Frequency-Based Separation of Climate Signals

  • Alexander Ilin
  • Harri Valpola
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3721)


The paper presents an example of exploratory data analysis of climate measurements using a recently developed denoising source separation (DSS) framework. We analysed a combined dataset containing daily measurements of three variables: surface temperature, sea level pressure and precipitation around the globe. Components exhibiting slow temporal behaviour were extracted using DSS with linear denoising. These slow components were further rotated using DSS with nonlinear denoising which implemented a frequency-based separation criterion. The rotated sources give a meaningful representation of the slow climate variability as a combination of trends, interannual oscillations, the annual cycle and slowly changing seasonal variations.


Power Spectrum Independent Component Analysis Empirical Orthogonal Function Slow Component Independent Component Analysis 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


  1. 1.
    von Storch, H., Zwiers, W.: Statistical Analysis in Climate Research. Cambridge Univ. Press, Cambridge (1999)CrossRefGoogle Scholar
  2. 2.
    Richman, M.B.: Rotation of principal components. J. of Climatology 6, 293–335 (1986)CrossRefGoogle Scholar
  3. 3.
    Kim, K.-Y., Wu, Q.: A comparison study of EOF techniques: Analysis of nonstationary data with periodic statistics. J. of Climate 12, 185–199 (1999)CrossRefGoogle Scholar
  4. 4.
    Hyvärinen, A., Karhunen, J., Oja, E.: Independent Component Analysis. J. Wiley, Chichester (2001)CrossRefGoogle Scholar
  5. 5.
    Aires, F., Chédin, A., Nadal, J.-P.: Independent component analysis of multivariate time series: Application to the tropical SST variability. J. of Geophysical Research 105, 437–455 (2000)CrossRefGoogle Scholar
  6. 6.
    Lotsch, A., Friedl, M.A., Pinzón, J.: Spatio-temporal deconvolution of NDVI image sequences using independent component analysis. IEEE Trans. on Geoscience and Remote Sensing 41, 2938–2942 (2003)CrossRefGoogle Scholar
  7. 7.
    Särelä, J., Valpola, H.: Denoising source separation. Journal of Machine Learning Research 6, 233–272 (2005)Google Scholar
  8. 8.
    Ilin, A., Valpola, H., Oja, E.: Semiblind source separation of climate data detects El Niño as the component with the highest interannual variability. In: Proc. of Int. Joint Conf. on Neural Networks (IJCNN 2005), Montreal, Quebec, Canada (2005) (accepted)Google Scholar
  9. 9.
    Valpola, H., Särelä, J.: Accurate, fast and stable denoising source separation algorithms. In: Puntonet, C.G., Prieto, A.G. (eds.) ICA 2004. LNCS, vol. 3195, pp. 65–72. Springer, Heidelberg (2004)CrossRefGoogle Scholar
  10. 10.
    Hyvärinen, A., Hoyer, P., Inki, M.: Topographic independent component analysis. Neural Computation 13(7), 1525–1558 (2001)CrossRefGoogle Scholar
  11. 11.
    Trenberth, K.E., Caron, J.M.: The Southern Oscillation revisited: Sea level pressures, surface temperatures, and precipitation. Journal of Climate 13, 4358–4365 (2000)CrossRefGoogle Scholar
  12. 12.
    Kalnay, E., Coauthors: The NCEP/NCAR 40-year reanalysis project. Bulletin of the American Meteorological Society 77, 437–471 (1996)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2005

Authors and Affiliations

  • Alexander Ilin
    • 1
  • Harri Valpola
    • 2
  1. 1.Helsinki University of TechnologyNeural Networks Research CentreEspoosFinland
  2. 2.Lab. of Computational EngineeringHelsinki University of TechnologyEspooFinland

Personalised recommendations