Air quality prediction based on LSTM algorithm

Qiankun Ren

doi:10.1117/12.2624653

6 February 2022 Air quality prediction based on LSTM algorithm

Qiankun Ren

Proceedings Volume 12081, Sixth International Conference on Electromechanical Control Technology and Transportation (ICECTT 2021); 1208141 (2022) https://doi.org/10.1117/12.2624653
Event: Sixth International Conference on Electromechanical Control Technology and Transportation (ICECTT 2021), 2021, Chongqing, China

Abstract

In recent years, the problem of environmental pollution has received extensive attention from researchers from all over the world. The rising dust and the increase of inhalable particulate matter have gradually reduced people's average life span. Therefore, how to correctly and effectively develop a reasonable algorithm to predict air quality has become the main task at present. In this paper, the LSTM neural network algorithm is used. The LSTM neural network prediction model is established by taking dew point, temperature, air pressure, wind direction, wind speed, snow amount, rainfall and PM2.5 concentration at the previous moment as input factors, and PM2.5 concentration at the current time as the output factor. Comparing the LSTM neural network model with the classical regression model, the experimental results show that the LSTM neural network prediction model has higher stability and higher prediction accuracy than the regression model, and has greater advantages than the existing prediction model.

Citation Download Citation

Qiankun Ren "Air quality prediction based on LSTM algorithm", Proc. SPIE 12081, Sixth International Conference on Electromechanical Control Technology and Transportation (ICECTT 2021), 1208141 (6 February 2022); https://doi.org/10.1117/12.2624653

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