Skip to Content
MIT News feature

Mapping Air

Romain Lacombe, SM ’08, wants to help people find clean air—and generate data we can use.
Jan Buchczik

Romain Lacombe, SM ’08, was training for the Paris Marathon in 2014 when he began to wonder if huffing through the city’s streets might be harmful to his health. Lacombe, a Technology and Policy Program alum who was then working on the French prime minister’s task force on open data, looked for air-quality information and hit a familiar wall: the available data wasn’t standardized or readily usable. So he teamed up with college friend David Lissmyr, a new father worried about his son’s exposure to pollution, and founded Plume Labs with the goal of making it easy to access—and act on—air-quality data.

The company collected and standardized publicly available data from 12,000 governmental sources. It then built forecasting models that allow it to provide daily and hourly air-quality projections for cities in 65 countries—and now, with the recent addition of satellite data, for most of the world’s cities—through its free Plume Air Report app.

This summer the Paris-based startup will launch Flow, a smart personal air-quality tracker that displays real-time readings of ambient pollution levels while also pouring data into the app. That crowdsourced data will be used to help model air quality hourly at the street level for Flow users. The device, which is the size of a candy bar, attaches to a bag or bicycle and draws air in through a constellation of tiny holes. Flow’s array of sensors measure three kinds of pollutants: fine and coarse particulate matter, nitrogen dioxide, and volatile organic compounds.

With Flow and the app, Plume aims to make managing pollution exposure as simple as tallying steps with a Fitbit, Lacombe says. Armed with real-time information and in-app recommendations, users could change their route to avoid a pollution hot spot or schedule a run or an outing with kids for a time when air quality is best. 

In a market full of personal fitness trackers, Lacombe sees a need for an environmental health tracker. A 2013 MIT study found that pollution from U.S. automobiles kills more people than car accidents, some 53,000 per year—and the World Health Organization attributes seven million premature deaths per year to air pollution. Other personal trackers on the market measure only one or two pollutants.

Plume calibrated and tweaked Flow’s tiny sensors by testing them in a variety of weather conditions against meteorological instruments that detect pollutants at concentrations of less than one part per billion. While Flow is less precise, it will be able to measure pollutants accurately enough to gauge exposure in relation to the World Health Organization’s hourly, daily, and annual guidelines.

Flow, a personal air-quality tracker developed by Plume Labs, measures fine and coarse particulate matter, nitrogen dioxide, and volatile organic compounds.

Getting consumers excited about air quality required creativity. “It’s probably the least sexy problem area we can think of,” Lacombe says. But with the help of a flock of pigeons carrying air-sensor backpacks, Plume tweeted pollution data from the skies over London. That prompted 100 (human) Londoners to volunteer for a three-month Flow beta test that generated half a million air-quality data points over 1,300 miles of sidewalks.

Lacombe, who was named a 2018 TED Fellow, hopes Flow will help people create healthier routines and, ultimately, influence policy. “If it can be a spark that helps a local school start thinking ‘Can we stop idling with cars dropping kids in front of the school every morning?’” he says, “that could be a win.”

Keep Reading

Most Popular

Large language models can do jaw-dropping things. But nobody knows exactly why.

And that's a problem. Figuring it out is one of the biggest scientific puzzles of our time and a crucial step towards controlling more powerful future models.

The problem with plug-in hybrids? Their drivers.

Plug-in hybrids are often sold as a transition to EVs, but new data from Europe shows we’re still underestimating the emissions they produce.

Google DeepMind’s new generative model makes Super Mario–like games from scratch

Genie learns how to control games by watching hours and hours of video. It could help train next-gen robots too.

How scientists traced a mysterious covid case back to six toilets

When wastewater surveillance turns into a hunt for a single infected individual, the ethics get tricky.

Stay connected

Illustration by Rose Wong

Get the latest updates from
MIT Technology Review

Discover special offers, top stories, upcoming events, and more.

Thank you for submitting your email!

Explore more newsletters

It looks like something went wrong.

We’re having trouble saving your preferences. Try refreshing this page and updating them one more time. If you continue to get this message, reach out to us at with a list of newsletters you’d like to receive.