A REVIEW OF HYBRID FORECASTING METHODS FOR ATMOSPHERIC POLLUTANTS IN SHORT-TERM BASED ON DATA DECOMPOSITION

LI Youjie; ZHAO Shunyu; YANG Ping; WANG Yelin

doi:10.13205/j.hjgc.202304029

Volume 41 Issue 4

Apr. 2023

Turn off MathJax

Article Contents

Article Navigation > ENVIRONMENTAL ENGINEERING > 2023 > 41(4): 213-224

LI Youjie, ZHAO Shunyu, YANG Ping, WANG Yelin. A REVIEW OF HYBRID FORECASTING METHODS FOR ATMOSPHERIC POLLUTANTS IN SHORT-TERM BASED ON DATA DECOMPOSITION[J]. ENVIRONMENTAL ENGINEERING , 2023, 41(4): 213-224. doi: 10.13205/j.hjgc.202304029

Citation:

LI Youjie, ZHAO Shunyu, YANG Ping, WANG Yelin. A REVIEW OF HYBRID FORECASTING METHODS FOR ATMOSPHERIC POLLUTANTS IN SHORT-TERM BASED ON DATA DECOMPOSITION[J]. ENVIRONMENTAL ENGINEERING , 2023, 41(4): 213-224. doi: 10.13205/j.hjgc.202304029

Citation:

PDF( 10748 KB)

A REVIEW OF HYBRID FORECASTING METHODS FOR ATMOSPHERIC POLLUTANTS IN SHORT-TERM BASED ON DATA DECOMPOSITION

doi: 10.13205/j.hjgc.202304029

1. Faculty of Management and Economics, Kunming University of Science and Technology, Kunming 650093, China;
2. School of Ecology, Environment and Resources, Guangdong University of Technology, Guangzhou 510006, China

Received Date: 2022-06-20
Available Online: 2023-05-26
Publish Date: 2023-04-01

Abstract

Abstract

Atmospheric pollutants’ short-term prediction is of great significance to formulate effective control measures for the atmospheric environment and reduce the health risk on residents. Hybrid model can make accurate and reliable prediction by mining time-frequency information contained in time series via data decomposition, becoming the development trend of atmospheric pollutants’ short-term prediction. The existing short-term prediction models of atmospheric pollutants were sorted out from the time scale. Meanwhile, the hybrid models based on wavelet decomposition, empirical mode decomposition and variational mode decomposition were reviewed. Subsequently, according to the aims, the prediction structure of the hybrid model was summarized into data de-noising, secondary decomposition, component processing and error modification. The advantages, disadvantages, and application range of each structure were summarized. The results showed that the four hybrid structures were not universally applicable to all situations and should be used selectively according to data characteristics and other conditions. Finally, the issues of existing hybrid prediction models were summarized. It was pointed out that the future research should be carried out from the perspectives of the adaptive hybrid structure, the impact of data characteristics on performance and the balance of multi-performance of the model.
- data decomposition method,
- atmospheric pollutant,
- short-term forecasting,
- hybrid model

FullText(HTML)

References(111)

