Download pdf
Prediction of Beijing's PM2.5 Concentration Based on the LSTM Model
- 1 College of Artificial Intelligence, Tianjin University of Science and Technology, Tianjin, 300457, China
- 2 Faculty of Data Science, City University of Macau, Macao, 519031, China
* Author to whom correspondence should be addressed.
Abstract
PM2.5 has serious impacts on cardiovascular and respiratory health. As people's attention to physical health increases, the issue of PM2.5 has become increasingly prominent. The goal of this research is to create a prediction model for Beijing's PM2.5 concentrations using the Long Short-Term Memory (LSTM) deep learning algorithm. This paper utilizes PM2.5 measurements from the US Embassy in Beijing and meteorological data from Beijing Capital International Airport from 2010 to 2014. The study forecasts PM2.5 concentrations via the LSTM model by integrating variables such as temperature, pressure, and wind speed. The results of this study validate the feasibility of the LSTM model in predicting PM2.5 and yield relatively good prediction outcomes. It is evident that concentrations are lower in the summer and higher in the winter. However, the prediction results are lower compared to the actual data and are not effective in predicting drastic changes caused by other influencing factors. The results provide information for the creation of more efficient air quality management plans by exposing the connections between PM2.5 and different meteorological variables.
Keywords
PM2.5, LSTM, prediction model
[1]. Xu, Y., & Wu, J. (2023). Short-term PM2.5 prediction based on machine learning (in Chinese). Computers and Telecommunications, (12), 72-77.
[2]. Huang, C.-J., & Kuo, P.-H. (2018). A deep CNN-LSTM model for particulate matter (PM2.5) forecasting in smart cities. Sensors, 18(7), 2220.
[3]. Xiao, W., He, Y., Meng, F., Xu, J., Liu, S., & Yang, X. (2018). Development and comparison of atmospheric chemistry mechanisms in air quality models (in Chinese). Journal of Environmental Engineering Technology, (01), 12-22.
[4]. Yang, Q., Jin, C., Li, T., Yuan, Q., Shen, H., & Zhang, L. (2022). Research progress and challenges of data-driven quantitative remote sensing (in Chinese). Journal of Remote Sensing, (02), 268-285.
[5]. Li, Z., Zhang, T., & Li, H. (2023). Prediction of PM2.5 concentration based on XGBoost and LSTM combined model (in Chinese). Journal of Hebei Institute of Architecture and Civil Engineering, (04), 219-223.
[6]. Bai, S. N., & Shen, X. L. (2019). PM2.5 prediction based on LSTM recurrent neural network. Computer Applications and Software, (01), 67-70+104.
[7]. Liu, M., & Wei, L. (2020). EMD-LSTM algorithm and its application in PM2.5 prediction. Journal of Changchun University of Technology, (04), 322-327+417.
[8]. Li, Z. Y., Zhang, T. Y., & Li, H. Q. (2023). PM2.5 concentration prediction based on the XGBoost and LSTM combined model. Journal of Hebei University of Architecture and Engineering, (04), 219-223.
[9]. Mo, W. (2022). Research on air quality prediction based on deep learning (Master's thesis, East China Normal University) (in Chinese). Master's thesis. https://link.cnki.net/doi/10.27149/d.cnki.ghdsu.2022.004253 doi:10.27149/d.cnki.ghdsu.2022.004253.
[10]. Zia, U. (2024). Predict air quality in Beijing, China. Kaggle. https://www.kaggle.com/datasets/stealthtechnologies/preeeeeeee.
[11]. Qu, Y., Qian, X., Song, H., He, J., Li, J., & Xiu, H. (2024). Machine-learning-based model and simulation for air quality prediction.
[12]. Colah. (2015, August 27). Understanding LSTM networks. https://colah.github.io/posts/2015-08-Understanding-LSTMs/
[13]. Yan, J., & Wang, G. (2022). Self-variable weights-based CNN & LSTM combination for PM2.5 concentration prediction: A case study in Beijing. Advances in Applied Mathematics, 11(4), 2095-2106.
[14]. Bai, S., & Shen, X. (2019). Prediction of PM2.5 based on LSTM recurrent neural network. Computer Applications and Software, 36(1), 67-70.
Cite this article
Li,Y.;Wu,J. (2024). Prediction of Beijing's PM2.5 Concentration Based on the LSTM Model. Applied and Computational Engineering,112,35-41.
Data availability
The datasets used and/or analyzed during the current study will be available from the authors upon reasonable request.
Disclaimer/Publisher's Note
The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of EWA Publishing and/or the editor(s). EWA Publishing and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content.
About volume
Volume title: Proceedings of the 5th International Conference on Signal Processing and Machine Learning
© 2024 by the author(s). Licensee EWA Publishing, Oxford, UK. This article is an open access article distributed under the terms and
conditions of the Creative Commons Attribution (CC BY) license. Authors who
publish this series agree to the following terms:
1. Authors retain copyright and grant the series right of first publication with the work simultaneously licensed under a Creative Commons
Attribution License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this
series.
2. Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the series's published
version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial
publication in this series.
3. Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and
during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See
Open access policy for details).