Skip to main content

Advertisement

Springer Nature Link
Log in

Efficient PM2.5 forecasting using geographical correlation based on integrated deep learning algorithms

  • Review Article
  • Published:
Neural Computing and Applications Aims and scope Submit manuscript

Abstract

This paper proposes a deep learning model that integrates a convolutional neural network and a gated recurrent unit with groups of neighboring stations to accurately predict PM2.5 concentrations at 25 stations in Seoul, South Korea. The deep learning model uses observations obtained from one Korea Meteorological Administration (KMA) station, 25 National Institute of Environmental Research (NIER) stations, and 28 automatic weather stations (AWSs) throughout Seoul. To train the deep learning model, we use all available meteorological and air quality data observed between 2015 and 2017. With the trained model, we predict PM2.5 concentrations at all 25 NIER stations in Seoul for 2018. This study also proposes a geographical polygon group model that determines the optimal number of neighboring NIER stations required to increase the accuracy of PM2.5 concentration predictions at the target station. Comparing the model measures for each of the 25 monitoring sites in 2018, we find that the geographical polygon group model achieves an index of agreement of 0.82–0.89 and a Pearson correlation coefficient of 0.70–0.83. Compared to the method using only meteorological and air quality data from one target station (average IOA = 0.77) to predict PM2.5 concentrations at the 25 stations in Seoul, the proposed method using geographical correlation-based neighboring NIER stations as polygonal groups (average IOA = 0.85) improves the PM2.5 prediction accuracy by an average of about 10%. This approach, based on deep learning, can be updated to predict air pollution or air quality indices up to several days in advance.

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

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

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
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12

Similar content being viewed by others

Explore related subjects

Discover the latest articles, news and stories from top researchers in related subjects.

References

  1. Bartell SM, Longhurst J, Tjoa T, Sioutas C, Delfino RJ (2013) Particulate air pollution, ambulatory heart rate variability, and cardiac arrhythmia in retirement community residents with coronary artery disease Environ Health Perspect 121(10):1135–1141

    Article  Google Scholar 

  2. Brauer M, Amann M, Burnett RT, Cohen v, Dentener F, Ezzati M, Thurston GD (2012) Exposure assessment for estimation of the global burden of disease attributable to outdoor air pollution Environ Sci Technol 46(2):652–660

    Article  Google Scholar 

  3. Crouse DL, Peters PA, Donkelaar van A, Goldberg MS, Villeneuve PJ, Brion O, Burnett RT (2012) Risk of nonaccidental and cardiovascular mortality in relation to long-term exposure to low concentrations of fine particulate matter: a Canadian national-level cohort study Environ Health Perspect 120(5):708–714

    Article  Google Scholar 

  4. Engel-Cox JA, Kim Oanh NT, Donkelaar van A, Martin RV, Zell E (2013) Toward the next generation of air quality monitoring: particulate matter. Atmos Environ 80:584–590

    Article  Google Scholar 

  5. Byun D, Schere KL (2006) Review of the governing equations, computational algorithms, and other components of the models-3 community multiscale air quality (CMAQ) modeling system. Appl Mech Rev 59:51–77

    Article  Google Scholar 

  6. Zhang Y, Bocquet M, Mallet V,Seigneur C, Baklanov A (2012) Real-time air quality forecasting, part II: state of the science, current research needs, and future prospects. Atmos Environ 60:656–676

    Article  Google Scholar 

  7. Slini T, Karatzas K, Moussiopoulos N (2001) Statistical analysis of environmental data as the basis of forecasting: an air quality application. Sci Total Environ 288:227–237

    Article  Google Scholar 

  8. Han LJ, Zhou WQ, Li WF, Li L (2014) Impact of urbanization level on urban air quality: a case of fine particles (PM2.5) in Chinese cities. Environ Pollut 194:163–170

    Article  Google Scholar 

  9. Pérez P, Trier A, Reyes J (2000) Prediction of PM2.5 concentrations several hours in advance using neural networks in Santiago. Chile Atmos Environ 34(8):1189–1196

    Article  Google Scholar 

  10. Perez P, Reyes J (2006) An integrated neural network model for PM10 forecasting. Atmos Environ 40(16):2845–2851

    Article  Google Scholar 

  11. Yildirim Y, Bayramoglu M (2006) Adaptive neuro-fuzzy based modelling for prediction of air pollution daily levels in city of Zonguldak. Chemosphere 63(9):1575–1582

    Article  Google Scholar 

  12. Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks. Proc Adv Neural Inf Process Syst 25:1090–1098

    Google Scholar 

  13. Pak U, Ma J, Ryu U, Ryom K, Juhyok U, Pak K, Pak C (2020) Deep learning-based PM25 prediction considering the spatiotemporal correlations: a case study of Beijing China. Sci Total Environ 699:10

