Communications for Statistical Applications and Methods

The Korean Statistical Society (한국통계학회)
권호 표지
DOI QR코드

DOI QR Code

Aerosol optical depth prediction based on dimension reduction methods

  • Jungkyun Lee (Department of Statistics, Chung-Ang University) ;
  • Yaeji Lim (Department of Statistics, Chung-Ang University)
  • Received : 2024.01.24
  • Accepted : 2024.02.20
  • Published : 2024.09.30
Download PDF
⟨ Previous Next ⟩

Abstract

As the concentration of fine dust has recently increased, numerous related studies are being conducted to address this issue. Aerosol optical depth (AOD) is a vital atmospheric parameter for measuring the optical properties of aerosols in the atmosphere, providing crucial information related to fine dust. In this paper, we apply three dimension reduction methods, nonnegative matrix factorization (NMF), empirical orthogonal functions (EOF) analysis and independent component analysis (ICA), to AOD data to analyze the patterns of fine dust in the East Asia region. Through a comparison of three dimension reduction methods, we observe that some patterns are observed in all three method, while some information are only extracted in a specific method. Additionally, we forecast AOD levels based on three methods, and compare the predictive performance of the three methodologies.

Keywords

Acknowledgement

This research was supported by the Chung-Ang University Research Scholarship Grants in 2023.

References

  1. Cai Y, Gu H, and Kenney T (2023). Rank selection for non-negative matrix factorization, Statistics in Medicine, 42, 5676-5693.
  2. Cho KW, Jung YJ, and Oh CH (2021). Comparative study of performance of deep learning algorithms in particulate matter concentration prediction, Journal of Advanced Navigation Technology, 25, 409-414.
  3. Guo JP, Zhang XY, Che HZ et al. (2009). Correlation between PM concentrations and aerosol optical depth in eastern China, Atmospheric Environment, 43, 5876-5886.
  4. Hannachi A, Jolliffe IT, and Stephenson DB (2007). Empirical orthogonal functions and related techniques in atmospheric science: A review, International Journal of Climatology: A Journal of the Royal Meteorological Society, 27, 1119-1152.
  5. Hoffman MD, Blei DM, and Cook PR (2010). Bayesian nonparametric matrix factorization for recorded music, ICML, 10, 439-446.
  6. Hyndman RJ and Khandakar Y (2008). Automatic time series forecasting: The forecast package for R, Journal of Statistical Software, 27, 1-22.
  7. Hyvarinen A and Oja E (2000). Independent component analysis: Algorithms and applications, Neural Networks, 13, 411-430.
  8. Karimian H, Li Y, Chen Y, and Wang Z (2023). Evaluation of different machine learning approaches and aerosol optical depth in PM2. 5 prediction, Environmental Research, 216, 114465.
  9. Kim MJ (2019). The effects of transboundary air pollution from China on ambient air quality in South Korea, Heliyon, 5, e02953.
  10. Kim SW, Choi IJ, and Yoon SC (2010). A multi-year analysis of clear-sky aerosol optical properties and direct radiative forcing at Gosan, Korea (2001-2008), Atmospheric Research, 95, 279-287.
  11. Khoir ANU, Ooi MCG, Juneng L, Ramadhan MAI, Virgianto RH, and Tangang F (2022). Spatiotemporal analysis of aerosol optical depth using rotated empirical orthogonal function over the Maritime Continent from 2001 to 2020, Atmospheric Environment, 290, 119356.
  12. Lee HJ, Coull BA, Bell ML, and Koutrakis P (2012). Use of satellite-based aerosol optical depth and spatial clustering to predict ambient PM2. 5 concentrations, Environmental Research, 118, 8-15.
  13. Lee DD and Seung HS (1999). Learning the parts of objects by non-negative matrix factorization, Nature, 401, 788-791.
  14. Levy R and Hsu C (2015). MODIS atmosphere L2 aerosol product. NASA MODIS adaptive processing system, Goddard Space Flight Center, USA, Available from: http://dx.doi.org/10.5067/MODIS/MOD04 L2.006
  15. Ma Q, Zhang Q, Wang Q, Yuan X, Yuan R, and Luo C (2021). A comparative study of EOF and NMF analysis on downward trend of AOD over China from 2011 to 2019, Environmental Pollution, 288, 117713.
  16. Pascual-Montano A, Carazo JM, Kochi K, Lehmann D, and Pascual-Marqui RD (2006). Nonsmooth nonnegative matrix factorization (nsNMF), IEEE Transactions on Pattern Analysis and Machine Intelligence, 28, 403-415.
  17. Shrestha P and Barros AP (2010). Joint spatial variability of aerosol, clouds and rainfall in the Himalayas from satellite data, Atmospheric Chemistry and Physics, 10, 8305-8317.
  18. Xin J, Zhang Q, Wang L, Gong C, Wang Y, Liu Z, and Gao W (2014). The empirical relationship between the PM2. 5 concentration and aerosol optical depth over the background of North China from 2009 to 2011, Atmospheric Research, 138, 179-188.
  19. Wang YX and Zhang YJ (2012). Nonnegative matrix factorization: A comprehensive review, IEEE Transactions on Knowledge and Data Engineering, 25, 1336-1353.