Air pollution prediction in context of supervised machine learning and time series model

Xiaoyang Feng

doi:10.1117/12.2672662

28 March 2023 Air pollution prediction in context of supervised machine learning and time series model

Xiaoyang Feng

Proceedings Volume 12597, Second International Conference on Statistics, Applied Mathematics, and Computing Science (CSAMCS 2022); 125973I (2023) https://doi.org/10.1117/12.2672662
Event: Second International Conference on Statistics, Applied Mathematics, and Computing Science (CSAMCS 2022), 2022, Nanjing, China

Abstract

Air pollution refers to the release of pollutants into the atmosphere that is harmful to human beings and even the entire planet. It can be labeled as one of the most dangerous threats that humanity ever faced. As society progresses, the population surges rapidly accompanied by energy consumption increasement. Globally, especially in some developing countries, factory exhaust and tail gas emissions have also risen, causing more toxic pollution. In this case, it is possible to investigate air quality conditions and predict future trends based on machine learning methods. On this basis, scientific prevention suggestions can be provided for environmental monitoring departments to effectively control air pollution, prevent residents from being exposed to noxious pollutants, and alleviate global warming. This paper applies regression models, classification models, and time series models to predict the trend of air quality index through the content of chemical components in the atmosphere. According to the analysis, random forest regression and LSTM perform best in predicting AQI in India, whose R² is 0.906 with accuracy 97.3%. The outcomes have a certain reference value to improve the accuracy of air quality prediction.

Citation Download Citation

Xiaoyang Feng "Air pollution prediction in context of supervised machine learning and time series model", Proc. SPIE 12597, Second International Conference on Statistics, Applied Mathematics, and Computing Science (CSAMCS 2022), 125973I (28 March 2023); https://doi.org/10.1117/12.2672662

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available