References

[1]	HAN X, LIU Y Q, GAO H, et al. Forecasting PM_2.5 induced male lung cancer morbidity in China using satellite retrieved PM_2.5 and spatial analysis[J]. Journal of Cleaner Production, 2017, 607/608: 1009-1017.
[2]	COHEN A J, BRAUER M, BURNETT R, et al. Estimates and 25-year trends of the global burden of disease attributable to ambient air pollution: an analysis of data from the Global Burden of Diseases Study[J]. Lancet, 2017, 389: 1907-1918.
[3]	刘聪, 李鑫. 空气污染与城乡收入差距:基于健康视角的检验[J]. 统计与决策, 2021, 37(4): 100-103.
[4]	NAM K M, SELIN N E, REILLY J M, et al. Measuring welfare loss caused by air pollution in Europe: a CGE analysis[J]. Energy Policy, 2010, 38: 5059-5071.
[5]	生态环境部. 2020中国生态环境状况公报[R]. 北京: 生态环境部, 2021.
[6]	鞠昌华,高吉喜.《"十三五"生态环境保护规划》的特点分析[J].环境保护,2017,45(5):42-44.
[7]	XIAO K, WANG Y K, WU G, et al. Spatiotemporal characteristics of air pollutants (PM₁₀, PM_2.5, SO₂, NO₂, O₃, and CO) in the inland basin city of Chengdu, southwest China[J]. Atmosphere, 2018, 9(2): 74.
[8]	LIU H, YAN G X, DUAN Z, et al. Intelligent modeling strategies for forecasting air quality time series: a review[J]. Applied Soft Computing, 2021, 102: 106957.
[9]	ZHANG J S, DING W F. Prediction of air pollutants concentration based on an extreme learning machine: the case of Hong Kong[J]. International Journal of Environmental Research and Public Health, 2017, 14(2): 114.
[10]	汪伟全. 空气污染的跨域合作治理研究:以北京地区为例[J]. 公共管理学报, 2014, 11(1): 55-64 ,140.
[11]	WAN K, SHACKLEY S, DOHERTY R M, et al. Science-policy interplay on air pollution governance in China[J]. Environmental Science & Policy, 2020, 107(4): 150-157.
[12]	黄国和. 应用多元统计分析理论预测城市大气污染[J]. 环境科学, 1991,12(2): 29-34 ,95.
[13]	孟凡强. ARIMA模型在空气污染指数预测中的应用[J]. 统计与决策, 2009(7): 33-35.
[14]	KUMAR A, GOYAL P. Forecasting of daily air quality index in Delhi[J]. Science of the Total Environment, 2011, 409(24): 5517-5523.
[15]	付倩娆. 基于多元线性回归的雾霾预测方法研究[J]. 计算机科学, 2016, 43(增刊1): 526-528.
[16]	YIN Q, WANG J F, HU M G, et al. Estimation of daily PM_2.5 concentration and its relationship with meteorological conditions in Beijing[J]. Journal of Environmental Sciences, 2016, 48: 161-168.
[17]	KURT A, OKTAY A B. Forecasting air pollutant indicator levels with geographic models 3days in advance using neural networks[J]. Expert Systems with Applications, 2010, 37(12): 7986-7992.
[18]	聂邦胜. 国内外常用的空气质量模式介绍[J]. 海洋技术, 2008, 27(1): 118-121 ,132.
[19]	薛文博, 王金南, 杨金田, 等. 国内外空气质量模型研究进展[J]. 环境与可持续发展, 2013, 38(3): 14-20.
[20]	WANG L T, JANG C, ZHANG Y, et al. Assessment of air quality benefits from national air pollution control policies in China. Part Ⅱ: evaluation of air quality predictions and air quality benefits assessment[J]. Atmospheric Environment, 2010, 44(28): 3449-3457.
[21]	沈劲, 王雪松, 李金凤, 等. Models-3/CMAQ和CAMx对珠江三角洲臭氧污染模拟的比较分析[J]. 中国科学(化学), 2011, 41(11): 1750-1762.
[22]	王峰, 汪健伟, 杨宁, 等. VOCs源强不确定性对臭氧生成及污染防治影响的模拟分析[J]. 环境科学, 2021, 42(12): 5713-5722.
[23]	王自发, 谢付莹, 王喜全, 等. 嵌套网格空气质量预测模式系统的发展与应用[J]. 大气科学, 2006, 30(5): 778-790.
[24]	尹文君, 张大伟, 严京海, 等. 基于深度学习的大数据空气污染预报[J]. 中国环境管理, 2015, 7(6): 46-52.
[25]	王勤耕, 夏思佳, 万祎雪, 等. 当前城市空气污染预报方法存在的问题及新思路[J]. 环境科学与技术, 2009, 32(3): 189-192.
[26]	YANG J H, KANG S C, JI Z M, et al. Investigating air pollutant concentrations, impact factors, and emission control strategies in western China by using a regional climate-chemistry model[J]. Chemosphere, 2019, 246: 125767.
[27]	周广强, 瞿元昊, 高伟, 等. 云下湿清除作用对长三角PM_2.5模拟的影响[J]. 中国环境科学, 2020, 40(7): 2794-2801.
[28]	DENG J L. Control problems of grey systems[J]. Systems. & Control Letters, 1982, 1(5): 288-294.
