Skip to main content

AQI time series prediction based on a hybrid data decomposition and echo state networks

Environmental Science and Pollution Research volume 28, pages 51160–51182 (2021)Cite this article

Abstract

A hybrid AQI time series prediction model is proposed based on EWT-SE-VMD secondary decomposition, ICA (imperialist competitive algorithm) feature selection, and ESN (echo state network) neural network. Firstly, EWT (empirical wavelet transform) and VMD (variational mode decomposition) are used to decompose the original AQI time series into several stable and reliable subseries. Then, the ICA is used to select features of the above subseries for the ESN prediction model. Finally, the optimized feature variables are put into the ESN deep network to establish a prediction model of each AQI subseries and obtain the future AQI index. According to the experimental results of the daily AQI series in Beijing, Tianjin, and Shijiazhuang, we find that (a) among all decomposition methods, the proposed secondary decomposition method (EWT-SE-VMD) performs best in processing data; (b) it is proved that the proposed hybrid model has broad application prospect and research value in the AQI prediction field.

This is a preview of subscription content, access via your institution.

Access options

Buy single article

Instant access to the full article PDF.

43,34 €

Price includes VAT (Finland)
Tax calculation will be finalised during checkout.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14
Fig. 15
Fig. 16
Fig. 17.
Fig. 18
Fig. 19
Fig. 20
Fig. 21
Fig. 22
Fig. 23
Fig. 24
Fig. 25

Data Availability

Not applicable.

Abbreviations

AQI:

Air quality index

ARIMA:

Autoregressive integrated moving averaging

DCT:

Discrete cosine transform

VMD:

Variational mode decomposition

EMD:

Empirical mode decomposition

WD:

Wavelet decomposition

GA:

Genetic algorithm

PSO:

Particle swarm optimization

SVM:

Support vector machine

MLP:

Multi-layer perceptron

CNN:

Convolutional neural network

LSTM:

Long short-term memory

EWT-SE-VMD:

Empirical wavelet transform-sample entropy-variational mode decomposition

ICA:

Imperialist competitive algorithm

ESN:

Echo state network

EWT:

Empirical wavelet transform

SE:

Sample entropy

GMDH:

Group method of data handling

RBF:

Radial basis function neuron network

ELMAN:

Elman neural network

ELM:

Extreme learning machine

BP:

Back propagation neural network

GRNN:

Generalized regression neural network

NAR:

Nonlinear autoregressive neural network

MAE:

Mean absolute error

MAPE:

Mean absolute percentage error

RMSE:

Root mean square error

MG:

Geometric mean bias

FAC2:

Fraction of predictions within a factor of two of observations

EWT-MAEGA-NARX:

Empirical wavelet transform-multi-agent evolutionary genetic algorithm-nonlinear autoregressive network with exogenous inputs

DWT-ARIMA-ANN:

Discrete wavelet transform-autoregressive integrated moving averaging-artificial neural network

FEEMD-VMD-CS-ELM:

Fast ensemble empirical mode decomposition-variational mode decomposition

Attention-LSTM:

Long short-term memory with attention

WRF-Chem:

Weather Research and Forecasting model coupled to Chemistry

References

  • Atashpaz-Gargari E, Lucas C (2007) Imperialist competitive algorithm: an algorithm for optimization inspired by imperialistic competition, 2007 IEEE congress on evolutionary computation. IEEE:4661–4667

  • Bai Y, Li Y, Wang X, Xie J, Li C (2016) Air pollutants concentrations forecasting using back propagation neural network based on wavelet decomposition with meteorological conditions. Atmospheric Pollut Res 7:557–566

    Article  Google Scholar 

  • Brook RD, Rajagopalan S, Pope CA III, Brook JR, Bhatnagar A, Diez-Roux AV, Holguin F, Hong Y, Luepker RV, Mittleman MA (2010) Particulate matter air pollution and cardiovascular disease: an update to the scientific statement from the American Heart Association. Circulation 121:2331–2378

