Is it safe to breathe today? In cities such as Singapore, Beijing and New Delhi, where air pollution can reach dangerous levels, this question has become part of everyday life.
A project called 聽is using artificial intelligence to find clarity amid the smog. The app, built by a team at Nanyang Technological University in Singapore, will estimate air quality by analysing large numbers of photos of the city.
Advertisement
Air sensors can be expensive to install, says Pan Zhengxiang, a graduate student who was inspired to create the app from his time fighting forest fires for the air force. A smartphone app provides the opportunity for a low-cost solution 鈥� particularly in a country such as Singapore, which has one of the world鈥檚 highest levels of smartphone ownership per capita.
AirTick will collect photos in bulk for any city it wants to track, recording when and where each was taken and the positioning of the camera. Those images will be checked against official air-quality data. The information will be used to train a machine-learning algorithm, which will learn to estimate the level of pollutants in the air solely on the basis of evidence from photos.
The idea is to gradually improve the algorithm so that the general public can eventually obtain accurate real-time estimates of the air quality in their neighbourhood. Smartphone cameras will act as a proxy for air-pollution sensors, which are less common. 鈥淎ny camera-enabled mobile device installed with AirTick can become an air-quality sensor,鈥� says Zhengxiang.
A study with the prototype app took place with 100 users in November, and the group hopes to roll it out to the public this year. The project will be presented this month at the AAAI Conference on Artificial Intelligence in Phoenix, Arizona.
Dirty air
Air pollution is a serious problem in South and East Asia. Schools and factories are shut down on days when pollutants reach dangerous levels. The World Health Organization 聽that one in eight deaths worldwide are caused by air pollution every year.
A smartphone tool could be valuable for people with extra concerns about going outside on smoggy days, such as those with a respiratory disease or young children, says , a computer scientist at the University of Rochester in New York. Last year, his group 聽to sort photos taken at Beijing tourist attractions by haze levels.
鈥淚f we want to know right now, right here what the air quality really is, then we can鈥檛 rely on the sensors. There just aren鈥檛 that many of them,鈥� Luo says. 鈥淲ith programmes like this, people could make a better decision for themselves based on where they are.鈥�
