基于Informer模型结合多尺度小波变换的空气质量指数预测
Air Quality Index Prediction Based on Informer Model Combined with Multi-Scale Wavelet Transform
DOI: 10.12677/aam.2025.146334, PDF,   
作者: 吴梓建*, 韩素芳#, 乔慧梁：云南民族大学数学与计算机科学学院，云南 昆明
关键词: 小波变换；Informer模型；AQI；空气污染；Wavelet Transformer； Informer Model； AQI； Air Pollution
摘要: 随着全球城市化和工业化的快速发展，空气污染问题越来越严重，能准确预测空气质量变换对社会意义重大。本文用小波变换与Informer结合的模型预测武汉市东湖生态旅游风景区的空气质量指数(AQI)。研究选取2023年1月1日至2024年12月31日每小时该区域的气象数据，针对数据的非平稳性，用小波变换对数据去噪，提高其平稳性，例如对不同数据类型选择适配的小波基：AQI、PM2.5、PM10数据选择db6小波基；对于SO2、NO2、O3、CO数据采用sym6小波基等。将处理后的数据输入Informer模型中进行长短期预测。并构建LSTM、Informer、Autoformer和小波变换与Informer结合模型，在不同时间段对比预测，通过MAE和RMSE等指标评估。发现结合模型在各时间段预测中，指标值均优于其他模型，表明该模型在AQI长短期预测中有更高的精度和稳定性。
Abstract: With the rapid development of global urbanization and industrialization, the problem of air pollution has become increasingly serious. Accurately predicting the changes in air quality is of great significance to society. This paper uses a model combining wavelet transform and Informer to predict the Air Quality Index (AQI) of the East Lake Ecological Tourist Scenic Area in Wuhan. The study selects hourly meteorological data of the area from January 1, 2023 to December 31, 2024. To address the non-stationarity of the data, wavelet transform is used to denoise the data and improve its stationarity. For example, the db6 wavelet basis is selected for AQI, PM2.5, and PM10 data, while the sym6 wavelet basis is used for SO2, NO2, O3, and CO data. The processed data is then input into the Informer model for long-term and short-term predictions. LSTM, Informer, Autoformer, and the combined model of wavelet transform and Informer are constructed, and predictions are compared in different time periods. The MAE and RMSE indicators are used for evaluation. It is found that the combined model has better indicator values in all prediction periods, indicating that this model has higher accuracy and stability in long-term and short-term AQI predictions.
文章引用：吴梓建, 韩素芳, 乔慧梁. 基于Informer模型结合多尺度小波变换的空气质量指数预测[J]. 应用数学进展, 2025, 14(6): 452-464. https://doi.org/10.12677/aam.2025.146334

参考文献

[1] Moradi, H., Talaiekhozani, A., Kamyab, H., Chelliapan, S. and Nadda, A.K. (2022) Development of Equations to Predict the Concentration of Air Pollutants Indicators in Yazd City, Iran. Journal of Inorganic and Organometallic Polymers and Materials, 34, 38-47. [Google Scholar] [CrossRef] 
[2] Zhang, B., Rong, Y., Yong, R., Qin, D., Li, M., Zou, G., et al. (2022) Deep Learning for Air Pollutant Concentration Prediction: A Review. Atmospheric Environment, 290, Article ID: 119347. [Google Scholar] [CrossRef] 
[3] Appel, K.W., Napelenok, S.L., Foley, K.M., Pye, H.O.T., Hogrefe, C., Luecken, D.J., et al. (2017) Description and Evaluation of the Community Multiscale Air Quality (CMAQ) Modeling System Version 5.1. Geoscientific Model Development, 10, 1703-1732. [Google Scholar] [CrossRef] [PubMed]
[4] Sicard, P., Crippa, P., De Marco, A., Castruccio, S., Giani, P., Cuesta, J., et al. (2021) High Spatial Resolution Wrf-Chem Model over Asia: Physics and Chemistry Evaluation. Atmospheric Environment, 244, Article ID: 118004. [Google Scholar] [CrossRef] 