[29]	TIEN T. A new grey prediction model FGM (1, 1)[J]. Mathematical and Computer Modelling, 2009, 49: 1416-1426.
[30]	CHANG C J, LI D C, HUANG Y H, et al. A novel gray forecasting model based on the box plot for small manufacturing data sets[J]. Applied Mathematics and Computation, 2015, 265: 400-408.
[31]	熊萍萍, 袁玮莹, 叶琳琳, 等. 灰色MGM(1,m,N)模型的构建及其在雾霾预测中的应用[J]. 系统工程理论与实践, 2020, 40(3): 771-782.
[32]	WU L F, ZHAO H Y. Using FGM (1,1) model to predict the number of the lightly polluted day in Jing-Jin-Ji region of China[J]. Atmospheric Pollution Research, 2019, 10(2): 552-555.
[33]	张爱琳, 白丽娜, 韩液, 等. 基于多变量分数阶灰色模型的郑州市空气质量预测[J]. 安全与环境学报, 2022, 22(4): 2258-2269.
[34]	COMRIE A C. Comparing neural networks and regression models for ozone forecasting[J]. Journal of the Air & Waste Management Association, 1997, 47(6): 653-663.
[35]	梁泽, 王玥瑶, 岳远紊, 等. 耦合遗传算法与RBF神经网络的PM_2.5浓度预测模型[J]. 中国环境科学, 2020, 40(2): 523-529.
[36]	ESLAMI E, SALMAN A K, CHOI Y, et al. A data ensemble approach for real-time air quality forecasting using extremely randomized trees and deep neural networks[J]. Neural Computing and Applications, 2020, 32(2): 7563-7579.
[37]	黄春桃, 范东平, 卢集富, 等. 基于深度学习模型的广州市大气PM_2.5和PM₁₀浓度预测[J]. 环境工程, 2021, 39(12): 135-140.
[38]	LIU H, CHEN C. Data processing strategies in wind energy forecasting models and applications: a comprehensive review[J]. Applied Energy, 2019, 249: 392-408.
[39]	ASHISH M, RASHMI B. Prediction of daily air pollution using wavelet decomposition and adaptive-network-based fuzzy inference system[J]. International Journal of Environmental Sciences, 2011, 2: 185.
[40]	郑霞, 胡东滨, 李权. 基于小波分解和SVM的大气污染物浓度预测模型研究[J]. 环境科学学报, 2020, 40(8): 2962-2969.
[41]	吴曼曼, 徐建新, 王钦. 基于数据分解的AQI的CEEMD-Elman神经网络预测研究[J]. 中国环境科学, 2019, 39(11): 4580-4588.
[42]	SHARMA E, DEO R C, PRASAD R, et al. A hybrid air quality early-warning framework: an hourly forecasting model with online sequential extreme learning machines and empirical mode decomposition algorithms[J]. Science of the Total Environment, 2020, 709(20): 135934.
[43]	WU Q L, LIN H X. Daily urban air quality index forecasting based on variational mode decomposition, sample entropy and LSTM neural network[J]. Sustainable Cities and Society, 2019, 50: 101657.
[44]	XING G Y, ZHAO E L, ZHANG C Y, et al. A decomposition-ensemble approach with denoising strategy for PM_2.5 concentration forecasting[J]. Discrete Dynamics in Nature and Society, 2021, 2021: 5577041.
[45]	LAINE A, FAN J. Texture classification by wavelet packet signatures[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1993, 15(11): 1186-1191.
[46]	JIANG F, HE J Q, TIAN T H. A clustering-based ensemble approach with improved pigeon-inspired optimization and extreme learning machine for air quality prediction[J]. Applied Soft Computing, 2019, 85: 105827.
[47]	GILLES J. Empirical wavelet transform[J]. IEEE Transactions on Signal Processing, 2013, 61(16): 3999-4010.
[48]	HUANG N E, SHEN Z, LONG S R, et al. The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis[J]. Proceedings of The Royal Society of London. Series A: Mathematical, Physical and Engineering Sciences, 1998, 454: 903-995.
[49]	王业林, 杨萍, 李斌, 等. 数据分解模式下PM_2.5与气态污染物的组合预测研究[J]. 环境科学学报, 2021, 41(8): 3043-3050.
[50]	WU Z H, HUANG N E. Ensemble empirical mode decomposition: a noise-assisted data analysis method[J]. Advances in Adaptive Data Analysis, 2009, 1: 1-41.
[51]	YEH J R, SHIEH J S, HUANG N E. Complementary ensemble empirical mode decomposition: a novel noise enhanced data analysis method[J]. Advances in Adaptive Data Analysis, 2010, 2(2): 135-156.