    Article  Google Scholar 

  14. Zhang CY, Chen CP, Gan M, Chen L (2015) Predictive deep Boltzmann machine for multiperiod wind speed forecasting. IEEE Trans Sustainable Energy 6:1416–1425

    Article  Google Scholar 

  15. Li X, Peng L, Yao X, Cui S, Hu Y, You C, Chi T (2017) Long short-term memory neural network for air pollutant concentration predictions: method development and evaluation. Environ Pollut 231:997–1004

    Article  Google Scholar 

  16. 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 

  17. Li T, Shen H, Yuan Q, Zhang X, Zhang L (2017) estimating ground-level PM2.5 by fusing satellite and station observations: a geo-intelligent deep learning approach. Geophys Res Lett 44(23):11985–11993

    Article  Google Scholar 

  18. Eslami E, Choi Y, Lops Y, Sayeed A (2019) A real-time hourly ozone prediction system using deep convolutional neural network. Neural Comput Appl 8:1 5

    Google Scholar 

  19. Xu L, Yu Y, Yu J, Niu Z, Yin L (2013) Spatial distribution and sources identification of elements in PM2.5 among the coastal city group in the Western Taiwan Strait region, China. Sci Total Environ 442:77–85

    Article  Google Scholar 

  20. Wang YG, Ying Q, Hu J, Zhang H (2014) Spatial and temporal variations of six criteria air pollutants in 31 provincial capital cities in China during 2013–2014. Environ Int 73:413–422

    Article  Google Scholar 

  21. Zhao SP, Yu Y, Yin DY, He JJ, Liu N, Qu JJ, Xiao JH (2016) Annual and diurnal variations of gaseous and particulate pollutants in 31 provincial capital cities based on in situ air quality monitoring data from China National Environmental Monitoring Center. Envrion Int 86:92–106

    Article  Google Scholar 

  22. Hoff RM, Christopher SA (2009) Remote sensing of particulate pollution from space: have we reached the promised land? J Air Waste Manage 59:645–675

    Article  Google Scholar 

  23. Paciorek CJ, Liu Y (2008) Limitations of remotely-sensed aerosol as a spatial proxy for fine particulate matter. Environ Health Perspect 117:904–909

    Article  Google Scholar 

  24. Ma XY, Wang JY, Yu FQ, Jia HL, Hu YN (2016) Can MODIS AOD be employed to derive PM2.5 in Beijing–Tianjin–Hebei over China? Atmos Res 181:250–256

    Article  Google Scholar 

  25. Wu J, Li J, Peng J, Li W, Xu G, Dong C (2015) Applying land use regression model to estimate spatial variation of PM25 in Beijing, China. Environ Sci Pollut Res 22(9):7045–7061

    Article  Google Scholar 

  26. Schmidhuber J (2015) Deep learning in neural networks: an overview Neural Netw 61 85 117

    Article  Google Scholar 

  27. Cho K, van Merrienboer B, Gulcehre C, Bahdanau D, Bougares F, Schwenk H, Bengio Y (2014) Learning phrase representations using RNN encoder-decoder for statistical machine translation. In: Conference on empirical methods in natural language processing.

  28. Felix G, Jürgen S, Fred C (1999) Learning to forget: continual prediction with LSTM. In: Proceedings of the ICANN'99, IEE, London, pp 850–855

  29. Ravanelli M, Brakel P, Omologo M, Bengio Y (2018) Light gated recurrent units for speech recognition. IEEE Trans Emerg Top Comput Intell 2(2):92–102

    Article  Google Scholar 

  30. Pan R, Yang T, Cao J (2015) Missing data imputation by K nearest neighbors based on grey relational structure and mutual information. Appl Intell 43:614–632

    Article  Google Scholar 

  31. LeCun Y, Bengio Y (1995) Convolutional networks for images, speech, and time series. In: The handbook of brain theory and neural networks, vol 3361, no. 10

  32. Pouyaei A, Choi Y, Jung J, Sadeghi B, Song CH (2020) Concentration trajectory route of air pollution with an integrated langrangian model (C-TRAIL Model v1.0) derived from the community multiscale air quality model (CMAQ Model v5.2). Geosci Model Dev 13:3498–3505

    Article  Google Scholar 

  33. Jung J, Souri AH, Wong DC, Lee S, Jeon W, Kim J, Choi Y (2019) The impact of the direct effect of aerosols on meteorology and air quality using aerosol optical depth assimilation during the KORUS-AQ campaign. J Geophys Res Atmos. https://doi.org/10.1029/2019JD030641

  34. Souri AH, Choi Y, Pan S, Curci G, Nowlan C, Janz SJ, Kowalewski MG, Liu J, Herman JR, Weinheimer AJ (2018) First top-down estimates of anthropogenic NOx emissions using high-resolution airborne remote sensing observations. J Geophy Res Atmos. https://doi.org/10.1002/2017JD028009

