用于空气质量预测的集成时间序列模型
Ensemble Time Series Forecasting Model for Air Quality Prediction
DOI: 10.12677/aam.2025.1410454, PDF,   
作者: 乔慧梁*, 韩素芳#, 吴梓建：云南民族大学数学与计算机科学学院，云南 昆明
关键词: 深度学习；集成学习；空气质量指数；Deep Learning； Ensemble Learning； Air Quality Index
摘要: 空气质量指数(AQI)是衡量空气质量的关键指标，具有随机性和非平稳性，构建一个合理的预测系统对整体社会有一定意义。本文整合集成学习策略，提出一种新型的用于提高模型的预测精度和稳健性的集成模型框架。通过对中国云南省的空气质量指数的预测，从而证明基于堆叠随机森林时间序列的预测模型实现了对比传统的LSTM、GRU和Transformer模型的性能较为显著的稳健性提升和精度提升。在对云南省共计13个样本点的预测中，本文模型平均R2值达到0.801，表明了模型在数值预测方面有较高的准确性。
Abstract: The air quality index (AQI) serves as a crucial metric for gauging air quality. Given the intrinsic randomness and non-stationarity within, constructing a rational analysis-prediction system for AQI remains a meaningful task. This study minimizing Integrating ensemble learning strategies and effectively improving both the prediction accuracy and the robustness of the model, is applied to air quality monitoring in Yunnan Province, China. Experimental results demonstrate that the proposed based on stacked random forest time series prediction model achieves significant accuracy while outperforming traditional LSTM, GRU, and Transformer or some common other models that used for AQI prediction. In the prediction of a total of 13 sample points in Yunnan Province, the evaluation report indicates that the model’s average coefficient of determination R2 reaches 0.801. On this basis, its high accuracy in numerical prediction is demonstrated.
文章引用：乔慧梁, 韩素芳, 吴梓建. 用于空气质量预测的集成时间序列模型[J]. 应用数学进展, 2025, 14(10): 426-437. https://doi.org/10.12677/aam.2025.1410454

参考文献

[1] Sousa, S., Martins, F., Alvimferraz, M. and Pereira, M. (2007) Multiple Linear Regression and Artificial Neural Networks Based on Principal Components to Predict Ozone Concentrations. Environmental Modelling & Software, 22, 97-103. [Google Scholar] [CrossRef] 
[2] Ancelet, T., Davy, P.K., Trompetter, W.J., Markwitz, A. and Weatherburn, D.C. (2014) Sources and Transport of Particulate Matter on an Hourly Time-Scale during the Winter in a New Zealand Urban Valley. Urban Climate, 10, 644-655. [Google Scholar] [CrossRef] 
[3] Li, Y., Peng, T., Hua, L., Ji, C., Ma, H., Nazir, M.S., et al. (2022) Research and Application of an Evolutionary Deep Learning Model Based on Improved Grey Wolf Optimization Algorithm and DBN-ELM for AQI Prediction. Sustainable Cities and Society, 87, Article 104209. [Google Scholar] [CrossRef] 
[4] Song, C. and Fu, X. (2020) Research on Different Weight Combination in Air Quality Forecasting Models. Journal of Cleaner Production, 261, Article 121169. [Google Scholar] [CrossRef] 
[5] Li, G., Tang, Y. and Yang, H. (2022) A New Hybrid Prediction Model of Air Quality Index Based on Secondary Decomposition and Improved Kernel Extreme Learning Machine. Chemosphere, 305, Article 135348. [Google Scholar] [CrossRef] [PubMed]
[6] Wei, W., Ramalho, O., Malingre, L., Sivanantham, S., Little, J.C. and Mandin, C. (2019) Machine Learning and Statistical Models for Predicting Indoor Air Quality. Indoor Air, 29, 704-726. [Google Scholar] [CrossRef] [PubMed]
[7] Li, H., Wang, J., Li, R. and Lu, H. (2019) Novel Analysis-Forecast System Based on Multi-Objective Optimization for Air Quality Index. Journal of Cleaner Production, 208, 1365-1383. [Google Scholar] [CrossRef] 
