ETRI Journal

Electronics and Telecommunications Research Institute (한국전자통신연구원)
권호 표지
DOI QR코드

DOI QR Code

Air quality index prediction using seasonal autoregressive integrated moving average transductive long short-term memory

  • Subramanian Deepan (Department of Networking and Communications, College of Engineering and Technology, SRM Institute of Science and Technology) ;
  • Murugan Saravanan (Department of Networking and Communications, College of Engineering and Technology, SRM Institute of Science and Technology)
  • Received : 2023.07.19
  • Accepted : 2023.11.03
  • Published : 2024.10.10
Download PDF
⟨ Previous Next ⟩

Abstract

We obtain the air quality index (AQI) for a descriptive system aimed to communicate pollution risks to the population. The AQI is calculated based on major air pollutants including O3, CO, SO2, NO, NO2, benzene, and particulate matter PM2.5 that should be continuously balanced in clean air. Air pollution is a major limitation for urbanization and population growth in developing countries. Hence, automated AQI prediction by a deep learning method applied to time series may be advantageous. We use a seasonal autoregressive integrated moving average (SARIMA) model for predicting values reflecting past trends considered as seasonal patterns. In addition, a transductive long short-term memory (TLSTM) model learns dependencies through recurring memory blocks, thus learning long-term dependencies for AQI prediction. Further, the TLSTM increases the accuracy close to test points, which constitute a validation group. AQI prediction results confirm that the proposed SARIMA-TLSTM model achieves a higher accuracy (93%) than an existing convolutional neural network (87.98%), least absolute shrinkage and selection operator model (78%), and generative adversarial network (89.4%).