    CAS  Article  Google Scholar 

  • Cao J, Yang C, Li J, Chen R, Chen B, Gu D, Kan H (2011) Association between long-term exposure to outdoor air pollution and mortality in China: a cohort study. J Hazard Mater 186:1594–1600

    CAS  Article  Google Scholar 

  • Chai T, Draxler RR (2014) Root mean square error (RMSE) or mean absolute error (MAE)? – arguments against avoiding RMSE in the literature. Geosci Model Dev 7:1247–1250

    Article  Google Scholar 

  • Chandrashekar G, Sahin F (2014) A survey on feature selection methods. Comput Electr Eng 40:16–28

    Article  Google Scholar 

  • Chang JC, Hanna SR (2004) Air quality model performance evaluation. Meteorog Atmos Phys 87:167–196

    Article  Google Scholar 

  • Chen W, Tang H, Zhao H (2015) Diurnal, weekly and monthly spatial variations of air pollutants and air quality of Beijing. Atmos Environ 119:21–34

    CAS  Article  Google Scholar 

  • Cheng N, Li Y, Cheng B, Wang X, Meng F, Wang Q, Qiu Q (2018) Comparisons of two serious air pollution episodes in winter and summer in Beijing. J Environ Sci 69:141–154

    Article  Google Scholar 

  • Cheng J, Su J, Cui T, Li X, Dong X, Sun F, Yang Y, Tong D, Zheng Y, Li Y (2019a) Dominant role of emission reduction in PM 2.5 air quality improvement in Beijing during 2013–2017: a model-based decomposition analysis. Atmos Chem Phys 19:6125–6146

    CAS  Article  Google Scholar 

  • Cheng Y, Zhang H, Liu Z, Chen L, Wang P (2019b) Hybrid algorithm for short-term forecasting of PM2.5 in China. Atmos Environ 200:264–279

    CAS  Article  Google Scholar 

  • Coker E, Kizito S (2018) A narrative review on the human health effects of ambient air pollution in Sub-Saharan Africa: an urgent need for health effects studies. Int J Environ Res Public Health 15:427

    Article  CAS  Google Scholar 

  • Gilles J (2013) Empirical wavelet transform. IEEE Trans. Signal Process 61:3999–4010

    Google Scholar 

  • Guo H, Wang Y, Zhang H (2017) Characterization of criteria air pollutants in Beijing during 2014–2015. Environ Res 154:334–344

    CAS  Article  Google Scholar 

  • Huang CJ, Kuo PH (2018) A deep CNN-LSTM model for particulate matter (PM2.5) Forecasting in Smart Cities. Sensors 18:2220

    Article  Google Scholar 

  • Jaeger H, Haas H (2004) Harnessing nonlinearity: predicting chaotic systems and saving energy in wireless communication. Science 304:78–80

    CAS  Article  Google Scholar 

  • Janssen S, Guerreiro C, Viaene P, Georgieva E, Thunis P (2017) Guidance document on modelling quality objectives and benchmarking. FAIRMODE:1–58

  • Jiang P, Liu Z, Niu X, Zhang L (2020) A combined forecasting system based on statistical method, artificial neural networks, and deep learning methods for short-term wind speed forecasting. Energy:119361

  • Khandelwal I, Adhikari R, Verma G (2015) Time series forecasting using hybrid ARIMA and ANN models based on DWT decomposition. Procedia Comput Sci 48:173–179

    Article  Google Scholar 

  • Lei MT, Monjardino J, Mendes L, Gonçalves D, Ferreira F (2019) Macao air quality forecast using statistical methods. Air Qual Atmos Health 12:1049–1057

    CAS  Article  Google Scholar 

  • Li X, Peng L, Hu Y, Shao J, Chi T (2016) Deep learning architecture for air quality predictions. Environ Sci Pollut Res 23:22408–22417

