Air quality in Chinese cities rank among the worst in the globe due to fossil fuel demand from rapid industrialization. Beijing, China’s capital city, is no exception, with heavy smog that reduces visibility and causes health issues. The cycle of ozone and particulate levels in Beijing offer insight into past, present, and future air quality.
Ozone levels are highest in summer and lowest in winter: the opposite is true for particulate levels. As a result, both time series have a cyclical nature, allowing future levels to be predicted with relative accuracy. The autoregressive integrated moving average model, otherwise known as the ARIMA model, allows for forecasting and understanding of time series data, making it the model of choice for this project.
The implications of this project are vast: scientists can use the model to better understand how ozone and particulate levels rise and fall in Beijing, and use the model to predict such levels in the future, allowing for better environmental policy.
Additional Items: N/A
Developer(s): Matthew Lee, San Marino High School, Participant, Global IoT Datathon hosted by Terbine
Data Feeds Employed:
Open Source Tools:
Original Posting Date: 10 September 2020