Article Details

Abstract

The commonly used air quality prediction model has poor prediction effect on unknown conditions, and the actual meteorological conditions have a significant impact on the concentration of air pollutants. In order to reduce the error caused by meteorological conditions to the model prediction of pollution concentration, it is of great significance to obtain a model with good prediction accuracy. Therefore, this paper proposes a quadratic collaborative data prediction and optimization method based on Ensemble Learning. Firstly, it combines the measured data with primary predicted data, and uses the Fancyimpute library for data interpolation for missing and deviating from the normal distribution data. Secondly, the BaggingRegressor model in Ensemble Learning is used to construct a quadratic model, and the influence of meteorological conditions on pollutant concentration is analyzed from the whole to the individual. The voting mechanism is used to synthesize all the prediction results, and the ensemble prediction results are obtained. Finally, a collaborative data prediction model is constructed, and the location relationship and wind direction factors are included for comprehensive prediction. The experimental results show that the method can effectively improve the prediction accuracy of the data, and the collaborative prediction model improves the prediction accuracy of the monitoring points.

Keywords

Fancyimpute library; data interpolation; Ensemble Learning; BaggingRegressor model; quadratic model; collaborative prediction model

References

1. [1] Yang Liuming, Gao Shuaipeng, Huang Fei, etc Research on Optimization of Urban Air Quality Forecasting Method Based on Neural Network Model [J]. Environmental Monitoring and Early Warning, 2023, 15 (2): 33-39
2. [2] Zhang Shunshun, Lu Yanxi, Luo Wei, etc Research on Air Pollution Forecasting Based on AQI [J]. Energy and Environment, 2024 (1): 97-99+120
3. [3] Yu Jingjing, Tang Lili, Wu Hao, etc Overview of Prediction Methods for Air Quality Index [J]. Environmental Science and Technology, 2023, 29 (6): 55-59+64
4. [4] Wang Biao, Peng Yu, Wang Wei, etc Research progress on the application of data mining in numerical simulation of air quality [J]. Environmental Science Research, 2024, 37 (8): 1703-1713
5. [5] Zhang Tianjiao, Hai Tao, Wang Jun, etc Air Quality Monitoring System Based on LPWAN and AQI Index Prediction [J]. Science, Technology and Engineering, 2024, 24 (15): 6558-6566
6. [6] Li Jiacheng, Liang Longyue Air quality prediction and identification of influencing factors based on machine learning methods [J]. Computer Technology and Development, 2024, 34 (1): 164-170
7. [7] Wang Zijian, Luo Min, Zhu Qinquan, etc A secondary air quality forecasting model and calculation method based on multi-source data fusion [J]. Jiangxi Science, 2023, 41 (2): 405-411
8. [8] Wang Kaiwen, Li Hongbin Air Quality Index Prediction Model Based on Multiple Linear Regression [J]. Information Recording Materials, 2024, 25 (2): 1-3
9. [9] Zhu Shengkai, Chen Jinjie Secondary prediction of air quality based on extreme learning machine model [J]. Software Engineering, 2022, 25 (8): 39-42
10. [10] Liu Jinna, Yang Lijun, Hu Yongle A secondary air quality forecasting method based on LSTM [J]. Journal of Beijing Institute of Printing and Technology, 2023, 31 (6): 59-63
11. [11] MENDEZ M，MERAYO M G，NUNEZ M. Machine Learning Algorithms to Forecast Air Quality: A Survey [J].Artificial Intelligence Review，2023，56（9）：10031-10066.
12. [12] Xiao Yu Research and Application of Air Quality Numerical Forecasting Correction Method Based on Multi Machine Learning Algorithm Coupling [J]. Environmental Science Research, 2022, 35 (12): 2693-2701
13. [13] Xu Ailan, Zhu Yanmin, Sun Qiang, etc Deep learning air quality forecasting based on K-means partitioning of regions [J]. Journal of Nantong University: Natural Science Edition, 2021, 20 (3): 49-56
14. [14] Li Jiacheng, Liang Longyue Air quality prediction and identification of influencing factors based on machine learning methods [J]. Computer Technology and Development, 2024, 34 (1): 164-170
15. [15] LIU Q，CUI B Y，LIU Z. Air Quality Class Prediction Using Machine Learning Methods Based on Monitoring Data and Secondary Modeling [J/OL].Atmosphere，2024，15（5）：553[2024-10-03].https://doi.org/10.3390/atmos15050553.
16. [16] Li Yijun, Zhang Zhenhao, Hu Jian, etc WRF-CMAQ Optimization Method Based on BP Neural Network [J]. Microcomputer Applications, 2023, 39 (7): 161-164
17. [17] WANG J，ZHANG W，SHI W，et al. Analysis of the Causes of an O3 Pollution Event in Suqian on 18–21 June 2020 Based on the WRF-CMAQ Model [J/OL].Atmosphere，2024，15（7）：831[2024-08-21]. https://doi.org/10.3390/atmos15070831.
18. [18] Boxin Guidelines and Case Studies for Air Quality Models (SMOKE, WRF, CMAQ, etc.) [M]. Beijing: China Environmental Publishing Group, 2019
19. [19] LI J L，YU S C，CHEN X，et al. Evaluation of the WRF-CMAQ Model Performances on Air Quality in China with the Impacts of the Observation Nudging on Meteorology [J/OL].Aerosol and Air Quality Research，2022，22（4）：220023[2024-09-20].https://doi.org/10.4209/aaqr.220023.
20. [20] MEENA D P K，SINGH D V. Air Quality Monitoring and Pollution Control Technologies [J].International Journal of Multidisciplinary Research in Science, Engineering and Technology，2024，7（2）：4409-4426.
21. [21] SACHDEVA S，SINGH H，BHATIA S，et al. An Integrated Framework for Predicting Air Quality Index Using Pollutant Concentration and Meteorological Data [J].Multimedia Tools and Applications，2024，83（16）：46967-46996.
22. [22] LIU W B，LING X B，XUE Y，et al. Study on the Concentration of Top Air Pollutants in Xuzhou City in Winter 2020 Based on the WRF-Chem and ADMS-Urban Models [J/OL].Atmosphere，2024，15（1）：129[2024-09-23].https://doi.org/10.3390/atmos15010129.
23. [23] Jin Mei, Wang Zongshuang, Guo Min, etc Research on Global Environmental Air Quality Standards and Future Prospects for Chinese Standards [J]. Environmental Science Research, 2024, 37 (9): 1897-1910

About the authors

Liang Lina (1996-), female, Han ethnicity, from Xiong'an, Hebei Province, China, research intern, master's degree, research direction: machine learning and data mining; Zhang Yu (1998-), male, Han nationality, from Dezhou, Shandong, teaching assistant, master's degree, research direction: image processing; Zhang Jiawei (1993-), male, Han ethnicity, from Tangshan, Hebei Province, is currently pursuing a master's degree in machine learning and data mining.