    Article  Google Scholar 

  • Li J, Gao W, Cao L, Xiao Y, Zhang Y, Zhao S, Liu Z, Liu Z, Tang G, Ji D, Hu B, Song T, He L, Hu M, Wang Y (2021) Significant changes in autumn and winter aerosol composition and sources in Beijing from 2012 to 2018: Effects of clean air actions. Environ Pollut 268:115855

    CAS  Article  Google Scholar 

  • Lin B, Zhu J (2018) Changes in urban air quality during urbanization in China. J Clean Prod 188:312–321

    CAS  Article  Google Scholar 

  • Liu H, Duan Z, F-z H, Y-f L (2018a) Big multi-step wind speed forecasting model based on secondary decomposition, ensemble method and error correction algorithm. Energy Convers Manag 156:525–541

    Article  Google Scholar 

  • Liu Y, Wu J, Yu D, Hao R (2018b) Understanding the patterns and drivers of air pollution on multiple time scales: the case of northern China. Environ Manag 61:1048–1061

    Article  Google Scholar 

  • Liu H, Wu H, Lv X, Ren Z, Liu M, Li Y, Shi H (2019) An intelligent hybrid model for air pollutant concentrations forecasting: case of Beijing in China. Sustain Cities Soc 47:101471

    Article  Google Scholar 

  • Luo H, Wang D, Yue C, Liu Y, Guo H (2018) Research and application of a novel hybrid decomposition-ensemble learning paradigm with error correction for daily PM10 forecasting. Atmos Res 201:34–45

    CAS  Article  Google Scholar 

  • Lv M, Li Y, Chen L, Chen T (2019) Air quality estimation by exploiting terrain features and multi-view transfer semi-supervised regression. Inf Sci 483:82–95

    Article  Google Scholar 

  • Madaan D, Dua R, Mukherjee P, Lall B (2019) Vayuanukulani: adaptive memory networks for air pollution forecasting. arXiv preprint arXiv 1904.03977

  • Nieto PG, Lasheras FS, García-Gonzalo E, de Cos JF (2018) PM10 concentration forecasting in the metropolitan area of Oviedo (Northern Spain) using models based on SVM, MLP, VARMA and ARIMA: a case study. Sci Total Environ 621:753–761

    Article  CAS  Google Scholar 

  • Russo A, Lind PG, Raischel F, Trigo R, Mendes M (2015) Neural network forecast of daily pollution concentration using optimal meteorological data at synoptic and local scales. Atmospheric Pollut Res 6:540–549

    CAS  Article  Google Scholar 

  • Song C, Wu L, Xie Y, He J, Chen X, Wang T, Lin Y, Jin T, Wang A, Liu Y, Dai Q, Liu B, Wang YN, Mao H (2017) Air pollution in China: status and spatiotemporal variations. Environ Pollut 227:334–347

    CAS  Article  Google Scholar 

  • Sun W, Sun J (2017) Daily PM 2.5 concentration prediction based on principal component analysis and LSSVM optimized by cuckoo search algorithm. J Environ Manag 188:144–152

    CAS  Article  Google Scholar 

  • Wang Y, Zhang X, Arimoto R (2006) The contribution from distant dust sources to the atmospheric particulate matter loadings at Xian, China during spring. Sci Total Environ 368:875–883

    CAS  Article  Google Scholar 

  • Wang Y, Liu H, Mao G, Zuo J, Ma J (2017) Inter-regional and sectoral linkage analysis of air pollution in Beijing–Tianjin–Hebei (Jing-Jin-Ji) urban agglomeration of China. J Clean Prod 165:1436–1444

    CAS  Article  Google Scholar 

  • Wang Z, Chen L, Zhu J, Chen H, Yuan H (2020) Double decomposition and optimal combination ensemble learning approach for interval-valued AQI forecasting using streaming data. Environ Sci Pollut Res 27:37802–37817

    Article  Google Scholar 

  • Willmott CJ, Matsuura K (2005) Advantages of the mean absolute error (MAE) over the root mean square error (RMSE) in assessing average model performance. Clim Res 30:79–82

