Analysis of environmental factors of PM2.5 concentration in China based on feature selection and label construction

Ziyi Pan; Meili Liu; Chun-Te Lee; Jeng-Eng Lin

doi:10.1117/12.2619726

9 December 2021 Analysis of environmental factors of PM2.5 concentration in China based on feature selection and label construction

Ziyi Pan, Meili Liu, Chun-Te Lee, Jeng-Eng Lin

Author Affiliations +

Proceedings Volume 12030, Third International Conference on Optoelectronic Science and Materials (ICOSM 2021); 120301P (2021) https://doi.org/10.1117/12.2619726
Event: Third International Conference on Optoelectronic Science and Materials (ICOSM 2021), 2021, Hefei, China

Abstract

PM2.5 is the main cause of air pollution and hinders the sustainable development of Chinese cities. Researchers have used a variety of methods including regression analysis to find factors that affect PM2.5, but feature selection is rarely used, and there are few standard methods that can solve the problem of label learning in small data sets. The purpose of this research is to determine the important factors affecting PM2.5 environmental variables and pollutants through machine learning algorithms and regression analysis based on the "China Statistical Yearbook". In this paper, the production of general solid industrial waste significantly increases PM2.5 concentration, and the comprehensive utilization of general industrial solid waste is the most economical and feasible measure to significantly reduce PM2.5 concentration. This paper also puts forward solutions to the comprehensive utilization of general solid industrial waste.

Citation Download Citation

Ziyi Pan, Meili Liu, Chun-Te Lee, and Jeng-Eng Lin "Analysis of environmental factors of PM2.5 concentration in China based on feature selection and label construction", Proc. SPIE 12030, Third International Conference on Optoelectronic Science and Materials (ICOSM 2021), 120301P (9 December 2021); https://doi.org/10.1117/12.2619726

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