Online Program Home
My Program

Abstract Details

Activity Number: 362 - SPEED: Food, Environment, Biomedical Imaging and Physical System Visualization/Learning, Part 2
Type: Contributed
Date/Time: Tuesday, July 30, 2019 : 11:35 AM to 12:20 PM
Sponsor: Quality and Productivity Section
Abstract #307785
Title: Air Pollutant Prediction Using Precipitation
Author(s): Patrick Chang*
Companies: JLS Middle School
Keywords: Pollutant; Precipitation; Correlation; Regression; Prediction; Neural Networks

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 precipitation to predict air pollutants. In this paper, we studied whether we can infer the levels of ozone, Carbon Monoxide, Nitrogen Dioxide, Sulfur Dioxide, PM10 particulates, and lead from precipitation. Regression analysis tools including simple linear regression and nonlinear regression methods such as neural networks are used in this study. First, we studied whether the air pollutant levels could be predicted by precipitation alone. Second, the wind factor was also included for improving air pollutant prediction.

Authors who are presenting talks have a * after their name.

Back to the full JSM 2019 program