Hourly pollutants forecasting using a deep learning approach to obtain the AQI

  1. Moscoso-López, José Antonio 1
  2. González-Enrique, Javier 1
  3. Urda, Daniel 2
  4. Ruiz-Aguilar, Juan Jesús 1
  5. Turias, Ignacio J 1
  1. 1 Intelligent Modelling of Systems Research Group, Polytechnic School of Engineering, (Algeciras), University of Cadiz, Av. Ramon Puyol s/n, 11202 Algeciras, Spain
  2. 2 Grupo de Inteligencia Computacional Aplicada (GICAP), Departamento de Ingeniería Informática, Escuela Politécnica Superior, Universidad de Burgos, Av. Cantabria s/n, 09006 Burgos, Spain
Journal:
Logic Journal of the IGPL

ISSN: 1367-0751,  1368-9894

Year of publication: 2022

Type: Article

DOI: 10.1093/JIGPAL/JZAC035 GOOGLE SCHOLAR lock_openOpen access editor

More publications in: Logic Journal of the IGPL

Abstract

The Air Quality Index (AQI) shows the state of air pollution in a unique and more understandable way. This work aims to forecast the AQI in Algeciras (Spain) 8 hours in advance. The AQI is calculated indirectly through the predicted concentrations of five pollutants (O3, NO2, CO, SO2 and PM10) to achieve this goal. Artificial neural networks (ANNs), sequence-to-sequence long short-term memory networks (LSTMs) and a newly proposed method combing a rolling window with the latter (LSTMNA) are employed as the forecasting techniques. Besides, two input approaches are evaluated: using only the data from the own time series of the pollutant in the first case or adding exogenous variables in the second one. Several window sizes are employed (24, 28 and 72 hours) with ANNs and LSTMNAs. Additionally, several feature ranking methods are applied in the exogenous approach to select the most relevant lagged variables to feed the models. Results show how the proposed exogenous approach increases the performance of the prediction models. Besides, the newly proposed method LSTMNA provides the best performances in most of the cases evaluated. Hence, it constitutes an exciting alternative to standard LSTMs and ANNs to predict pollutants concentrations and, consequently, the AQI.