[5] Ge, B.Z., Wang, Z.F., Xu, X.B., Wu, J.B., Yu, X.L. and Li, J. (2014) Wet Deposition of Acidifying Substances in Different Regions of China and the Rest of East Asia: Modeling with Updated NAQPMS. Environmental Pollution, 187, 10-21. [Google Scholar] [CrossRef] [PubMed]
[6] Gao, Z. and Zhou, X. (2024) A Review of the Camx, CMAQ, Wrf-Chem and NAQPMS Models: Application, Evaluation and Uncertainty Factors. Environmental Pollution, 343, Article ID: 123183. [Google Scholar] [CrossRef] [PubMed]
[7] Weiß, C.H. and Swidan, O. (2024) Weighted Discrete ARMA Models for Categorical Time Series. Journal of Time Series Analysis, 46, 505-529. [Google Scholar] [CrossRef] 
[8] Alsharif, M.H., Younes, M.K. and Kim, J. (2019) Time Series ARIMA Model for Prediction of Daily and Monthly Average Global Solar Radiation: The Case Study of Seoul, South Korea. Symmetry, 11, Article No. 240. [Google Scholar] [CrossRef] 
[9] Ehteram, M. and Banadkooki, F.B. (2023) A Developed Multiple Linear Regression (MLR) Model for Monthly Groundwater Level Prediction. Water, 15, Article No. 3940. [Google Scholar] [CrossRef] 
[10] Zhang, Y., Xu, T.X., Zhang, C.J., et al. (2024) Deep Learning Tool: Reconstruction of Long Missing Climate Data Based on Multilayer Perceptron (MLP). EGUsphere.
[11] Talepour, N., Birgani, Y.T., Kelly, F.J., Jaafarzadeh, N. and Goudarzi, G. (2024) Analyzing Meteorological Factors for Forecasting PM10 and PM2.5 Levels: A Comparison between MLR and MLP Models. Earth Science Informatics, 17, 5603-5623. [Google Scholar] [CrossRef] 
[12] Yuzer, E.O. and Bozkurt, A. (2025) Artificial Neural Network Models for Solar Radiation Estimation Based on Meteorological Data. Acta Polytechnica Hungarica, 22, 43-65. [Google Scholar] [CrossRef] 
[13] Wu, T., Chen, P., Chen, C., Chung, M., Ye, Z. and Li, M. (2024) Classification and Regression Tree (CART)-Based Estimation of Soil Water Content Based on Meteorological Inputs and Explorations of Hydrodynamics Behind. Agricultural Water Management, 299, Article ID: 108869. [Google Scholar] [CrossRef] 
[14] Zhong, Y., Zhang, B., Ji, X. and Wu, J. (2024) Fault Diagnosis of PV Array Based on Time Series and Support Vector Machine. International Journal of Photoenergy, 2024, Article ID: 2885545. [Google Scholar] [CrossRef] 
[15] Wang, H., Li, Y., Huang, G., Zhang, Q., Ma, Y. and Li, Y. (2024) Development of a Random-Forest-Copula-Factorial Analysis (RFCFA) Method for Predicting Propagation between Meteorological and Hydrological Drought. National Science Open, 3, Article ID: 20230022. [Google Scholar] [CrossRef] 
[16] Menéndez-García, L.A., García-Nieto, P.J., García-Gonzalo, E. and Sánchez Lasheras, F. (2024) Time Series Analysis for COMEX Platinum Spot Price Forecasting Using SVM, MARS, MLP, VARMA and ARIMA Models: A Case Study. Resources Policy, 95, Article ID: 105148. [Google Scholar] [CrossRef] 
[17] Kumar, K. and Pande, B.P. (2022) Air Pollution Prediction with Machine Learning: A Case Study of Indian Cities. International Journal of Environmental Science and Technology, 20, 5333-5348. [Google Scholar] [CrossRef] [PubMed]
