Skip to main content
SpringerLink
Log in

A novel hybrid algorithm with static and dynamic models for air quality index forecasting

  • Original Paper
  • Published:
Nonlinear Dynamics Aims and scope Submit manuscript

Abstract

Two data-driven algorithms, back propagation neural network (BPNN) and support vector regression (SVR), are adopted to predict air quality index (AQI) in Jiangsu Province. Meanwhile, the static model, the dynamic model of daily training and the half-daily training are established to validate the performance of algorithms comprehensively. The fundamental advantage of support vector is that less data in the full set is selected to efficiently capture the whole characteristics, whereas BPNN is more accurate in description of the high dimensional models since the parameters are well trained. The comparisons between two algorithms for the above models demonstrate that BPNN outperforms SVR in terms of accuracy since most of the mean absolute percentage errors of BPNN are less than 10%, which decrease 3% compared with that of SVR, whereas the computational cost of SVR is much less than that of BPNN. Furthermore, a novel hybrid model, the SVR-BPNN model, is proposed to further predict and analyze the AQI, which performs as fairly well as BPNN but is less time-consuming.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6

Similar content being viewed by others

Data availability

Data is provided on the site https://github.com/barrel-0314/AQIdata.

References

  1. Yin, Z., Wang, H.: Statistical prediction of winter haze days in the north China plain using the generalized additive model. J. Appl. Meteorol. Climatol. 56, 2411–2419 (2017)

    Article  Google Scholar 

  2. Cheng, K.: Spatial overflow effect of haze pollution in China and its influencing factors. Nature Environ. Pollut. Technol. 15, 1409–1416 (2016)

    Google Scholar 

  3. Shi, Y., Matsunaga, T., Yamaguchi, Y., et al.: Long-term trends and spatial patterns of satellite-retrieved PM2.5 concentrations in South and Southeast Asia from 1999 to 2014. Sci. Total Environ. 615, 177–186 (2018)

    Article  Google Scholar 

  4. Wang, H., Wang, J., Wang, X.: An AQI level forecasting model using chi-square test and BP neural network. In: Proceedings of the 2nd International Conference on Intelligent Information Processing, vol. 24, pp. 1–6 (2017)

  5. Li, H., You, S., Zhang, H., et al.: Modelling of AQI related to building space heating energy demand based on big data analytics. Appl. Energy 203, 57–71 (2017)

  6. Zhang, Q., Laurent, B., Velay-Lasry, F., et al.: An air quality forecasting system in Beijing-application to the study of dust storm events in China in May 2008. J. Environ. Sci. 24(1), 102–111 (2012)

    Article  Google Scholar 

  7. Battista, G., De Lieto, Vollaro R.: Correlation between air pollution and weather data in urban areas: assessment of the city of Rome (Italy) as spatially and temporally independent regarding pollutants. Atmos. Environ. 165, 240–247 (2017)

    Article  Google Scholar 

  8. Li, M.: Haze pollution control strategies in China from the perspective of energy conservation and emission reduction. Nature Environ. Pollut. Technol. 15(3), 887–893 (2016)

    Google Scholar 

  9. Wei, J., Zhu, W., Liu, D., Han, X.: The temporal and spatial distribution of hazy days in cities of Jiangsu province China and an analysis of its causes. Adv. Meteorol. 2016, 1–11 (2016)

    Google Scholar 

  10. Koe, L., Jr., A., McGregor, J.: Application of DARLAM to regional haze modeling. Pure Appl. Geophys. 160, 189–204 (2003)

  11. Habtemichael, F., Cetin, M.: Short-term traffic flow rate forecasting based on identifying similar traffic patterns. Transp. Res. Part C 66, 61–78 (2016)

    Article  Google Scholar 

  12. Nair, S., Tan, L., Ramli, N., et al.: A decision tree for differentiating multiple system atrophy from Parkinson’s disease using 3-T MR imaging. Eur. Radiol. 23, 1459–1466 (2013)

    Article  Google Scholar 

  13. Hickey, S.: Naive Bayes classification of public health data with greedy feature selection. Commun. IIMA 13(2), 87–98 (2013)

    Google Scholar 

  14. Chen, J., Zhou, Y., Xie, Y.: Distribution network optimal planning based on improved Partheno-Genetic algorithm. In: Proceedings of the 2009 International Workshop on Information Security and Application, pp. 649-652 (2009)

  15. Leung, S., Liang, G., Solna, K., Zhao, H.: Expectation-maximization algorithm with local adaptivity. SIAM J. Imaging Sci. 2(3), 834–857 (2009)

    Article  MathSciNet  MATH  Google Scholar 

  16. Yang, X., Zhang, Z., Zhang, Z., et al.: A long-term prediction model of Beijing haze episodes using time series analysis. Comput. Intell. Neurosci. 2016, 1–7 (2016)

    Article  Google Scholar 

  17. Schurholz, D., Nurgazy, M., Zaslavsky, A., et al.: MyAQI: context-aware outdoor air pollution monitoring system. In: Proceedings of the 9th International Conference on the Internet of Things, pp 1–8 (2019)

  18. Hu, B., Xu, J., Gao, H., et al.: Modified BP neural network model is used for odd-even discrimination of integer number. Appl. Mech. Mater. 423, 2675–2678 (2013)

    Article  Google Scholar 

  19. Yi, X., Zhang, J., Wang, Z. et al.: Deep distributed fusion network for air quality prediction. In: Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pp. 965–973 (2018)

  20. Cui, K., Qin, X.: Virtual reality research of the dynamic characteristics of soft soil under metro vibration loads based on BP neural networks. Neural Comput. Appl. 29, 1233–1242 (2018)

