Ozone is one of the six common air pollutants identified by the Environmental Protection Agency (EPA) Clean Air Act. According to EPA, inhaling this can trigger a variety of health problems such COPD, chest pain and coughing which can worsen leading to bronchitis, emphysema, asthma, and even long-term lung damage. This caused more attention to the aforementioned agency.
Moreover, EPA recently changed the surface ozone regulation, reducing the maximum daily 8-hour average threshold from 75 to 70 parts per billion by volume. This sparked significant challenges to U.S. air quality (AQ) forecasters. Hence, Nikolay Balashov, a doctor of meteorology from Penn State, designed a new method to help these AQ forecasters in predicting surface ozone pollution levels for as early as 48-hours ahead through exploring the relationship between air pollutants and meteorological variables.
This method is called regression in self-organizing map (REGiS). It’s designed to weigh and combine statistical air quality models on the basis of predicted weather patterns, further creating probabilistic ozone forecasts. This method doesn’t even require significant computational power!
"If we can predict the level of ozone ahead of time, then it's possible that we can do something to combat it," says Balashov. "Ozone needs sunlight but it also needs other precursors to form in the atmosphere, such as chemicals found in vehicle emissions. Reducing vehicle use (on the days when the weather is conducive to the formation of unhealthy ozone concentrations) will reduce the level of emissions that contribute to higher levels of ozone pollution."
Known methods nowadays are expensive to run and are often not available in developing nations. REGiS, on the other hand, is diversely applicable. It can be used even in countries that lack resources since the method just utilizes statistics, historical weather and air quality data.
While pollution is apparently invincible at this point, it is vital to have rich information that could greatly aid in implementing necessary regulatory systems.