The Paris-based Organisation for Economic Co-operation and Development (OECD) released a report earlier this summer that suggests outdoor air pollution caused more than 3 million premature deaths in 2010, with elderly people and children most vulnerable. I've got to believe the untold numbers of homeless youth and adults who live on the streets in urban centers around the world are also incredibly susceptible to ill effects of vehicle exhaust and particulate matter in the air – and the serious heart and lung conditions they can bring on. With the OECD projecting a possible doubling, or even tripling, of premature deaths from dirty air by 2060, public officials should pay close attention to technology solutions like the one described below from Council Associate Partner Siemens. – Philip Bane
As the World Health Organization has pointed out, there are seven million deaths every year from air pollution, yet there are also local measures cities can implement on short notice to mitigate the effects of dirty air.
Enter Dr. Ralph Grothmann from Siemens Corporate Technology (CT). He has developed air pollution forecasting models based on neural networks that can predict the degree of pollution in large urban areas several days in advance.
"Neural networks are computer models that operate like the human brain," Grothmann explains in an article in Pictures of the Future, a Siemens magazine on research and innovation. "Through training, they learn to recognize relationships and to make predictions."
Using London as a testbed
As he developed his forecasting system, Grothmann used the weather and emissions data the city of London collects from some 150 sensor stations located throughout the metro area.
"This data allowed us to train our system," Grothmann explains. "Specifically, we gathered emission measurements for gases such as carbon monoxide, carbon dioxide and nitrogen oxides. We linked the development of these emissions with the weather data from the same period of time, which included factors such as humidity, solar irradiation, cloud cover and temperature."
Recurring events such as workdays and weekends, holidays, trade shows and sports events were also programmed into the model since they affect traffic and emissions in a variety of ways.
The process of "training" the model went through hundreds of iterations as it figured out the effect all of the particular variables.
"Now our system can predict the level of air pollution at 150 places in the city for every hour of the next three days with an error rate of less than 10%," Grothmann says. "Our results also make it possible to infer what the main drivers of the predicted air pollution will be."
How cities can act
Experts say that almost 90% of the world's urban residents breathe air that contains more pollutant emissions than the recommended thresholds. But with the data the forecasting system provides, action can be taken to both reduce levels and exposure.
"For example, if our system predicts above-average pollution levels in certain parts of London for the next two days because of traffic, the city could temporarily raise its congestion charge, block through traffic for trucks in high-impact areas for certain hours, or make it more appealing for people to use local public transit systems," Grothmann says.
There are also smartphone apps and web-based monitoring that can provide citizens with alerts to stay indoors or away from specific areas when heavy pollution is predicted.
You may also be interested in…
How Seattle cut 9,000 tons of carbon emissions (D.C. and San Diego too)
Scientists take smog fighting to the streets
This article is from the Council's Compassionate Cities initiative which highlights how city leaders and other stakeholders can leverage smart technologies to end suffering in their communities and give all citizens a route out of poverty. Click the Compassionate Cities box on our registration page to receive our weekly newsletter.
Connect with #compassionatecities…
See all the latest Compassionate Cities headlines
Follow Managing Director @Philip_Bane on Twitter
Join us on Facebook
Share your insights in our LinkedIn discussion group