[52]	TORRES M E, COLOMINAS M A, SCHLOTTHAUER G, et al. A complete ensemble empirical mode decomposition with adaptive noise[J]. 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2011: 4144-4147.
[53]	COLOMINAS M A, SCHLOTTHAUER G, TORRES M E. Improved complete ensemble EMD: a suitable tool for biomedical signal processing[J]. Biomedical Signal Processing and Control, 2014, 14: 19-29.
[54]	RILLING G, FLANDRIN P, GONCALVES P, et al. Bivariate empirical mode decomposition[J]. IEEE Signal Processing Letters, 2007, 14(12): 936-939.
[55]	REHMAN N, MANDIC D P. Multivariate empirical mode decomposition[J]. Proceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences, 2010, 466(2117): 1291-1302.
[56]	WANG J L, LI Z J. Extreme-point symmetric mode decomposition method for data analysis[J]. Advances in Adaptive Data Analysis, 2013, 5(3): 1137-1137.
[57]	WANG Y H, YEH C H, YOUNG H, et al. On the computational complexity of the empirical mode decomposition algorithm[J]. Physica A Statistical Mechanics & Its Applications, 2014, 400: 159-167.
[58]	LI H, ZHI L, WEI M. A time varying filter approach for empirical mode decomposition[J]. Signal Processing, 2017, 138: 146-158.
[59]	DRAGOMIRETSKIY K, ZOSSO D. Variational mode decomposition[J]. IEEE Transactions on Signal Processing, 2014, 62(3): 531-544.
[60]	ZHANG C, ZHOU J Z, LI C S, et al. A compound structure of ELM based on feature selection and parameter optimization using hybrid backtracking search algorithm for wind speed forecasting[J]. Energy Conversion and Management, 2017, 143: 360-376.
[61]	LIU Y S, YANG C H, HUANG K K, et al. Non-ferrous metals price forecasting based on variational mode decomposition and LSTM network[J]. Knowledge-Based Systems, 2019, 188(5): 105006.
[62]	李祥, 彭玲, 邵静, 等. 基于小波分解和ARMA模型的空气污染预报研究[J].环境工程, 2016, 34(8): 110-113 ,134.
[63]	尹建光, 彭飞, 谢连科, 等. 基于小波分解与自适应多级残差修正的最小二乘支持向量回归预测模型的PM_2.5浓度预测[J]. 环境科学学报, 2018, 38(5): 2090-2098.
[64]	FENG X, LI Q, ZHU Y J, et al. Artificial neural networks forecasting of PM_2.5 pollution using air mass trajectory based geographic model and wavelet transformation[J]. Atmospheric Environment, 2015, 107: 118-128.
[65]	刘炳春, 陈佳丽, 郭晓玲, 等. 基于DWT-GRU模型的天津市NO₂浓度预测研究[J]. 环境科学与技术, 2020, 43(6): 94-100.
[66]	QIAO W B, WANG Y N, ZHANG J Z, et al. An innovative coupled model in view of wavelet transform for predicting short-term PM₁₀ concentration[J]. Journal of Environmental Management, 2021, 289: 112438.
[67]	SU X, AN J, ZHANG Y, et al. Prediction of ozone hourly concentrations by support vector machine and kernel extreme learning machine using wavelet transformation and partial least squares methods[J]. Atmospheric Pollution Research, 2020, 11(6): 51-60.
[68]	LIU H, LONG Z, DUAN Z, et al. A new model using multiple feature clustering and neural networks for forecasting hourly PM_2.5 concentrations, and its applications in China[J]. Engineering, 2020, 6(8): 944-956.
[69]	KIM J, WANG X, KANG C, et al. Forecasting air pollutant concentration using a novel spatiotemporal deep learning model based on clustering, feature selection and empirical wavelet transform[J]. Science of the Total Environment, 2021, 801: 149654.
[70]	LIU H, YANG R. A spatial multi-resolution multi-objective data-driven ensemble model for multi-step air quality index forecasting based on real-time decomposition[J]. Computers in Industry, 2021, 125: 103387.
[71]	LIU H, JIN K R, DUAN Z. Air PM_2.5 concentration multi-step forecasting using a new hybrid modeling method: comparing cases for four cities in China[J]. Atmospheric Pollution Research, 2019, 10(5): 1588-1600.
[72]	ZHU S L, LIAN X Y, LIU H X, et al. Daily air quality index forecasting with hybrid models: a case in China[J]. Environmental Pollution, 2017, 231: 1232-1244.
