Similar to forecasting weather, there are models to predict levels of air pollution and air quality. There are many forecast models that require more complexity than weather forecast models. These models are mathematical simulations of how airborne pollutants disperse in the air.1
Why air quality information is needed
Air pollution occurs when the surrounding air contains gases, dust, fumes or odors in high enough quantities to be harmful to the health of humans and animals or enough to cause damage to plants and materials.
Air pollution is one of the great killers of our time. In 2015, polluted air was responsible for 6.4 million deaths worldwide: 2.8 million from household air pollution and 4.2 million from ambient (outdoor) air pollution.2,3 Data from that year shows that air pollution worldwide caused:
- 19% of all cardiovascular deaths
- 24% of ischaemic heart disease deaths
- 21% of stroke deaths
- 23% of lung cancer deaths4
Additionally, outdoor air pollution appears to be an important risk factor for neurodevelopmental disorders in children5 and neurodegenerative diseases in adults6.
With the economic, ecologic and human toll air pollution takes, forecasting technology is an increasingly important endeavor.
Benefits of air pollution information and forecasting
Air pollution forecasting is a worthwhile investment on multiple levels - individual, community, national and global. Accurate forecasting helps people plan ahead, decreasing the effects on health and the costs associated.
If people are aware of variations in the quality of the air they breathe, the effect of pollutants on health as well as concentrations likely to cause adverse effects and actions to curtail pollution. Furthermore, there is a greater likelihood of motivating changes in both individual behaviour and public policy7, as people want air quality information.8
Such awareness has the potential to create a cleaner environment and a healthier population. Governments also make use of early forecasting to establish procedures to reduce the severity of local pollution levels.9
Accuracy in air quality forecasting
When predicting air quality, there are many variables to take into account, some of which are quite unpredictable. For example, Beijing’s authorities sometimes order coal plants and factories to close and ban a portion of the city’s millions of registered vehicles from operating.10
Air pollution levels are strongly correlated with local weather conditions11 and nearby pollution emissions.12 However, long-range transport of pollution - through strong winds - is also a significant influencing factor and must be taken into consideration when forecasting local AQI readings.13
Predicting air quality, therefore, not only involves the difficulties of weather forecasting, it also requires data on and knowledge of:
- Local pollutant concentrations and emissions
- Pollutant concentrations and emissions from distant locations
- Movements and possible transformations of pollutants
- Prevailing winds
The many factors at play in predicting air quality result in air pollution forecasting being both subjective and objective.14
Air quality forecasting techniques
There are many such forecast models, and all require more complexity than weather forecast models. These models are mathematical simulations of how airborne pollutants disperse in the air.
The first step to an accurate air quality forecast is an excellent weather forecast. Meteorological (weather) forecasting can be categorized into three main categories: climatology, statistical methods and three-dimensional (3-D) models.
Climatology is based on the assumption that the past is a good indicator of the future. This method is based on the relationship between specific weather conditions and pollution levels, and therefore can be very one-dimensional. This method is often extended to include the matching of weather patterns to pollution patterns. There are many limitations to this method and it is viewed as a tool to complement other forecasting methods.
The association between air quality and weather patterns can be quantified using statistical methods. The three most commonly used include:
- Classification and regression tree (CART) is designed to classify data into dissimilar groups. Software identifies variables that correlate with ambient pollution levels. The data is used to forecast concentrations based on weather conditions and correlated pollutant concentrations.
- Regression analysis estimates relationships between variables. By analyzing historical data sets, associations are made between pollution levels and meteorological data variables. The result is an equation that can be used to forecast future pollution levels.
- Artificial neural networks use adaptive learning and pattern recognition techniques. Computer-based algorithms are designed to simulate the human brain’s capability for pattern recognition. This is debatably the most suited method for forecasting pollution due to its multi-dimensional approach.
One disadvantage of the above statistical methods is that they assume stability in terms of the processes that affect air quality. Therefore, any drastic changes to emissions or climate (short or long term) will severely diminish the accuracy of these techniques. There are more complex methods that attempt to take these shortfalls into account. They are known as three-dimensional models.
Three-dimensional (3-D) models
Three-dimensional models mathematically represent all the important processes that have an impact on outdoor air pollution levels. Three-dimensional models simulate the emission, transport, and transformation of air pollution by making use of several submodels, including:
- Emission model: Simulates the spatial distribution of emissions from both natural and human sources.
- Meteorological model: Creates a trajectory model to predict the ambient levels of pollution using the 3-D meteorological model and emissions data.
- Chemical model: Looks at the transformation of primary (emitted) pollution into secondary pollution to determine the outcome of the pollutant.15
Pollution forecasting techniques are rapidly improving and will continue increasing in accuracy. Accurate and accessible air pollution forecasts help raise public awareness, allow for sensitive populations to plan ahead, and provide governments with information for public health alerts. This is an exciting new field for researchers and scientists that can provide a promising future.
 Air quality forecasting – How accurate can it be? (2015).
 Forouz M. (2016). Global burden of diseases, injuries, and risk factors study 2015.
 Prüss-Ustün A. (2016). Preventing disease through healthy environments.
 Wang H. (2016). Global, regional, and national life expectancy, all-cause mortality, and cause-specific mortality for 249 causes of death, 1980–2015.
 Grandjean P. (2014). Neurobehavioural effects of developmental toxicity.
 Kioumourtzoglou M. (2016). Long-term PM2.5 exposure and neurological hospital admissions in the northeastern United States.
 Kelly F. (2012). Monitoring air pollution: Use of early warning systems for public health.
 Kelly F. (2015). Air pollution and public health: emerging hazards and improved understanding of risk.
 Dawes S. (2013). Socioeconomic benefits of adding NASA satellite data to AirNow.
 Ye J. (2017). How Beijing’s sky changes before and after major political meetings.
 Baklanov A. (2014). Online coupled regional meteorology chemistry models in Europe: Current status and prospects.
 Andrade M. (2015). Air quality forecasting system for Southeastern Brazil.
 Shumake-Guillemot J. (2014). Air quality and human health, a priority for joint action.
 Air Quality Forecasting Tools. (n.d.).
 Ryan W. (2016). The air quality forecast rote: Recent changes and future challenges.