Air quality data is invaluable, for example, for urban planning and mitigating the adverse health effects of air pollution.
The World Health Organization (WHO) has estimated that air pollution is annually to blame for approximately seven million deaths worldwide. While fixed air quality monitoring stations are capable of producing reliable data, they do so by means of expensive technologies – a fact that has limited the geographical and temporal availability of such data.
“Low-cost sensors could be installed, for example, in offices or public transport,” envisioned Martha Arbayani Zaidan, a postdoctoral researcher at the University of Helsinki’s Institute for Atmospheric and Earth System Research.
“The masses of data accumulated through the sensors would benefit research focused on population health urban planning and environmental research.”
Low-cost tech solutions
Earlier low-cost solutions, however, have failed to produce data that is of high enough quality that it can be used without comparing or calibrating it to that produced by fixed stations. The research team overcame the problem by combining low-cost sensors with technological solutions that automatically adjust measuring accuracy by means of artificial intelligence and mathematical models known as virtual sensors.
“The mathematical models we employ make it possible to, for example, estimate black carbon concentrations in the environment,” told Zaidan.
The technique has been tested in prototype form by comparing its results to those of two fixed monitoring stations in Helsinki, one of which is operated by Helsinki Region Environmental Services Authority and the other jointly by the Finnish Meteorological Institute and the University of Helsinki.
While the early results have been promising, the research must solve issues related to connectivity and energy harvesting before the solution is ready for real-world deployment.