|
Abstract:
|
Elevated air pollutants impact human health in various ways. Ozone, Nitrogen Dioxide, Sulfur Dioxide, and PM10 can aggravate symptoms of pre-existing lung diseases. Carbon Monoxide is potentially lethal. Younger children exposed to lead are subject to lowered IQ and mental issues. Hence, an efficient air pollutant prediction system is key to public health.It is believed that air pollutant levels are affected by the amount of precipitation. For example, levels of pollutants will decrease when precipitation increases. By studying the relationship between precipitation and air pollutants, scientists may save time and money by only measuring one of the factors to predict the other. In this paper, we plan to study whether we can infer the levels of ozone, Carbon Monoxide, Nitrogen Dioxide, Sulfur Dioxide, PM10 particulates, and lead from average daily and weekly precipitation. First, we shall test the null hypothesis that assumes air pollutant levels are correlated to precipitation. Second, JMP Regression analysis tools including simple linear regression and nonlinear regression methods such as neural networks will be used and compared to predict air pollutant levels from precipitation.
|
