No Access

Comparison of Nitrogen Dioxide Predictions During a Pandemic and Non-pandemic Scenario in the City of Madrid using a Convolutional LSTM Network

Institute of New Imaging Technologies, Universitat Jaume I, Avinguda de Vicent Sos Baynat, s/n Castelló de la Plana 12071, Spain

E-mail Address: iskandar@uji.es

Corresponding author.

Search for more papers by this author

Francisco Ramos

Institute of New Imaging Technologies, Universitat Jaume I, Avinguda de Vicent Sos Baynat, s/n Castelló de la Plana 12071, Spain

Search for more papers by this author

, and

Sergio Trilles

Institute of New Imaging Technologies, Universitat Jaume I, Avinguda de Vicent Sos Baynat, s/n Castelló de la Plana 12071, Spain

Search for more papers by this author

https://doi.org/10.1142/S1469026822500146Cited by:6 (Source: Crossref)

Abstract

Traditionally, machine learning technologies with the methods and capabilities available, combined with a geospatial dimension, can perform predictive analyzes of air quality with greater accuracy. However, air pollution is influenced by many external factors, one of which has recently been caused by the restrictions applied to curb the relentless advance of COVID-19. These sudden changes in air quality levels can negatively influence current forecasting models. This work compares air pollution forecasts during a pandemic and non-pandemic period under the same conditions. The ConvLSTM algorithm was applied to predict the concentration of nitrogen dioxide using data from the air quality and meteorological stations in Madrid. The proposed model was applied for two scenarios: pandemic (January–June 2020) and non-pandemic (January–June 2019), each with sub-scenarios based on time granularity (1-h, 12-h, 24-h and 48-h) and combination of features. The Root Mean Square Error was taken as the estimation metric, and the results showed that the proposed method outperformed a reference model, and the feature selection technique significantly improved the overall accuracy.

Keywords:

Remember to check out the Most Cited Articles!
Check out these titles in artificial intelligence!

