Forecasting of PM2.5 concentration time series based on SSA-LSTM model

Yueyi Zhang; Di He; Qingyue Wu

doi:10.1117/12.2656939

13 January 2023 Forecasting of PM2.5 concentration time series based on SSA-LSTM model

Yueyi Zhang, Di He, Qingyue Wu

Proceedings Volume 12510, International Conference on Statistics, Data Science, and Computational Intelligence (CSDSCI 2022); 125101I (2023) https://doi.org/10.1117/12.2656939
Event: International Conference on Statistics, Data Science, and Computational Intelligence (CSDSCI 2022), 2022, Qingdao, China

Abstract

Clean air is a basic need for human health and well-being. Forecasting PM2.5 concentrations so that cities can make timely policy responses are of great significance of protecting citizens' respiratory health. This paper proposes a long short-term memory neural network models based on the Sparrow Search Algorithm (SSA-LSTM). The Sparrow Search Algorithm is used to optimize the number of hidden layer nodes, learning rate and number of iterations of the LSTM network to improve the forecasting accuracy of the model. In order to verify the validity of the model, the PM2.5 data onto five large cities including Beijing and Shanghai were used for time series forecasting. Compared with the existing long-short-term memory network model (LSTM), BP neural network models and bilateral long-short-term memory network model (Bilstm), the results show that the forecasting results forecast by this optimization model are the most consistent with the actual PM2.5. The forecasting error is effectively reduced, and the optimization result of the SSA algorithm has a good generalization effect.

Citation Download Citation

Yueyi Zhang, Di He, and Qingyue Wu "Forecasting of PM2.5 concentration time series based on SSA-LSTM model", Proc. SPIE 12510, International Conference on Statistics, Data Science, and Computational Intelligence (CSDSCI 2022), 125101I (13 January 2023); https://doi.org/10.1117/12.2656939

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