[18] Tang, J., Yang, R., Dai, Q., Yuan, G. and Mao, Y. (2023) Research on Feature Extraction of Meteorological Disaster Emergency Response Capability Based on an RNN Autoencoder. Applied Sciences, 13, Article No. 5153. [Google Scholar] [CrossRef] 
[19] Ouma, Y.O., Cheruyot, R. and Wachera, A.N. (2021) Rainfall and Runoff Time-Series Trend Analysis Using LSTM Recurrent Neural Network and Wavelet Neural Network with Satellite-Based Meteorological Data: Case Study of Nzoia Hydrologic Basin. Complex & Intelligent Systems, 8, 213-236. [Google Scholar] [CrossRef] 
[20] Weng, Z., Li, W. and Jin, Z. (2021) Human Activity Prediction Using Saliency-Aware Motion Enhancement and Weighted LSTM Network. EURASIP Journal on Image and Video Processing, 2021, Article No. 3. [Google Scholar] [CrossRef] 
[21] Boughale, R., Zrelli, A. and Ezzedine, T. (2024) Enhancing Flood Forecasting with BiLSTM Networks. 2024 IEEE/ACS 21st International Conference on Computer Systems and Applications (AICCSA), Sousse, 22-26 October 2024, 1-6. [Google Scholar] [CrossRef] 
[22] Park, K., Seong, Y., Jung, Y., Youn, I. and Choi, C.K. (2023) Development of Water Level Prediction Improvement Method Using Multivariate Time Series Data by GRU Model. Water, 15, Article No. 587. [Google Scholar] [CrossRef] 
[23] Huang, C.J. and Kuo, P.H. (2018) A Deep CNN-LSTM Model for Particulate Matter (PM2.5) Forecasting in Smart Cities. Sensors, 18, Article No. 2220.
[24] Du, S., Li, T., Yang, Y. and Horng, S. (2021) Deep Air Quality Forecasting Using Hybrid Deep Learning Framework. IEEE Transactions on Knowledge and Data Engineering, 33, 2412-2424. [Google Scholar] [CrossRef] 
[25] Sun, Y. and Liu, J. (2022) AQI Prediction Based on CEEMDAN-ARMA-LSTM. Sustainability, 14, Article No. 12182. [Google Scholar] [CrossRef] 
[26] Zhou, K., Zhang, C., Xu, B., Huang, J., Li, C. and Pei, Y. (2024) TE-LSTM: A Prediction Model for Temperature Based on Multivariate Time Series Data. Remote Sensing, 16, Article No. 3666. [Google Scholar] [CrossRef] 
[27] Vaswani, A., Shazeer, N., Parmar, N., et al. (2017) Attention Is All You Need. Proceedings of the 31st International Conference on Neural Information Processing Systems, Long Beach, 4-9 December 2017, 6000-6010.
[28] Wen, Q., Zhou, T., Zhang, C., et al. (2023) Transformers in Time Series: A Survey.
[29] Ahmed, S., Nielsen, I.E., Tripathi, A., Siddiqui, S., Ramachandran, R.P. and Rasool, G. (2023) Transformers in Time-Series Analysis: A Tutorial. Circuits, Systems, and Signal Processing, 42, 7433-7466. [Google Scholar] [CrossRef] 
[30] Qin, Z., Wei, B., Gao, C., Chen, X., Zhang, H. and In Wong, C.U. (2025) SFDformer: A Frequency-Based Sparse Decomposition Transformer for Air Pollution Time Series Prediction. Frontiers in Environmental Science, 13, Article ID: 1549209. [Google Scholar] [CrossRef] 
[31] Hou, Q., Gao, Z., Lu, M. and Yu, Y. (2025) Atmosphere, 16, Article No. 431. [Google Scholar] [CrossRef] 
[32] Zhou, H., Zhang, S., Peng, J., Zhang, S., Li, J., Xiong, H., et al. (2021) Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting. Proceedings of the AAAI Conference on Artificial Intelligence, 35, 11106-11115. [Google Scholar] [CrossRef] 

为你推荐