References

1. I. H. Fong, T. Li, S. Fong, R. K. Wong and A. J. Tallón-Ballesteros, Predicting concentration levels of air pollutants by transfer learning and recurrent neural network, Knowl. Based Syst. 192 (2020) 105622. Crossref, Google Scholar
2. W. Zhai and C. Cheng, A long short-term memory approach to predicting air quality based on social media data, Atmos. Environ. 237 (2020) 17411. Crossref, Google Scholar
3. W. Yang, M. Deng, F. Xu and H. Wang, Prediction of hourly PM2.5 using a space-time support vector regression model, Atmos. Environ. 181 (2018) 12–19. Crossref, Google Scholar
4. J. Ma, Y. Ding, V. J. Gan, C. Lin and Z. Wan, Spatiotemporal prediction of PM2.5 concentrations at different time granularities using IDW-BLSTM, IEEE Access 7 (2019) 107897–107907. Crossref, Google Scholar
5. S. Kim, S. Hong, M. Joh and S.-k. Song, arXiv:1711.02316. Google Scholar
6. Z. Yuan, X. Zhou and T. Yang, Hetero-convlstm: A deep learning approach to traffic accident prediction on heterogeneous spatio-temporal data, in Proc. 24th ACM SIGKDD Int. Conf. Knowledge Discovery & Data Mining, 2018, pp. 984–992. Crossref, Google Scholar
7. V.-D. Le, T.-C. Bui and S. K. Cha, arXiv:1911.12919. Google Scholar
8. Air pollution. https://bit.ly/3gScSXF. Accessed 24 June 2021. Google Scholar
9. W. Liu, X.-G. Yue and P. B. Tchounwou, Response to the COVID-19 epidemic: The chinese experience and implications for other countries (2020). Google Scholar
10. Z. S. Venter, K. Aunan, S. Chowdhury and J. Lelieveld, COVID-19 lockdowns cause global air pollution declines, Proc. Natl. Acad. Sci. 117(32) (2020) 18984–18990. Crossref, Google Scholar
11. J. M. Baldasano, COVID-19 lockdown effects on air quality by NO2 in the cities of Barcelona and Madrid (Spain), Sci. Total Environ. 741 (2020) 140353. Crossref, Google Scholar
12. D. Iskandaryan, F. Ramos and S. Trilles, Features exploration from datasets vision in air quality prediction domain, Atmosphere 12(3) (2021) 312. Crossref, Google Scholar
13. S. Khomenko, M. Cirach, E. Pereira-Barboza, N. Mueller, J. Barrera-Gómez, D. Rojas-Rueda, K. de Hoogh, G. Hoek and M. Nieuwenhuijsen, Premature mortality due to air pollution in European cities: A health impact assessment, Lancet Planet. Health 5(3) (2021) e121–e134. Crossref, Google Scholar
14. Portal de Datos Abiertos del Ayuntamiento de Madrid. https://bit.ly/2TZzwEo. Accessed 24 June 2021. Google Scholar
15. Z. Li, S. H. L. Yim and K.-F. Ho, High temporal resolution prediction of street-level PM2.5 and NOx concentrations using machine learning approach, J. Clean. Prod. (2020) 121975. Crossref, Google Scholar
16. L. Goulier, B. Paas, L. Ehrnsperger and O. Klemm, Modelling of urban air pollutant concentrations with artificial neural networks using novel input variables, Int. J. Environ. Res. Public Health 17(6) (2020) 2025. Crossref, Google Scholar
17. L. Li et al., Cluster-based bagging of constrained mixed-effects models for high spatiotemporal resolution nitrogen oxides prediction over large regions, Environ. Int. 128 (2019) 310–323. Crossref, Google Scholar
18. J. Chen et al., A comparison of linear regression, regularization, and machine learning algorithms to develop Europe-wide spatial models of fine particles and nitrogen dioxide, Environ. Int. 130 (2019) 104934. Crossref, Google Scholar
19. L. Munkhdalai, T. Munkhdalai, K. H. Park, T. Amarbayasgalan, E. Erdenebaatar, H. W. Park and K. H. Ryu, An end-to-end adaptive input selection with dynamic weights for forecasting multivariate time series, IEEE Access 7 (2019) 99099–99114. Crossref, Google Scholar
20. J. A. Kamińska, A random forest partition model for predicting No 2 concentrations from traffic flow and meteorological conditions, Sci. Total Environ. 65 (2019) 475–483. Crossref, Google Scholar
21. E. Pardo and N. Malpica, Air quality forecasting in Madrid using long short-term memory networks, in Int. Work-Conf. Interplay between Natural and Artificial Computation (Springer, 2017), pp. 232–239. Crossref, Google Scholar
22. M. Krishan, S. Jha, J. Das, A. Singh, M. K. Goyal and C. Sekar, Air quality modelling using long short-term memory (LSTM) over NCT-Delhi, India, Air Qual. Atmos. Health 12(8) (2019) 899–908. Crossref, Google Scholar
23. H. Peng, A. R. Lima, A. Teakles, J. Jin, A. J. Cannon and W. W. Hsieh, Evaluating hourly air quality forecasting in Canada with nonlinear updatable machine learning methods, Air Qual. Atmos. Health 10(2) (2017) 195–211. Crossref, Google Scholar
24. J. Zhang and W. Ding, Prediction of air pollutants concentration based on an extreme learning machine: The case of Hong Kong, Int. J. Environ. Res. Public Health 14(2) (2017) 114. Crossref, Google Scholar
25. K. B. Shaban, A. Kadri and E. Rezk, Urban air pollution monitoring system with forecasting models, IEEE Sens. J. 16(8) (2016) 2598–2606. Crossref, Google Scholar
26. W. Tamas, G. Notton, C. Paoli, M.-L. Nivet and C. Voyant, Hybridization of air quality forecasting models using machine learning and clustering: An original approach to detect pollutant peaks, Aerosol Air Qual. Res. 16(2) (2016) 405–441. Crossref, Google Scholar
27. E. Debry and V. Mallet, Ensemble forecasting with machine learning algorithms for ozone, nitrogen dioxide and PM10 on the Prev’Air platform, Atmos. Environ. 91 (2014) 71–84. Crossref, Google Scholar
28. C.-M. Vong, W.-F. Ip, P.-k. Wong and J.-y. Yang, Short-term prediction of air pollution in Macau using support vector machines, J. Control Sci. Eng. 2012 (2012) Article ID 518032, 11 pages, https://doi.org/10.1155/2012/518032. Crossref, Google Scholar
29. W. Wang, C. Men and W. Lu, Online prediction model based on support vector machine, Neurocomputing 71(4–6) (2008) 550–558. Crossref, Google Scholar
30. X. Shi, Z. Chen, H. Wang, D.-Y. Yeung, W.-K. Wong and W.-c. Woo, arXiv:1506.04214. Google Scholar
31. H. Peng, F. Long and C. Ding, Feature selection based on mutual information criteria of max-dependency, max-relevance, and min-redundancy, IEEE Trans. Pattern Anal. Mach. Intell. 27(8) (2005) 1226–1238. Crossref, Google Scholar
32. One hot encoder. https://bit.ly/3nwzXCe. Accessed 24 June 2021. Google Scholar
33. H. Zheng, H. Li, X. Lu and T. Ruan, A multiple kernel learning approach for air quality prediction, Adv. Meteorol. 2018 (2018) Article ID 3506394, 15 pages, https://doi.org/10.1155/2018/3506394. Crossref, Google Scholar