Advertisement

Thematic Spatiotemporal Association Rules to Track the Evolving of Visual Features and Their Meaning in Satellite Image Time Series

  • C. R. SilveiraJr.
  • J. R. Cecatto
  • M. T. P. Santos
  • M. X. Ribeiro
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 738)

Abstract

Satellite Image Time Series (SITS) is a set of images taken from the same satellite scene at different times. The mining of SITS is challenging task because it requires spatiotemporal data analysis. An example of the need for SITS mining is the analysis of solar flares and their evolving. Thematic Spatiotemporal Association Rules (TSARs) are associations that show spatiotemporal relationships among the values of the thematics attributes. By employing TSARs, we propose an approach to track the evolving of visual features of SITS images and their meaning. Our approach, called Miner of Thematic Spatiotemporal Associations for Images (MiTSAI), considers the data extracting and transformation, the thematic spatiotemporal association rule mining (TSARs), and the post-processing of the mined TSARs, that relate the visual features and their meaning. Our experiment shows that the proposed approach improves the domain expert team understanding of Solar SITS. Moreover, MiTSAI presented an acceptable time performance being able of extracting and processing TSARs using a long period of historical data faster than the period needed for the arrival of new data in the database.

Keywords

Image classification Spatiotemporal association classifier Solar data Thematic spatiotemporal association rules extraction Temporal series of images Temporal series of semantic data 

Notes

Acknowledgements

The authors thank the SolarMonitor.org for free providing of the solar data used in this work. We also thank CAPES, CNPq and FAPESP for the financial support.

References

  1. 1.
    S.J. Ahmad, R.K. Jolly, Big data manipulation-a new concern to the ICT world (a massive survey/statistics along with the necessity) 1–51 (2015) International Journal of Engineering and Applied Sciences (IJEAS), 4(5) (2017)Google Scholar
  2. 2.
    M. Ivanova, M. Kersten, S. Manegold, Y. Kargin, Data vaults: database technology for scientific file repositories. Comput. Sci. Eng. 15(3), 32–42 (2013)Google Scholar
  3. 3.
    G. Feuerlicht, Database trends and directions: current challenges and opportunities, in DATESO (Citeseer, 2010), pp. 163– 174Google Scholar
  4. 4.
    Y. Hu, V.Y. Gunapati, P. Zhao, D. Gordon, N.R. Wheeler, M.A. Hossain, T.J. Peshek, L.S. Bruckman, G.Q. Zhang, R.H. French, A nonrelational data warehouse for the analysis of field and laboratory data from multiple heterogeneous photovoltaic test sites. IEEE J. Photovoltaics 7, 230–236 (2017)Google Scholar
  5. 5.
    G. Cortés, M. Girotto, S.A. Margulis, Analysis of sub-pixel snow and ice extent over the extratropical andes using spectral unmixing of historical landsat imagery. Remote Sens. Environ. 141, 64–78 (2014)Google Scholar
  6. 6.
    A. Madraky, Z. Othman, A. Hamdan, Analytic methods for spatio-temporal data in a nature-inspired data model. Int. Rev. Comput. Softw. 9(3), 547–556 (2014)Google Scholar
  7. 7.
    V. Radhakrishna, S.A. Aljawarneh, P. Kumar, V. Janaki, A novel fuzzy similarity measure and prevalence estimation approach for similarity profiled temporal association pattern mining. Futur. Gener. Comput. Syst. (2017)Google Scholar
  8. 8.
    C.R. Silveira-Junior, M.T.P. Santos, M.X. Ribeiro, Stretchy time pattern mining: a deeper analysis of environment sensor data, in The Twenty-Sixth International FLAIRS Conference, 2013Google Scholar
  9. 9.
    C.R. Silveira-Junior, D.C. Carvalho, M.T.P. Santos, M.X. Ribeiro, Incremental mining of frequent sequences in environmental sensor data, in The Twenty-Sixth International FLAIRS Conference, 2015Google Scholar
  10. 10.
    K. Pillai, R. Angryk, J. Banda, M. Schuh, T. Wylie, Spatio-temporal co-occurrence pattern mining in data sets with evolving regions, in 2012 IEEE 12th International Conference on Data Mining Workshops (ICDMW), 2012, pp. 805–812Google Scholar
  11. 11.
    T. Landgrebe, A. Merdith, A. Dutkiewicz, R. Mafaler, Relationships between palaeogeography and opal occurrence in Australia: a data-mining approach. Comput. Geosci. 56, 76–82 (2013)CrossRefGoogle Scholar
  12. 12.
    K. Pillai, R. Angryk, B. Aydin, A filter-and-refine approach to mine spatiotemporal co-occurrences, in Proceedings of the 21st ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems (2013), pp. 104–113Google Scholar
  13. 13.
    NOAA, www.solarmonitor.org April 2016. Accessed 13 April 2016
  14. 14.
    H. Bay, T. Tuytelaars, L. Van Gool, Surf: speeded up robust features, in European Conference on Computer Vision (Springer, Berlin, 2006), pp. 404–417Google Scholar
  15. 15.
    M.X. Ribeiro, A.J.M. Traina, C. Traina Jr., A new algorithm for data discretization and feature selection, in Proceedings of the 2008 ACM Symposium on Applied Computing, SAC ’08, New York, NY (ACM, New York, 2008), pp. 953–954Google Scholar
  16. 16.
    F. Petitjean, C. Kurtz, N. Passat, P. GançArski, Spatio-temporal reasoning for the classification of satellite image time series. Pattern Recogn. Lett. 33, 1805–1815 (2012)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing AG, part of Springer Nature 2018

Authors and Affiliations

  • C. R. SilveiraJr.
    • 1
  • J. R. Cecatto
    • 2
  • M. T. P. Santos
    • 1
  • M. X. Ribeiro
    • 1
  1. 1.Federal University of São Carlos (UFSCar)São CarlosBrazil
  2. 2.National Institute of Space ResearchSão José dos CamposBrazil

Personalised recommendations