Air pollution is one of the most significant public health issues we face today. There is a broad misconception that air pollution is an issue that only affects developing nations and third world countries, but in reality air pollution affects nearly everyone. Only recently, the World Health Organization claimed that air pollution is the ‘new tobacco,’ with the simple act of breathing killing at least 7 million people a year and harming billions more. The WHO estimates that 9 out of 10 people worldwide are breathing in polluted air, with very few countries taking any significant or meaningful action.
Air pollutants are pervasive and highly toxic. Two of the most harmful pollutants are methane and benzene. They contribute to ozone smog pollution which is particularly harmful to the elderly and children, and can also induce asthma attacks, bronchitis and emphysema. Benzene is also a highly toxic carcinogen.
A challenge to reducing air pollution is that it can be difficult to accurately monitor what is floating around in the air. However, by utilizing advanced IoT sensors, machine learning and low-cost, mobile-enabled sensor technologies, air conditions can be accurately monitored and data can be viewed in real time and analyzed for trends. Today there are a number of innovative solutions being developed that harness these emerging technologies to better understand and ultimately reduce air pollution.
In London, the GSMA teamed up with the Royal Borough of Greenwich to develop a mobile air quality monitoring vehicle named ‘The Smogmobile.’ This was an electric vehicle outfitted with a high tech, air quality lab, driving across the borough and sampling the air quality every minute. The lab was then able to aggregate that data through advanced machine learning algorithms with additional data sets, both real-time and historical, to generate actionable insights.
Through methods like this, city officials can be alerted to localized, high priority air quality issues and take proactive action. For example, if it was found that there were dangerously high levels of pollutants at a particular road intersection, measures could be taken to improve traffic flow by optimizing traffic lights, or by rerouting traffic.
Another example of a city taking action to improve their capacity to monitor air quality is Chicago. A citywide network of sensors, developed with Argonne National Library and the Chicago Department of Innovation and Technology, was deployed on lampposts around the city in 2014. They use a technology called ‘waggle chips,’ which are sensors that monitor the presence of air pollutants including carbon monoxide, nitrogen dioxide, ozone and particulate matter. The city is able to harness the data collected by these sensors to understand patterns which help them to predict and prevent future occurrences, while also using the data to address individual incidents.
One barrier to monitoring air quality in cities is that the required infrastructure has been limited due to the high installation and operational costs of fixed environmental observation stations. However, advances in IoT and sensor technologies have led to the development of lower cost, modular stations that can capture data and transfer it to the cloud in real-time. This also enables air quality data to be applied more easily to additional, related data sets, such as weather and traffic.
An example of this emerging technology is our modular WeatherMesh stations for monitoring and forecasting environmental conditions. WeatherMesh is significantly lower in cost than traditional roadside weather and environmental stations (RWIS), and its modular design enables it to be deployed on existing infrastructure (such as street lights or traffic lights) or with additional sensors (such as air quality).
We recently showcased our WeatherMesh stations at IoT in Action, demonstrating its modular design, gateway application, real-time data dashboards and forecasting capabilities. At the event, Live Earth, a Fathym partner, demonstrated our environmental forecast data fused with multiple data sets. By gaining insight into current weather conditions, pollutants and sources of air quality disruption on a highly localized level, we can better understand how to develop intelligent and informed mitigation strategies.