[73]	HUANG G Y, LI X Y, ZHANG B, et al. PM_2.5 Concentration forecasting at surface monitoring sites using GRU neural network based on empirical mode decomposition[J]. Science of the Total Environment, 2021, 768(3): 144516.
[74]	蒋洪迅, 闫超超, 张立峰. 基于时序分解和神经网络的PM_2.5浓度预测研究:以沈阳市为例[J]. 系统科学与数学, 2021, 41(12): 3446-3460.
[75]	TENG M F, LI S W, XING J, et al. 24-hour prediction of PM_2.5 concentrations by combining empirical mode decomposition and bidirectional long short-term memory neural network[J]. Science of the Total Environment, 2022,15: 153276.
[76]	WANG Z C, CHEN L R, DING Z N, et al. An enhanced interval PM_2.5 concentration forecasting model based on BEMD and MLP^I with influencing factors[J]. Atmospheric Environment, 2020, 223: 117200.
[77]	YUAN W Y, WANG K Q, BO X, et al. A novel multi-factor & multi-scale method for PM_2.5 concentration forecasting[J]. Environmental Pollution, 2019, 255: 113187.
[78]	QIN S S, LIU F, WANG J Z, et al. Analysis and forecasting of the particulate matter (PM) concentration levels over four major cities of China using hybrid models[J]. Atmospheric Environment, 2014, 98: 665-675.
[79]	翁克瑞, 刘淼, 刘钱. TPE-XGBOOST与LassoLars组合下PM_2.5浓度分解集成预测模型研究[J]. 系统工程理论与实践, 2020, 40(3): 748-760.
[80]	NIU M F, KAI G, SUN S L, et al. Application of decomposition-ensemble learning paradigm with phase space reconstruction for day-ahead PM_2.5 concentration forecasting[J]. Journal of Environmental Management, 2017, 196: 110-118.
[81]	BAI Y, ZENG B, LI C, et al. An ensemble long short-term memory neural network for hourly PM_2.5 concentration forecasting[J]. Chemosphere, 2019, 222: 286-294.
[82]	SONG C, FU X S. Research on different weight combination in air quality forecasting models[J]. Journal of Cleaner Production, 2020, 261: 121169.
[83]	ZHU S L, QIU X L, YIN Y R, et al. Two-step-hybrid model based on data preprocessing and intelligent optimization algorithms (CS and GWO) for NO₂ and SO₂ forecasting[J]. Atmospheric Pollution Research, 2019, 10(4): 1326-1335.
[84]	ZHU S L, WANG X L, MEI D S, et al. CEEMD-MR-hybrid model based on sample entropy and random forest for SO₂ prediction[J]. Atmospheric Pollution Research, 2022, 13(3): 101358.
[85]	梁涛, 谢高锋, 米大斌, 等.基于CEEMDAN-SE和LSTM神经网络的PM₁₀浓度预测[J]. 环境工程, 2020, 38(2): 107-113.
[86]	JIANG F X, ZHANG C Y, SUN S L, et al. Forecasting hourly PM_2.5 based on deep temporal convolutional neural network and decomposition method[J]. Applied Soft Computing, 2021, 113: 107988.
[87]	LI R R, DONG Y Q, ZHU Z J, et al. A dynamic evaluation framework for ambient air pollution monitoring[J]. Applied Mathematical Modelling, 2019, 65: 52-71.
[88]	XIAO Y T, WANG X K, WANG J Q, et al. An adaptive decomposition and ensemble model for short-term air pollutant concentration forecast using ICEEMDAN-ICA[J]. Technological Forecasting and Social Change, 2021, 166: 120655.
[89]	LUO H Y, WANG D Y, YUE C Q, et al. Research and application of a novel hybrid decomposition-ensemble learning paradigm with error correction for daily PM₁₀ forecasting[J]. Atmospheric Research, 2018, 201: 34-45.
[90]	SUN W, LI Z Q. Hourly PM_2.5 concentration forecasting based on mode decomposition-recombination technique and ensemble learning approach in severe haze episodes of China[J]. Journal of Cleaner Production, 2020, 263: 121442.
[91]	王建州, 杨文栋. 基于非线性修正策略的空气质量预警系统研究[J]. 系统工程理论与实践, 2019, 39(8): 2138-2151.
[92]	秦喜文, 王强进, 王新民, 等. 基于VMD和LSTM方法的北京市PM_2.5短期预测[J]. 吉林大学学报(地球科学版), 2022, 52(1): 214-221.