  35. Souri AH, Choi Y, Jeon W, Kochanski A, Diao L, Mandel J, Bhave PV, Pan S (2017) Quantifying the impact of biomass burning emissions on major inorganic aerosols and their precursors in the US. J Geophys Res Atmos

  36. Eslami E, Salman AK, Choi Y, Sayeed A, Lops Y (2019) A data ensemble approach for real-time air quality forecasting using extremely randomized trees and deep neural networks. Neural Comput Appl. doi:https://doi.org/10.1007/s00521-019-04287-6

  37. Lops Y, Choi Y, Eslami E, Sayeed A (2019) Real-time 7-day forecast of pollen counts using a deep convolutional neural network. Neural Comput Appl. https://doi.org/10.1007/s00521-019-04665-0

  38. Sayeed A, Choi Y, Eslami E, Lops Y, Roy A, Jung J (2019) Using a deep convolutional neural network to predict 2017 ozone concentrations, 24 hours. Adv Neural Netw

  39. Kim H, Park I, Song C, Lee K, Yun J, Kim H, Jeon M, Lee J, Han K (2019) Development of a daily PM10 and PM2.5 prediction system using a deep long short-term memory neural network model. Atmos Chem Phys 19:12935–12951

    Article  Google Scholar 

  40. Biancofiore F, Busilacchio M, Verdecchia M (2017) Recursive neural network model for analysis and forecast of PM10 and PM2.5. Atmos Pollut Res 8(4):652̄–659

    Article  Google Scholar 

  41. Liu H, Wang XM, Pang JM (2013) Feasibility and difficulties of China’s new air quality standard compliance: PRD case of PM2.5 and ozone from, 2010 to 2025. Atmos Chem Phys 13(23)12013–12027

    Article  Google Scholar 

  42. Mchenry JN, Vukovich JM, Hsu NC (2015) Development and implementation of a remote-sensing and in situ data-assimilating version of CMAQ for operational PM2.5 forecasting. Part 1: MODIS aerosol optical depth (AOD) data-assimilation design and testing. J Air Waste Manag Assoc 65(12):1395–1412

    Article  Google Scholar 

  43. Li X, Peng L, Yao X (2017) Long short-term memory neural network for air pollutant concentration predictions: method development and evaluation. Environ Pollut 231(Pt 1)997–1004

    Google Scholar 

  44. Song L, Pang S, Longley I et al. (2014) Spatio-temporal PM2.5 prediction by spatial data aided incremental support vector regression. In: International joint conference on neural networks. IEEE, pp 623–630

  45. Willmott CJ, Ackleson SG, Davis RE, Feddema JJ, Klink KM, Legates DR, O’Donnell J, Rowe CM (1985) Statistics for the evaluation and comparison of models. J Geophys Res Oceans 90:8995–9005 https://doi.org/10.1029/JC090iC05p08995

    Article  Google Scholar 

  46. Bengio Y, Lamblin P, Popovivi D, Larochelle H (2007) Greedy layer-wise training of deep networks. Adv Neural Inf Process Syst 19:153–168

    Google Scholar 

  47. Nair V, Hinton GE (2010) Rectified linear units improve restricted boltzmann machines. In: International conference on machine learning (ICML-10).

  48. Chollet F (2015) keras. https://keras.io

Download references

Acknowledgements

This study was supported by the High Priority Area Research Seed Grant of the University of Houston.

Author information

Authors and Affiliations

  1. Department of Earth and Atmospheric Sciences, University of Houston, Houston, TX, 77004, USA

    Inchoon Yeo, Yunsoo Choi, Yannic Lops & Alqamah Sayeed

Authors
  1. Inchoon Yeo
    View author publications

    You can also search for this author inPubMed Google Scholar

  2. Yunsoo Choi
    View author publications

    You can also search for this author inPubMed Google Scholar

  3. Yannic Lops
    View author publications

    You can also search for this author inPubMed Google Scholar

  4. Alqamah Sayeed
    View author publications

    You can also search for this author inPubMed Google Scholar

Corresponding author

Correspondence to Yunsoo Choi.

Ethics declarations

Conflict of interest

The authors declare that they have no conflict of interest.

Additional information

Publisher's Note

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

Supplementary Information

Below is the link to the electronic supplementary material.

Supplementary file1 (DOCX 137 kb)

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Yeo, I., Choi, Y., Lops, Y. et al. Efficient PM2.5 forecasting using geographical correlation based on integrated deep learning algorithms. Neural Comput & Applic 33, 15073–15089 (2021). https://doi.org/10.1007/s00521-021-06082-8

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00521-021-06082-8

Keywords