Skip to main content
SpringerLink
Log in

Airborne particle pollution predictive model using Gated Recurrent Unit (GRU) deep neural networks

  • Research Article
  • Published:
Earth Science Informatics Aims and scope Submit manuscript

Abstract

Developments in deep learning for time-series problems have shown promising results for data prediction. Particulate Matter equal or smaller than 10 μm (PM10) have increased importance in the research field due to the negative impact in the respiratory system. PM10 particles show non-linear behavior, hence it is not an easy task to implement techniques to predict subsequent concentration of the particles in the atmosphere. This paper presents a forecasting model using gated Recurrent unit (GRU) and Long-Short Term Memory (LSTM) networks, which are types of a deep recurrent neural network (RNN). The predicted results of PM10 are presented using data of Mexico City as a case study, showing that this type of deep network is feasible for predicting the non-linearities of this type of data. Several experiments were carried out for 12, 24, 48, and 120 h prediction, showing that this method may be applied to accurately forecast the behavior of PM10.

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
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

Similar content being viewed by others

References

  • Aceves-Fernandez MA et al (2018) Feature extraction of EEG signal upon BCI systems based on steady-state visual evoked potentials using the ant colony optimization algorithm. Discret Dyn Nat Soc:21. https://doi.org/10.1155/2018/2143873

  • Aceves-Fernandez MA et al (2015) Design and implementation of ant colony algorithms to enhance airborne pollution models. Int J Environ Sci Toxicol Res 3(2):22–28

    Google Scholar 

  • Akbarzadeh MA et al (2018) The association between exposure to air pollutants including PM10, PM2. 5, ozone, carbon monoxide, sulfur dioxide, and nitrogen dioxide concentration and the relative risk of developing STEMI: a case-crossover design. Environ Res 161:299–303

    Article  Google Scholar 

  • Bartzis JG et al (2019). Environmental data treatment to support exposure studies: the statistical behavior for NO2, O3, PM10 and PM2.5 air concentrations in Europe. https://doi.org/10.1016/j.envres.2019.108864

  • Bos PM et al (2019) Pulmonary toxicity in rats following inhalation exposure to poorly soluble particles: The issue of impaired clearance and the relevance for human health hazard and risk assessment. Regul Toxicol Pharmacol:104498

  • Cabrera-Hernandez MC, Aceves-Fernandez MA et al (2019) Parameters influencing the optimization process in airborne particles PM10 Using a Neuro-Fuzzy Algorithm Optimized with Bacteria Foraging (BFOA). Int J Intellig Sci 9:67–91. https://doi.org/10.4236/ijis.2019.93005

    Article  Google Scholar 

  • Caudillo L et al (2020) Nanoparticle size distributions in Mexico city. Atmos Pollut Res 11(1):78–84

    Article  Google Scholar 

  • Cho K, Van Merriënboer B et al (2014) Learning phrase representations using RNN encoder-decoder for statistical machine translation. arXiv preprint arXiv:1406.1078

  • Chung J, Gulcehre C et al (2014) Empirical evaluation of gated recurrent neural networks on sequence modeling. arXiv preprint arXiv:1412.3555

  • Diederik P et al (2014) A method for stochastic optimization, 2014. cite arxiv:1412.6980Comment: Published as a conference paper at the 3rd International Conference for Learning Representations, San Diego

  • Domínguez-Guevara R et al (2019) Propuesta de red neuronal convolutiva para la predicción de partículas contaminantes PM10 Convolutional Neural Network Proposal for Particulate Matter PM10 Prediction. Res Comput Sci 148(7):51–63

    Article  Google Scholar 

  • Franceschi F et al (2018) Discovering relationships and forecasting PM 10 and PM 2.5 concentrations in Bogotá, Colombia, using Artificial Neural Networks, Principal Component Analysis, and k-means clustering. Atmos Pollut Res. https://doi.org/10.1016/j.apr.2018.02.006

