//
AI can play a key role in future flood warning and monitoring systems
AI can play a key role in future flood warning and monitoring systems
Republish
Reprint

London, Dec 26: Researchers are combining Twitter, citizen science and artificial intelligence (AI) techniques to develop an early-warning system for flood-prone communities in urban areas.

In a study, published in the journal Computers & Geosciences, the researchers showed 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.

“By combining social media, citizen science and artificial intelligence in urban flooding research, we hope to generate accurate predictions and provide warnings days in advance,” said Roger Wang from University of Dundee in Britain.

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 research 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 them to be genuinely informative and that AI can play a key role in future flood warning and monitoring systems.

“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,” Wang said.

“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,” Wang said.

The researchers applied computer vision techniques 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 data collection and demonstrate great promise for improving monitoring and warnings in future,” Wang said.

Twitter data was streamed over a one-month period in 2015, with the filtering keywords of “flood”, “inundation”, “dam”, “dike”, and “levee”. More than 7,500 tweets were analysed over this time.

“We have reached the point of 70 per cent accuracy and we are using the thousands of images available on MyCoast to further improve this,” Wang said.

Click here for reuse options!
Copyright 2017 NewsGram

Next Story

Refugee Communities Can Be Built By Tech Industries

Mikkelsen said the initiative was a win-win as it would also benefit companies by slashing costs.

0
Refugees
Congolese families sit at the Kyangwali refugee settlement camp, Uganda, March 19, 2018. A California company is testing an app in Uganda that lets refugees earn money for AI training. VOA

Companies could help refugees rebuild their lives by paying them to boost artificial intelligence (AI) using their phones and giving them digital skills, a tech nonprofit said Thursday.

REFUNITE has developed an app, LevelApp, which is being piloted in Uganda to allow people who have been uprooted by conflict to earn instant money by “training” algorithms for AI.

Wars, persecution and other violence have uprooted a record 68.5 million people, according to the U.N. refugee agency.

People forced to flee their homes lose their livelihoods and struggle to create a source of income, REFUNITE co-chief executive Chris Mikkelsen told the Trust Conference in London.

Rohingya, Myanmar, refugees
Rohingya refugees cross floodwaters at Thangkhali refugee camp in Bangladesh’s Cox’s Bazar district. VOA

“This provides refugees with a foothold in the global gig economy,” he told the Thomson Reuters Foundation’s two-day event, which focuses on a host of human rights issues.

$20 a day for AI work

A refugee in Uganda currently earning $1.25 a day doing basic tasks or menial jobs could make up to $20 a day doing simple AI labeling work on their phones, Mikkelsen said.

REFUNITE says the app could be particularly beneficial for women as the work can be done from the home and is more lucrative than traditional sources of income such as crafts.

The cash could enable refugees to buy livestock, educate children and access health care, leaving them less dependant on aid and helping them recover faster, according to Mikkelsen.

Rohingya, Myanmar, refugees
Rohingya refugee women wait outside of a medical center at Jamtoli camp in Cox’s Bazar, Bangladesh. VOA

The work would also allow them to build digital skills they could take with them when they returned home, REFUNITE says.

“This would give them the ability to rebuild a life … and the dignity of no longer having to rely solely on charity,” Mikkelsen told the Thomson Reuters Foundation.

Teaching the machines

AI is the development of computer systems that can perform tasks that normally require human intelligence.

It is being used in a vast array of products from driverless cars to agricultural robots that can identify and eradicate weeds and computers able to identify cancers.

Refugees
In this Aug. 27, 1994 file photo, U.S. Coast Guard crew from the cutter Staten Island are hindered by rough seas in the Florida Straits as they attempt to rescue Cuban refugees. VOA

In order to “teach” machines to mimic human intelligence, people must repeatedly label images and other data until the algorithm can detect patterns without human intervention.

REFUNITE, based in California, is testing the app in Uganda where it has launched a pilot project involving 5,000 refugees, mainly form South Sudan and Democratic Republic of Congo. It hopes to scale up to 25,000 refugees within two years.

Also Read: Rohingyas Repatriation to Myanmar Scrapped by Bangladesh

Mikkelsen said the initiative was a win-win as it would also benefit companies by slashing costs.

Another tech company, DeepBrain Chain, has committed to paying 200 refugees for a test period of six months, he said. (VOA)