    Article  Google Scholar 

  • Wu Q, Lin H (2019) Daily urban air quality index forecasting based on variational mode decomposition, sample entropy and LSTM neural network. Sustain Cities Soc 50:101657

    Article  Google Scholar 

  • Wu W, Zhao S, Zhu C, Jiang J (2015) A comparative study of urban expansion in Beijing, Tianjin and Shijiazhuang over the past three decades. Landsc Urban Plan 134:93–106

    Article  Google Scholar 

  • Wu H, Liu H, Duan Z (2020) PM2.5 concentrations forecasting using a new multi-objective feature selection and ensemble framework. Atmospheric Pollut Res 11:1187–1198

    CAS  Article  Google Scholar 

  • Xu L, Duan F, He K, Ma Y, Zhu L, Zheng Y, Huang T, Kimoto T, Ma T, Li H (2017) Characteristics of the secondary water-soluble ions in a typical autumn haze in Beijing. Environ Pollut 227:296–305

    CAS  Article  Google Scholar 

  • Xu W, Tian Y, Liu Y, Zhao B, Liu Y, Zhang X (2019) Understanding the spatial-temporal patterns and influential factors on air quality index: the case of north China. Int J Environ Res Public Health 16:2820

    Article  Google Scholar 

  • Yang Z (2020) DCT-based least-squares predictive model for hourly AQI fluctuation forecasting. J Environ Inf 36:58–69

    Google Scholar 

  • Yuan G, Yang W (2019) Evaluating China’s air pollution control policy with extended AQI indicator system: example of the Beijing-Tianjin-Hebei region. Sustainability 11:939

    CAS  Article  Google Scholar 

  • Zhan D, Kwan M-P, Zhang W, Yu X, Meng B, Liu Q (2018) The driving factors of air quality index in China. J Clean Prod 197:1342–1351

    CAS  Article  Google Scholar 

  • Zhang L, Lin J, Qiu R, Hu X, Zhang H, Chen Q, Tan H, Lin D, Wang J (2018) Trend analysis and forecast of PM2. 5 in Fuzhou, China using the ARIMA model. Ecol Indic 95:702–710

    CAS  Article  Google Scholar 

  • Zhang Z, Zeng Y, Yan K (2021) A hybrid deep learning technology for PM 2.5 air quality forecasting. Environ Sci Pollut Res:1–14

  • Zhu D, Cai C, Yang T, Zhou X (2018) A machine learning approach for air quality prediction: model regularization and optimization. Big data and cognitive computing 2:5

    Article  Google Scholar 

Download references

Funding

The study is fully supported by the National Natural Science Foundation of China (Grant No. 52072412), the Changsha Science & Technology Project (Grant No. KQ1707017), and the innovation driven project of the Central South University (2019CX005).

Author information

Affiliations

  1. Institute of Artificial Intelligence and Robotics (IAIR), Key Laboratory of Traffic Safety on Track of Ministry of Education, School of Traffic and Transportation Engineering, Central South University, Changsha, 410075, Hunan, China

    Hui Liu & Xinyu Zhang

Authors
  1. Hui Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Xinyu Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

Hui Liu: conceptualization; data curation; methodology; writing, original draft; writing, review and editing; and validation

Xinyu Zhang: data curation; methodology; and writing—original draft

Corresponding author

Correspondence to Hui Liu.

Ethics declarations

Ethics approval

Not applicable.

Consent to participate

Not applicable.

Consent for publication

Not applicable.

Competing interests

The authors declare no competing interests.

Additional information

Publisher’s note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Responsible Editor: Marcus Schulz

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Liu, H., Zhang, X. AQI time series prediction based on a hybrid data decomposition and echo state networks. Environ Sci Pollut Res 28, 51160–51182 (2021). https://doi.org/10.1007/s11356-021-14186-w

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11356-021-14186-w

Keywords

  • AQI prediction
  • Hybrid model
  • EWT-SE-VMD secondary decomposition
  • ICA feature selection
  • ESN networks