  • Goglio P et al (2019) Advances and challenges of life cycle assessment (LCA) of greenhouse gas removal technologies to fight climate changes. J Clean Prod:118896

  • Grivas G et al (2006) Artificial neural network models for prediction of PM10 hourly concentrations, in the Greater Area of Athens, Greece. Atmos Environ 40:1216–1229. https://doi.org/10.1016/j.atmosenv.2005.10.036

    Article  Google Scholar 

  • Hochreiter S, Schmidhuber J (1997) Long short-term memory. Neural Comput 9(8):1735–1780

    Article  Google Scholar 

  • JHeck JC, Salem FM (2017) Simplified minimal gated unit variations for recurrent neural networks. In 2017 IEEE 60th International Midwest Symposium on Circuits and Systems (MWSCAS) (pp. 1593-1596). IEEE

  • Längkvist M et al (2014) A review of unsupervised feature learning and deep learning for time-series modeling. Pattern Recogn Lett 42:11–24

  • Montañez JAR, Fernandez MAA, Arriaga ST, Arreguin JMR, Calderon GAS (2019, September). Evaluation of a recurrent neuralnetwork LSTM for the detection of exceedances of particles PM10. In 2019 16th International Conference on Electrical Engineering, Computing Scienceand Automatic Control (CCE) (pp. 1–6). IEEE

  • Nom (2005) (norma oficial mexicana nom-025-ssa1–1993). salud ambiental. criterios para evaluar la calidad del aire ambiente, con respecto a material particulado. última modificación, septiembre del 2005. Secretaría de Salud, México (Health Secretariat)

  • Oh HR et al (2015) Long-range transport of air pollutants originating in China: a possible major cause of multi-day high-PM10 episodes during cold season in Seoul, Korea. Atmos Environ 109:23–30

    Article  Google Scholar 

  • Ordonez de León B, Aceves-Fernandez MA et al (2019) An improved particle swarm optimization (PSO): method to enhance modeling of airborne particulate matter (PM10). Evol Syst. https://doi.org/10.1007/s12530-019-09263-y

  • Schraufnagel DE et al (2019) Air pollution and noncommunicablediseases: a review by the Forum of International Respiratory Societies’ Environmental Committee, Part 2: air pollution and organ systems. Chest 155(2):417–426

  • SEDEMA (2018). Red automática de monitoreo ambiental. Available at http://www.aire.cdmx.gob.mx/, Accessed July 2018

  • Skrzypski J, Kami K, Jach-Szakiel E, Kami W (2009) Application of artificial neural networks for classification and prediction of air quality classes. WIT Trans Ecol Environ 127:219–228

    Article  Google Scholar 

  • Yetilmezsoy K. (2012). A prognostic approach based on fuzzy-logic methodology to forecast PM10 levels in Khaldiya residential area, Kuwait. Aerosol Air Qual Res. 12. https://doi.org/10.4209/aaqr.2012.07.0163

  • Zhou G-B, Wu J, Zhang C-L, Zhou Z-H. Minimal gated unit for recurrent neural networks. Int J AutomComput 13(3):226–234

Download references

Author information

Authors and Affiliations

  1. Facultad de Ingeniería, Universidad Autónoma de Querétaro, Querétaro, Mexico

    Josue Becerra-Rico, Marco A. Aceves-Fernández, Karen Esquivel-Escalante & Jesús Carlos Pedraza-Ortega

Authors
  1. Josue Becerra-Rico
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Marco A. Aceves-Fernández
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Karen Esquivel-Escalante
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Jesús Carlos Pedraza-Ortega
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Marco A. Aceves-Fernández.

Additional information

Communicated by: H. Babaie

Publisher’s note

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

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Becerra-Rico, J., Aceves-Fernández, M.A., Esquivel-Escalante, K. et al. Airborne particle pollution predictive model using Gated Recurrent Unit (GRU) deep neural networks. Earth Sci Inform 13, 821–834 (2020). https://doi.org/10.1007/s12145-020-00462-9

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s12145-020-00462-9

Keywords

Search

Navigation