[8] Xu, R., Deng, X., Wan, H., Cai, Y. and Pan, X. (2021) A Deep Learning Method to Repair Atmospheric Environmental Quality Data Based on Gaussian Diffusion. Journal of Cleaner Production, 308, Article 127446. [Google Scholar] [CrossRef] 
[9] Liu, H., Yue, F. and Xie, Z. (2022) Quantify the Role of Anthropogenic Emission and Meteorology on Air Pollution Using Machine Learning Approach: A Case Study of PM2.5 during the COVID-19 in Hubei Province, China. Environmental Pollution, 300, Article 118932. [Google Scholar] [CrossRef] [PubMed]
[10] Middya, A.I. and Roy, S. (2022) Pollutant Specific Optimal Deep Learning and Statistical Model Building for Air Quality Forecasting. Environmental Pollution, 301, Article 118972. [Google Scholar] [CrossRef] [PubMed]
[11] Zheng, L., Lin, R., Wang, X. and Chen, W. (2021) The Development and Application of Machine Learning in Atmospheric Environment Studies. Remote Sensing, 13, Article 4839. [Google Scholar] [CrossRef] 
[12] Yazdi, M.D., Kuang, Z., Dimakopoulou, K., Barrat, B., Suel, E., Amini, H., Lyapustin, A., Katsouyanni, K. and Schwartz, J. (2019) Predicting Fine Particulate Matter (PM2.5) in the Greater London AREA: an Ensemble Approach Using Machine Learning Methods. Remote Sensing, 3, 355-356.
[13] Huang, C. and Kuo, P. (2018) A Deep CNN-LSTM Model for Particulate Matter (PM2.5) Forecasting in Smart Cities. Sensors, 18, Article 2220. [Google Scholar] [CrossRef] [PubMed]
[14] Subramanian, D. and Marimuthu, P. (2024) Design and Synthesis of Time Series Forecasting and Deep Learning Prediction Model for Air Quality Index Prediction in Indian Cities. Indian Journal of Engineering and Materials Sciences, 31, 589-600.
[15] Tsai, Y., Zeng, Y. and Chang, Y. (2018) Air Pollution Forecasting Using RNN with LSTM. 2018 IEEE 16th Intl Conf on Dependable, Autonomic and Secure Computing, 16th Intl Conf on Pervasive Intelligence and Computing, 4th Intl Conf on Big Data Intelligence and Computing and Cyber Science and Technology Congress (DASC/PiCom/DataCom/ CyberSciTech), Athens, 12-15 August 2018, 1074-1079. [Google Scholar] [CrossRef] 
[16] Mao, W., Wang, W., Jiao, L., Zhao, S. and Liu, A. (2021) Modeling Air Quality Prediction Using a Deep Learning Approach: Method Optimization and Evaluation. Sustainable Cities and Society, 65, Article 102567. [Google Scholar] [CrossRef] 
[17] Espinosa, R., Palma, J., Jiménez, F., Kamińska, J., Sciavicco, G. and Lucena-Sánchez, E. (2021) A Time Series Forecasting Based Multi-Criteria Methodology for Air Quality Prediction. Applied Soft Computing, 113, Article 107850. [Google Scholar] [CrossRef] 
[18] Méndez, M., Merayo, M.G. and Núñez, M. (2023) Machine Learning Algorithms to Forecast Air Quality: A Survey. Artificial Intelligence Review, 56, 10031-10066. [Google Scholar] [CrossRef] [PubMed]
[19] Liu, H., Yan, G., Duan, Z. and Chen, C. (2021) Intelligent Modeling Strategies for Forecasting Air Quality Time Series: A Review. Applied Soft Computing, 102, Article 106957. [Google Scholar] [CrossRef] 
[20] Sun, W. and Li, Z. (2020) Hourly PM2.5 Concentration Forecasting Based on Feature Extraction and Stacking-Driven Ensemble Model for the Winter of the Beijing-Tianjin-Hebei Area. Atmospheric Pollution Research, 11, 110-121. [Google Scholar] [CrossRef] 
