When air pollution began to have a significant deleterious effect on human life, it became necessary to discover and understand the links between emission sources and the air quality deterioration and health effects they cause. Only after the impacts of sources have been assessed correctly will it be possible to devise and implement rational, convincing, and effective policies to improve air quality. Over $29 billion were spent in the United States in 1983 on air pollution abatement and control (Council on Environmental Quality 1984). If a fraction of that expense can be saved by better understanding the relation of air quality and health effects to emission sources, the monetary benefits will be tremendous. Knowledge of the relation between emissions by a source and pollutant concentrations in the air at later times and other places (that is, the source/receptor relationship) is essential to calculating the exposure of humans to these pollutants and hence to predicting the health impacts resulting from these source emissions. Mathematical models have evolved as the most practical means to relate source emissions to the subsequent air pollution concentrations.
source: https://www.ncbi.nlm.nih.gov/books/NBK218138/
Predicting air quality is a complex task due to the dynamic nature, volatility, and high variability in time and space of pollutants and particulates. At the same time, being able to model, predict, and monitor air quality is becoming more and more relevant, especially in urban areas, due to the observed critical impact of air pollution on citizens’ health and the environment. In this paper, we employ a popular machine learning method, support vector regression (SVR), to forecast pollutant and particulate levels and to predict the air quality index (AQI). Among the various tested alternatives, radial basis function (RBF) was the type of kernel that allowed SVR to obtain the most accurate predictions. Using the whole set of available variables revealed a more successful strategy than selecting features using principal component analysis.
source: Article A Machine Learning Approach to Predict Air Quality in California
Dear friend Eduard Babulak
I loved this question. It could be a good discussion topic, so recommend you consider the possibility.
There are several mathematical tools that can be used to model and simulate real-time nonlinear dynamic air pollution and its potential impact on health. Some of these tools include:
1. Computational Fluid Dynamics (CFD): This tool can be used to simulate the dispersion and transport of air pollutants in the atmosphere.
2. Chemical Transport Models (CTMs): These models can be used to simulate the chemical reactions and transformations of air pollutants in the atmosphere.
3. Statistical models: These models can be used to analyze the relationships between air pollutant concentrations and health outcomes.
4. Machine learning algorithms: These algorithms can be used to forecast pollutant levels and predict the air quality index (AQI).
5. multi-pollutant models: These models can be used to simulate the interactions between different air pollutants and their combined impact on health.
The choice of the most effective mathematical tool depends on the specific research question and the availability of data. In general, a combination of different tools and approaches may be needed to accurately model and simulate real-time nonlinear dynamic air pollution and its potential impact on health.
- Badges
- Science topic
- Similar topics
- Biological Science
- Biochemistry
- Biochemical Techniques
- Analytical Chemistry
- pH