[93]	XU Y N, LIU H, DUAN Z. A novel hybrid model for multi-step daily AQI forecasting driven by air pollution big data[J]. Air Quality, Atmosphere & Health, 2020, 13(2): 197-207.
[94]	蒋锋, 乔雅倩. 基于样本熵和优化极限学习机的PM_2.5浓度预测[J]. 统计与决策, 2021, 37(3): 166-171.
[95]	GUO H L, GUO Y L, ZHANG W Y, et al. Research on a novel hybrid decomposition-ensemble learning paradigm based on VMD and IWOA for PM_2.5 forecasting[J]. International Journal of Environmental Research and Public Health, 2021, 18(3): 1-20.
[96]	WANG C, ZHANG H L, MA P. Wind power forecasting based on singular spectrum analysis and a new hybrid Laguerre neural network[J]. Applied Energy,2020, 259: 114139.
[97]	SINVALDO R M, LEANDRO S C. Wind speed forecasting approach based on singular spectrum analysis and adaptive neuro fuzzy inference system[J]. Renewable Energy, 2018, 126: 736-754.
[98]	陈荣, 梁昌勇, 葛立新. 基于SEA的AGA-SVR节假日客流量预测方法研究[J]. 旅游科学, 2016, 30(5): 12-23.
[99]	GUO Z H, JIE W, LU H Y, et al. A case study on a hybrid wind speed forecasting method using BP neural network[J]. Knowledge-Based Systems, 2011, 24(7): 1048-1056.
[100]	ALADAǦ E. Forecasting of particulate matter with a hybrid ARIMA model based on wavelet transformation and seasonal adjustment[J]. Urban Climate, 2021, 39: 100930.
[101]	YANG Z S, WANG J. A new air quality monitoring and early warning system: air quality assessment and air pollutant concentration prediction[J]. Environmental Research, 2017, 158: 105-117.
[102]	ZHU S L, SUN J N, LIU Y F, et al. The air quality index trend forecasting based on improved error correction model and data preprocessing for 17 port cities in China[J]. Chemosphere, 2020, 252: 126474.
[103]	WANG D Y, WEI S, LUO H Y, et al. A novel hybrid model for air quality index forecasting based on two-phase decomposition technique and modified extreme learning machine[J]. Science of the Total Environment, 2017, 580: 719-733.
[104]	WANG D Y, LIU Y L, LUO H Y, et al. Day-Ahead PM_2.5 concentration forecasting using WT-VMD based decomposition method and back propagation neural network improved by differential evolution[J]. International Journal of Environmental Research and Public Health, 2017, 14(7): 764.
[105]	罗宏远, 王德运, 刘艳玲, 等. 基于二层分解技术和改进极限学习机模型的PM_2.5浓度预测研究[J]. 系统工程理论与实践, 2018, 38(5): 1321-1330.
[106]	GAN K, SUN S L, WANG S Y, et al. A secondary-decomposition-ensemble learning paradigm for forecasting PM_2.5 concentration[J]. Atmospheric Pollution Research, 2018, 9(6): 989-999.
[107]	WU Q L, LIN H X. A novel optimal-hybrid model for daily air quality index prediction considering air pollutant factors[J]. Science of the Total Environment, 2019, 683: 808-821.
[108]	JIANG F, QIAO Y Q, JIANG X C, et al. MultiStep ahead forecasting for hourly PM₁₀ and PM_2.5 based on two-stage decomposition embedded sample entropy and group teacher optimization algorithm[J]. Atmosphere, 2021, 12(1): 64.
[109]	LIU H, ZHANG X Y. AQI time series prediction based on a hybrid data decomposition and echo state networks[J]. Environmental Science and Pollution Research, 2021, 28(37): 51160-51182.
[110]	SUN W, XU Z W. A hybrid daily PM_2.5 concentration prediction model based on secondary decomposition algorithm, mode recombination technique and deep learning[J]. Stochastic Environmental Research and Risk Assessment, 2022, 36(4): 1143-1162.
[111]	ZHOU J G, XU Z T, WANG S G. A novel dual-scale ensemble learning paradigm with error correction for predicting daily ozone concentration based on multi-decomposition process and intelligent algorithm optimization, and its application in heavily polluted regions of China[J]. Atmospheric Pollution Research, 2022, 13(2): 101306.