Keywords

References

  1. M. K. AlOmar, M. M. Hameed, and M. A. AlSaadi, Multi hours ahead prediction of surface ozone gas concentration: robust artificial intelligence approach, Atmos. Pollut. Res. 11 (2020), 1572-1587.
  2. R. Sharma, R. Kumar, D. K. Sharma, L. H. Son, I. Priyadarshini, B. T. Pham, D. T. Bui, and S. Rai, Inferring air pollution from air quality index by different geographical areas: case study in India, Air Qual. Atmos. Health 12 (2019), 1347-1357.
  3. H. Amini, N. T. T. Nhung, C. Schindler, M. Yunesian, V. Hosseini, M. Shamsipour, M. S. Hassanvand, Y. Mohammadi, F. Farzadfar, A. M. Vicedo-Cabrera, J. Schwartz, S. B. Henderson, and N. Kunzli, Short-term associations between daily mortality and ambient particulate matter, nitrogen dioxide, and the air quality index in a Middle Eastern megacity, Environ. Pollut. 254 (2019), 113121.
  4. S. Zhu, L. Yang, W. Wang, X. Liu, M. Lu, and X. Shen, Optimal-combined model for air quality index forecasting: 5 cities in North China, Environ. Pollut. 243 (2018), 842-850.
  5. C. W. Chen and L. M. Chiu, Ordinal time series forecasting of the air quality index, Entropy 23 (2021), 1167.
  6. Q. Wu and H. Lin, A novel optimal-hybrid model for daily air quality index prediction considering air pollutant factors, Sci. Total Environ. 683 (2019), 808-821.
  7. R. Yan, J. Liao, J. Yang, W. Sun, M. Nong, and F. Li, Multihour and multi-site air quality index forecasting in Beijing using CNN, LSTM, CNN-LSTM, and spatiotemporal clustering, Expert Syst. Appl. 169 (2021), 114513.
  8. H. Li, J. Wang, R. Li, and H. Lu, Novel analysis-forecast system based on multi-objective optimization for air quality index, J. Clean. Prod. 208 (2019), 1365-1383.
  9. A. Cascallar-Fuentes, J. Gallego-Fernandez, A. Ramos-Soto, A. Saunders-Estevez, and A. Bugarin-Diz, Automatic generation of textual descriptions in data-to-text systems using a fuzzy temporal ontology: application in air quality index data series, Appl. Soft Comput. 119 (2022), 108612.
  10. L. A. Gladson, K. R. Cromar, M. Ghazipura, K. E. Knowland, C. A. Keller, and B. Duncan, Communicating respiratory health risk among children using a global air quality index, Environ. Int. 159 (2022), 107023.
  11. L. D. Perlmutt and K. R. Cromar, Comparing associations of respiratory risk for the EPA air quality index and health-based air quality indices, Atmos. Environ. 202 (2019), 1-7.
  12. K. R. Cromar and L. D. Perlmutt, EPA Air Quality Index: Limitations as a risk communication tool, (American Thoracic Society 2016 International Conference; A106 Epidemiology and risk factors of Asthma: From the Crib to Adulthood, San Francisco, CA, USA), 2016, art. no. A2774.
  13. X. Zhang and Z. Gong, Spatiotemporal characteristics of urban air quality in China and geographic detection of their determinants, J. Geogr. Sci. 28 (2018), 563-578.
  14. W.-Z. Huang, W.-Y. He, L. D. Knibbs, B. Jalaludin, Y.-M. Guo, L. Morawska, J. Heinrich, D.-H. Chen, Y.-J. Yu, X.-W. Zeng, H.-Y. Yu, B.-Y. Yang, L.-W. Hu, R.-Q. Liu, W.-R. Feng, and G.-H. Dong, Improved morbidity-based air quality health index development using Bayesian multi-pollutant weighted model, Environ. Res. 204 (2022), 112397.
  15. L. Ye and X. Ou, Spatial-temporal analysis of daily air quality index in the Yangtze River Delta region of China during 2014 and 2016, Chin. Geogr. Sci. 29 (2019), 382-393.
  16. C.-J. Liang, J.-J. Liang, C.-W. Jheng, and M.-C. Tsai, A rolling forecast approach for next six-hour air quality index track, Eco. Inform. 60 (2020), 101153.
  17. Y. Alyousifi, M. Othman, R. Sokkalingam, I. Faye, and P. C. Silva, Predicting daily air pollution index based on fuzzy time series Markov chain model, Symmetry 12 (2020), 293.
  18. R. Chauhan, H. Kaur, and B. Alankar, Air quality forecast using convolutional neural network for sustainable development in urban environments, Sustain. Cities Soc. 75 (2021), 103239.
  19. J. K. Sethi and M. Mittal, An efficient correlation based adaptive LASSO regression method for air quality index prediction, Earth. Sci. Inform 14 (2021), 1777-1786.
  20. D. Kothandaraman, N. Praveena, K. Varadarajkumar, B. M. Rao, D. Dhabliya, S. Satla, and W. Abera, Intelligent forecasting of air quality and pollution prediction using machine learning, Adsorpt. Sci. Technol. 2022 (2022), 5086622.
  21. P. Saha, P. Nath, A. I. Middya, and S. Roy, Improving temporal predictions through time-series labeling using matrix profile and motifs, Neural Comput. Applic. 34 (2022), 13169-13185.
  22. S. Abirami and P. Chitra, Regional spatio-temporal forecasting of particulate matter using autoencoder based generative adversarial network, Stoch. Environ. Res. Risk Assess. 36 (2022), 1255-1276.
  23. R. Janarthanan, P. Partheeban, K. Somasundaram, and P. N. Elamparithi, A deep learning approach for prediction of air quality index in a metropolitan city, Sustain. Cities Soc. 67 (2021), 102720.
  24. Y. Cong, X. Zhao, K. Tang, G. Wang, Y. Hu, and Y. Jiao, FALSTM: a novel toxic gas concentration prediction model in pollutant environment, IEEE Access 10 (2022), 1591-1602.
  25. P. R. Gokul, A. Mathew, A. Bhosale, and A. T. Nair, Spatio-temporal air quality analysis and PM2.5 predictions over Hyderabad City, India using artificial intelligence techniques, Eco. Inform. 76 (2023), 102067.
  26. S. Surono, K. W. Goh, C. W. Onn, and F. Marestiani, Developing an optimized recurrent neural network model for air quality prediction using K-means clustering and PCA dimension reduction, Int. J. Innov. Res. Sci. Stud. 6 (2023), 330-343.
  27. J. Ni, H. Yang, J. Yao, Z. Li, and P. Qin, Toxic gas dispersion prediction for point source emission using deep learning method, Hum. Ecol. Risk Assess. Int. J. 26 (2020), 557-570.
  28. A. G. Salman and B. Kanigoro, Visibility forecasting using auto-regressive integrated moving average (ARIMA) models, Proc. Comput. Sci. 179 (2021), 252-259.
  29. D. Doreswamy, K. S. H. Kumar, and I. Gad, Time series analysis for prediction of PM2.5 using seasonal autoregressive integrated moving average (SARIMA) model on Taiwan air quality monitoring network data, J. Comput. Theor. Nanosci. 17 (2020), 3964-3969.
  30. T. Xayasouk, H. Lee, and G. Lee, Air pollution prediction using long short-term memory (LSTM) and deep autoencoder (DAE) models, Sustainability 12 (2020), 2570.
  31. J. Ma, Z. Li, J. C. Cheng, Y. Ding, C. Lin, and Z. Xu, Air quality prediction at new stations using spatially transferred bidirectional long short-term memory network, Sci. Total Environ. 705 (2020), 135771.
  32. M. Ebrahimi, J. F. Nunamaker Jr., and H. Chen, Semi-supervised cyber threat identification in dark net markets: a transductive and deep learning approach, J. Manag. Inf. Syst. 37 (2020), 694-722.
  33. Z. Karevan and J. A. Suykens, Transductive LSTM for timeseries prediction: an application to weather forecasting, Neural Netw. 125 (2020), 1-9.