Advertisement

Oceanology

, Volume 57, Issue 2, pp 265–269 | Cite as

Application of machine learning methods to the solar disk state detection by all-sky images over the ocean

Marine Physics
  • 20 Downloads

Abstract

A new approach to automatic solar disk state detection by all-sky images using machine learning methods is developed and implemented. The efficiency of the most widely used machine learning algorithms is analyzed. The effect of reducing the dimensionality of the feature space on the classification accuracy is estimated. The multilayer artificial neural network model has shown the best accuracy in terms of the true score. The operation result demonstrates the effectiveness of machine learning methods applied to solar disk state detection by all-sky images.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    M. A. Krinitskiy and A. V. Sinitsyn, “Adaptive algorithm for cloud cover estimation from all-sky images over the sea,” Oceanology (Engl. Transl.) 56, 315–319 (2016).Google Scholar
  2. 2.
    M. Minsky and S. Papert, Perceptrons: An introduction to Computational Geometry, Chap. 13: Perceptrons and Pattern Recognition (MIT Press, Cambridge, MA, 1969).Google Scholar
  3. 3.
    RD 52.04.562-96: Recommendations for Hydrometeorological Stations and Posts, No. 5, Part 1: Actinometric Observations at the Stations, Chap. 7.2: Meteorological Parameters and Optic Characteristics of Atmosphere Determined by Actinometric Observations (Rosgidromet, Moscow, 1997), pp. 15–17.Google Scholar
  4. 4.
    S. P. Chistyakov, “Random forests: a review,” Tr. Karel. Nauch. Tsentr, Ross. Akad. Nauk, No. 1, 117–136 (2013).Google Scholar
  5. 5.
    L. Breiman, “Bagging predictors,” Mach. Learn. 24 (2), 123–140 (1996). doi 10.1023/A:1018054314350Google Scholar
  6. 6.
    L. Breiman, “Random forests,” Mach. Learn. 45 (1), 5–32 (2001). doi 10.1023/A:1010933404324CrossRefGoogle Scholar
  7. 7.
    R. A. Fisher, “The use of multiple measurements in taxonomic problems,” Ann. Eugen. 7 (2), 179–188 (1936).CrossRefGoogle Scholar
  8. 8.
    T. Hastie, R. Tibshirani, and J. Friedman, The Elements of Statistical Learning: Data Mining, Inference, and Prediction (Springer-Verlag, New York, 2008), pp. 353–360.Google Scholar
  9. 9.
    G. H. Joblove and D. Greenberg, “Color spaces for computer graphics,” Proceedings of the 5th Annual Conf. on Computer Graphics and Interactive Techniques (SIGGRAPH’ 78) (Association for Computing Machinery, New York, 1978), pp. 20–25. doi 10.1145/800248.80736210.1145/800248.807362Google Scholar
  10. 10.
    J. Kalisch and A. Macke, “Estimation of the total cloud cover with high temporal resolution and parameterization of short-term fluctuations of sea surface insolation,” Meteorol. Z. 17 (5), 603–611 (2008).CrossRefGoogle Scholar
  11. 11.
    Y. Le Cun, J. S. Denker, and S. A. Solla, “Optimal brain damage,” in Advances in Neural Information Processing Systems 2 (NIPS*89), Ed. by D. Touretzky (Morgan Kaufman, Denver, CO, 1990), Vol. 2, pp. 598–605.Google Scholar
  12. 12.
    C. N. Long and J. J. Deluisi, “Development of an automated hemispheric sky imager for cloud fraction retrievals,” 10th Symp. on Meteorological Observations and Instrumentation (Phoenix, AZ, 1998), pp. 171–174.Google Scholar
  13. 13.
    M. Yamashita, M. Yoshimura, and T. Nakashizuka, “Cloud cover estimation using multi-temporal hemisphere imageries,” XXth ISPRS Congress Technical Commission VII, July 12–23, 2004, Istanbul, Turkey (Istanbul, 2004), Vol. 35, Part B7, pp. 826–829.Google Scholar

Copyright information

© Pleiades Publishing, Inc. 2017

Authors and Affiliations

  1. 1.Institute of OceanologyRussian Academy of SciencesMoscowRussia

Personalised recommendations