Air quality prediction and early warning model based on LSTM-SARIMA
DOI:
https://doi.org/10.54097/hset.v63i.10867Keywords:
Random Forest, linear insertion, LSTM, SARIMA, weighted prediction.Abstract
With the development of modern society, air pollution has arisen and people's healthy life is threatened, drawing the attention of contemporary society. In this paper, the influencing factors related to PM2.5 concentration and their importance are obtained analytically by linear interpolation method with the help of multiple linear regression and random forest model with respect to air pollution. Meanwhile, based on LSTM model and SARIMA model, the PM2.5 concentration is weighted to predict the air quality for prewarning. Finally, a multi-step prediction model of AQI is developed, and the air quality index (AQI) is used to measure the air quality condition and explore the factors affecting the AQI value.
Downloads
References
Zhao Zheng, Yu Xiaojie, Xiong Yuzheng et al. PM2.5 prediction model based on regression analysis and decision tree algorithm [J]. Changjiang Information &Communications, 2022, 35 (11): 9 - 11.
Xia Weihuai, Liu Jiali, Feng Fenling. Demand forecast of railway refrigerated transportation based on random forest [J]. Journal of Railway Science and Engineering, 2022, 19 (4): 909 - 916.
Wu Weijie, Zhang Jingxiang. Random Forest Feature Selection Algorithm Based on Categorization Information and Application [J]. Computer Engineering and Applications, 2021, 57 (17): 147 - 156.
Zhang Min. Research on the Development Trend of College Students’ Physical Quality Based on Time Series Analysis [D]. North University of China, 2020.
Downloads
Published
Issue
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
