Twitter helps map Mumbai floods

Popular social media platform Twitter is reportedly being used to map monsoon floods in Mumbai, India. In this brand new initiative by the Climate Research Department of the Indian Institute of Technology, keywords used in tweets by the local community will be used to map severely flooded areas.

When monsoon rains inundate Mumbai each year, residents of India’s financial hub find their social media feeds flooded with flood memes, from Venetian gondolas navigating the city’s flooded streets to office workers traveling on inflatable boats .

This year, a research institute is hoping that social media can play a more practical role – asking residents to post details of flooding in their neighborhoods and using the data to issue geo-specific flood warnings in real time.

“Since we cannot monitor the floods in the city on our own, we decided to take the community’s help,” said Subimal Ghosh, head of climate research at the Indian Institute of Technology, Bombay, who is behind the initiative.

The IIT-Bombay project, launched in June just before the monsoons, will use digital elevation maps that show the area’s height above sea level, spatial data on rainfall along with tweets from local residents.

Tweets noting “ankle-deep” or “knee-deep” water, for example, will be collected by Twitter using an automated system that will try to extract information about flood depth and location from them.

This will be used to provide real-time flood information for the entire city, which will be published on a portal.

“For example, which areas need water pumping first, how can traffic be controlled and how can people get home?” Ghosh said. “The city needs a resilience plan,” he told the Thomson Reuters Foundation.

Around the world in countries including Australia and Indonesia, climate researchers are increasingly using data collected through social media to help monitor weather events such as floods.

They say the data can be used to improve emergency response and rescue efforts and to make more accurate forecasting, which will become even more important as climate change fuels extreme weather.

“We need participatory models for climate adaptation as we will be affected by more extreme rainfall in the near future. We will be able to show floods in real time like Google Maps shows red for traffic,” Ghosh said.

India’s financial capital, which sits on the coast of the Arabian Sea, has recorded “extreme” rainfall — defined as more than 200 mm (7.9 inches) of rain in 24 hours — about a dozen times between 2017 and 2021. show civil data.

This is double the number of similar events in the previous five-year period.

AI disaster bots

Similar projects elsewhere have shown how local people can play a role in preparing flood responses or alerts.

When flooding hit Australia’s east coast this year, submerging entire cities, Brisbane-based technology company FloodMapps posted a series of flood maps on its social media accounts, mainly Twitter.

The posts prompted some people to post similar maps of other areas. Others submitted photos of the areas depicted, helping to visualize what the maps show, a FloodMapps spokesperson said.

“People contacted others to warn them of flood conditions,” the spokesman added in emailed comments.

In one case, a business owner was able to warn his employees to stay home after seeing the card along with a photo from a neighbor, the company said.

In Indonesia, a local website founded about a decade ago, PetaBencana.id (which stands for disaster map), uses artificial intelligence (AI) and bots to map disasters in real time.

The award-winning platform asks people to verify their social media posts with geotagged photos and then combines official data to build up-to-date online flood maps that “have been used by millions of residents,” platform founder Nashin Mahtani said recently.

Low-income neighborhoods

South and East Asia are home to nearly 1.36 billion of the 1.46 billion people at risk of flooding worldwide, with India and China accounting for a third of them, according to the World Bank.

Low-income neighborhoods are more affected by flooding, especially in cities like Mumbai, which have large populations living in informal settlements, the World Bank report said, citing poor drainage and land-use planning as key factors.

While the city launched a flood forecasting system two years ago and installed massive drainage pumps in low-lying areas, storm-related disasters such as building collapses and landslides are common in monsoon months, researchers said.

Floods have hit Bangladesh and northeastern India in recent weeks, killing more than 25 people in the Indian state of Assam and leaving millions stranded with little food and drinking water in both countries.

“Floods are an inevitable reality and what we are unable to do is minimize the damage caused by floods,” said Prasoon Singh, head of the Center for Global Environment Studies at the New Delhi-based Energy and Resources Institute ( TERI).

“(But) crowdsourcing information can confirm forecasts, help adjust forecasts and improve relief and rescue operations,” he said, adding that information collected on social media can also be fed into arrays of historical data.

In the short term, Ghosh said he hopes the Mumbai project will help the city’s residents go about their daily business — even during the monsoon season.

“My daughter was at school when it started to rain heavily and buses were stuck on flooded roads. All the parents were worried and we did not know how to reach the school through waterlogged roads,” he said. “Real-time information is important.”