[21] Nur’aiah, Z., Woen, E.L., Najah, A.A. and Abdul, M.M. (2021) A Systematic Literature Review of Deep Learning Neural Network for Time Series Air Quality Forecasting. Environmental Science and Pollution Research, 29, 4958-4990. [Google Scholar] [CrossRef] [PubMed]
[22] Lin, C.-Y., Chang, Y-S. and Abimannan, S. (2021) Ensemble Multifeatured Deep Learning Models for Air Quality Forecasting. Atmospheric Pollution Research, 12, Article 101045. [Google Scholar] [CrossRef] 
[23] Diaz Resquin, M., Lichtig, P., Alessandrello, D., De Oto, M., Gómez, D., Rössler, C., et al. (2023) A Machine Learning Approach to Address Air Quality Changes during the COVID-19 Lockdown in Buenos Aires, Argentina. Earth System Science Data, 15, 189-209. [Google Scholar] [CrossRef] 
[24] Das, B., Dursun, Ö.O. and Toraman, S. (2022) Prediction of Air Pollutants for Air Quality Using Deep Learning Methods in a Metropolitan City. Urban Climate, 46, Article 101291. [Google Scholar] [CrossRef] 
[25] Zhao, Z., Wu, J., Cai, F., Zhang, S. and Wang, Y. (2022) A Statistical Learning Framework for Spatial-Temporal Feature Selection and Application to Air Quality Index Forecasting. Ecological Indicators, 144, Article 109416. [Google Scholar] [CrossRef] 
[26] Kurt, A. and Oktay, A.B. (2010) Forecasting Air Pollutant Indicator Levels with Geographic Models 3days in Advance Using Neural Networks. Expert Systems with Applications, 37, 7986-7992. [Google Scholar] [CrossRef] 
[27] Xiao, Q., Chang, H., Geng, G. and Liu, Y. (2018) An Ensemble Machine-Learning Model to Predict Historical PM2.5 Concentrations in China from Satellite Data. ISEE Conference Abstracts, 2018, 13260-13269. [Google Scholar] [CrossRef] 
[28] Qin, S., Liu, F., Wang, C., Song, Y. and Qu, J. (2015) Spatial-Temporal Analysis and Projection of Extreme Particulate Matter (PM10 and PM2.5) Levels Using Association Rules: A Case Study of the Jing-Jin-Ji Region, China. Atmospheric Environment, 120, 339-350. [Google Scholar] [CrossRef] 
[29] Ksibi, A., Salhi, A., Saleh Alluhaidan, A. and A. El-Rahman, S. (2023) Airstacknet: A Stacking Ensemble-Based Approach for Air Quality Prediction. Computers, Materials & Continua, 74, 2073-2096. [Google Scholar] [CrossRef] 
[30] Yu, W., Nakisa, B., Ali, E., Loke, S.W., Stevanovic, S. and Guo, Y. (2023) Sensor-based Indoor Air Temperature Prediction Using Deep Ensemble Machine Learning: An Australian Urban Environment Case Study. Urban Climate, 51, Article 101599. [Google Scholar] [CrossRef] 
[31] Wu, Q. and Lin, H. (2019) A Novel Optimal-Hybrid Model for Daily Air Quality Index Prediction Considering Air Pollutant Factors. Science of The Total Environment, 683, 808-821. [Google Scholar] [CrossRef] [PubMed]
[32] Aggarwal, A. and Toshniwal, D. (2021) A Hybrid Deep Learning Framework for Urban Air Quality Forecasting. Journal of Cleaner Production, 329, Article 129660. [Google Scholar] [CrossRef] 
[33] Huang, H. and Qian, C. (2023) Modeling PM2.5 Forecast Using a Self-Weighted Ensemble GRU Network: Method Optimization and Evaluation. Ecological Indicators, 156, Article 111138. [Google Scholar] [CrossRef] 

为你推荐