  21. Lin, Y., Chen, D., Chen, M., et al.: A precise BP neural network-based online model predictive control strategy for die forging hydraulic press machine. Neural Comput. Appl. 29, 585–596 (2018)

    Article  MathSciNet  Google Scholar 

  22. Li, J., Zhao, D., Ge, B., et al.: A link prediction method for heterogeneous networks based on BP neural network. Phys. A Stat. Mech. Appl. 495, 1–17 (2018)

    Article  Google Scholar 

  23. Zhou, C., Tao, J.: Adaptive combination forecasting model for China’s logistics freight volume based on an improved PSO-BP neural network. Kybernetes 44(4), 646–666 (2015)

  24. Li, G., Wang, Q., Li, H.: Network traffic prediction based on wavelet neural network improved by genetic algorithm. Int. Inf. Inst. 16(2A), 1047–1052 (2013)

    Google Scholar 

  25. Mao, Y.: Localization algorithm for mobile nodes in wireless sensor networks based on subsection learning of double-layers BP neural network. In: Proceedings of the 2013 Fifth International Conference on Multimedia Information Networking and Security (2013)

  26. He, J., Tang, X., Gong, P., et al.: Rapid radionuclide identification algorithm based on the discrete cosine transform and BP neural network. Ann. Nuclear Energy 112, 1–8 (2018)

    Article  Google Scholar 

  27. Song, P., Zhang, J., Zhang, Y.: Harmonic detection based on genetic BP neural network. Appl. Mech. Mater. 427, 1892–1895 (2013)

    Article  Google Scholar 

  28. Liu, L., Zhao, T., Ma, M., Wang, Y.: A new gene regulatory network model based on BP algorithm for interrogating differentially expressed genes of Sea Urchin. SpringerPlus 5, 1911 (2016)

    Article  Google Scholar 

  29. Li, C., Yang, Z., Yan, H., Wang, T.: The application and research of the GA-BP neural network algorithm in the MBR membrane fouling. Abstr. Appl. Anal. 2014, 1–8 (2014)

    Google Scholar 

  30. Sun, J., Shang, Z., Li, H.: Imbalance-oriented SVM methods for financial distress prediction: a comparative study among the new SB-SVM-ensemble method and traditional methods. J. Oper. Res. Soc. 65, 1905–1919 (2014)

    Article  Google Scholar 

  31. Keerthi, S., Shevade, S., Bhattacharyya, C., Murthy, K.: Improvements to Platt’s SMO algorithm for SVM classifier design. Neural Comput. 13, 637–649 (2001)

    Article  MATH  Google Scholar 

  32. Cherkassky, V., Ma, Y.: Practical selection of SVM parameters and noise estimation for SVM regression. Neural Netw. 17, 113–126 (2004)

    Article  MATH  Google Scholar 

  33. Schuldt, C., Laptev, I., Caputo, B.: Recognizing human actions: a local SVM approach. In: Proceedings of the 17th International Conference on Pattern Recognition (2004)

  34. Foody, G., Mathur, A.: Toward intelligent training of supervised image classifications: directing training data acquisition for SVM classification. Remote Sens. Environ. 93, 107–117 (2004)

    Article  Google Scholar 

  35. Foody, G., Mathur, A.: The use of small training sets containing mixed pixels for accurate hard image classification: training on mixed spectral responses for classification by a SVM. Remote Sens. Environ. 103, 179–189 (2006)

  36. Li, X., Kong, J.: Application of GA-SVM method with parameter optimization for landslide development prediction. Nat. Hazards Earth Syst. Sci. 14, 525–533 (2014)

    Article  Google Scholar 

  37. Wang, Q., Zhu, W., Wang, B.: Three-dimensional SVM with latent variable: application for detection of lung lesions in CT Images. J. Med. Syst. 39(1), 171 (2015)

    Article  MathSciNet  Google Scholar 

  38. Chen, H., Yang, B., Wang, G., et al.: A three-stage expert system based on support vector machines for thyroid disease diagnosis. J. Med. Syst. 36, 1953–1963 (2012)

    Article  Google Scholar 

  39. Silver, A., Lungren, M., Johnson, M., et al.: Using support vector machines to optimally classify rotator cuff strength data and quantify post-operative strength in rotator cuff tear patients. J. Biomech. 39, 973–979 (2006)

  40. Subasi, A.: Classification of EMG signals using PSO optimized SVM for diagnosis of neuromuscular disorders. Comput. Biol. Med. 43, 576–586 (2013)

  41. Nielsen, M.: Neural networks and deep learning. Determination press (2015)

  42. Deng, N., Tian, Y.: Support Vectors Machine: Theory, Algorithm And Development. Science press, Beijing (2009)

Download references

Acknowledgements

The research is supported by the National Natural Science Foundation of China (Grant nos. 62273092, 11701081) and the Key Project of Natural Science Foundation of China (Grant No. 61833005).

Author information

Authors and Affiliations

  1. School of Mathematics, Southeast University, Nanjing, 211189, China

    Xuan Zhao, Zhenhai Wu & Yiheng Wei

  2. School of Cyber Science and Engineering, Southeast University, Nanjing, 211189, China

    Jingyi Qiu

Authors
  1. Xuan Zhao
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Zhenhai Wu
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Jingyi Qiu
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Yiheng Wei
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Xuan Zhao.

Ethics declarations

Conflict of interest

The authors declare that there is no conflict of interests regarding the publication of this paper

Additional information

Publisher's Note

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

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Zhao, X., Wu, Z., Qiu, J. et al. A novel hybrid algorithm with static and dynamic models for air quality index forecasting. Nonlinear Dyn 111, 13187–13199 (2023). https://doi.org/10.1007/s11071-023-08552-1

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11071-023-08552-1

Keywords

Search

Navigation