€ View funding

Funding information

Funders

Bibliographic References

  • E. E. Agency, (2018)
  • He, (2019), Sustainable Cities and Society, 47, pp. 101472, 10.1016/j.scs.2019.101472
  • Liu, (2019), Sustainable Cities and Society, 47, pp. 101471, 10.1016/j.scs.2019.101471
  • Lin, (2018), Journal of Cleaner Production, 188, pp. 312, 10.1016/j.jclepro.2018.03.293
  • Ni, (2017), Atmospheric Environment, 150, pp. 146, 10.1016/j.atmosenv.2016.11.054
  • Plaia, (2011), Reviews in Environmental Science and Bio/Technology, 10, pp. 165, 10.1007/s11157-010-9227-2
  • Ribeiro, (2016), Science of the Total Environment, 562, pp. 740, 10.1016/j.scitotenv.2016.04.081
  • Zhou, (2019), Journal of Cleaner Production, 209, pp. 134, 10.1016/j.jclepro.2018.10.243
  • Pisoni, (2018), Atmospheric Environment, 183, pp. 84, 10.1016/j.atmosenv.2018.04.006
  • He, (2018), Urban Climate, 24, pp. 26, 10.1016/j.uclim.2018.01.004
  • Lauret, (2016), Environmental Modelling & Software, 85, pp. 56, 10.1016/j.envsoft.2016.08.001
  • Van Fan, (2018), Journal of Cleaner Production, 194, pp. 673, 10.1016/j.jclepro.2018.05.151
  • Yang, (2018), Journal of Cleaner Production, 170, pp. 388, 10.1016/j.jclepro.2017.09.162
  • Zhu, (2017), Environmental Pollution, 231, pp. 1232, 10.1016/j.envpol.2017.08.069
  • Boznar, (1993), Atmospheric Environment. Part B, Urban Atmosphere, 27, pp. 221, 10.1016/0957-1272(93)90007-S
  • Gardner, (1999), Atmospheric Environment, pp. 709, 10.1016/S1352-2310(98)00230-1
  • Comrie, (1997), Journal of the Air & Waste Management Association, 47, pp. 653, 10.1080/10473289.1997.10463925
  • Gardner, (2000), Atmospheric Environment, 34, pp. 21, 10.1016/S1352-2310(99)00359-3
  • Perez, (2001), Atmospheric Environment, 35, pp. 4929, 10.1016/S1352-2310(01)00268-0
  • Jiang, (2004), Atmospheric Environment, 38, pp. 7055, 10.1016/j.atmosenv.2003.10.066
  • Hooyberghs, (2005), Atmospheric Environment, 39, pp. 3279, 10.1016/j.atmosenv.2005.01.050
  • Azid, (2013), Journal of Environmental Protection, 4, pp. 1, 10.4236/jep.2013.412A1001
  • Kolehmainen, (2001), Atmospheric Environment, 35, pp. 815, 10.1016/S1352-2310(00)00385-X
  • Chelani, (2002), Environmental Modelling & Software, 17, pp. 159, 10.1016/S1364-8152(01)00061-5
  • González-Enrique, (2019), Stochastic Environmental Research and Risk Assessment, 33, pp. 801, 10.1007/s00477-018-01644-0
  • González-Enrique, (2019), Fresenius Environmental Bulletin, 28, pp. 681
  • Li, (2016), Environmental Science and Pollution Research, 23, pp. 22408, 10.1007/s11356-016-7812-9
  • Rao, (2019), International Journal of Intelligent Systems and Applications, 11, pp. 18
  • Kim, (2019), Atmospheric Chemistry and Physics, pp. 1
  • Kök, (2017), 2017 IEEE International Conference on Big Data (Big Data), pp. 1983, 10.1109/BigData.2017.8258144
  • Dorman, (1995), Quarterly Journal of the Royal Meteorological Society, 121, pp. 1903, 10.1002/qj.49712152807
  • Kyrkilis, (2007), Environment International, 33, pp. 670, 10.1016/j.envint.2007.01.010
  • U.S. Environmental Protection Agency, (2006)
  • Hochreiter, (1997), Neural Computation, 9, pp. 1735, 10.1162/neco.1997.9.8.1735
  • Gers, (2000), Neural Computation, 12, pp. 2451, 10.1162/089976600300015015
  • Hochreiter, (1998), International Journal of Uncertainty, Fuzziness and Knowledge-Based Systems, 6, pp. 107, 10.1142/S0218488598000094
  • Freeman, (2018), Journal of the Air & Waste Management Association, 68, pp. 866, 10.1080/10962247.2018.1459956
  • Shi, (2015), Proceedings of the 28th International Conference on Neural Information Processing Systems—Volume 1, pp. 802
  • Rumelhart, (1986), Parallel Distributed Processing: Explorations in the Microstructure of Cognition. Volume 1. Foundations, pp. 318, 10.7551/mitpress/5236.001.0001
  • Azid, (2014), Water, Air, and Soil Pollution, 225, pp. 1, 10.1007/s11270-014-2063-1
  • González-Enrique, (2019), Advances in Computational Intelligence. IWANN 2019. Lecture Notes in Computer Science, pp. 856
  • Van Roode, (2019), Environmental Monitoring and Assessment, 191, pp. 727, 10.1007/s10661-019-7901-6
  • Ruiz-Aguilar, (2021), Neural Computing and Applications, 33, pp. 2369, 10.1007/s00521-020-05141-w
  • Møller, (1993), Neural Networks, 6, pp. 525, 10.1016/S0893-6080(05)80056-5
  • Bishop, (1995), Neural Networks for Pattern Recognition
  • Sarle, (1995), Proceedings of the 27th Symposium on the Interface of Computing Science and Statistics, pp. 352
  • Gardner, (1998), Atmospheric Environment, 32, pp. 2627, 10.1016/S1352-2310(97)00447-0
  • González-Enrique, (2021), Stochastic Environmental Research and Risk Assessment, 35, pp. 1999, 10.1007/s00477-021-01992-4
  • Peng, (2005), IEEE Transactions on Pattern Analysis and Machine Intelligence, 27, pp. 1226, 10.1109/TPAMI.2005.159
  • Sutskever, (2014), Proceedings of the 27th International Conference on Neural Information Processing Systems—Volume 2, pp. 3104
  • González-Enrique, (2021), Sensors, 21, pp. 1770, 10.3390/s21051770
  • Brockwell, (2002), Introduction to Time Series and Forecasting, 10.1007/b97391
  • Moscoso-López, (2021), 15th International Conference on Soft Computing Models in Industrial and Environmental Applications (SOCO 2020). Advances in Intelligent Systems and Computing, pp. 123
  • Friedman, (1937), Journal of the American Statistical Association, 32, pp. 675, 10.1080/01621459.1937.10503522
  • Hochberg, (1987), Multiple Comparison Procedures, 10.1002/9780470316672