Self-Organizing Maps in Earth Observation Data Cubes Analysis

Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 976)


Earth Observation (EO) Data Cubes infrastructures model analysis-ready data generated from remote sensing images as multidimensional cubes (space, time and properties), especially for satellite image time series analysis. These infrastructures take advantage of big data technologies and methods to store, process and analyze the big amount of Earth observation satellite images freely available nowadays. Recently, EO Data Cubes infrastructures and satellite image time series analysis have brought new opportunities and challenges for the Land Use and Cover Change (LUCC) monitoring over large areas. LUCC have caused a great impact on tropical ecosystems, increasing global greenhouse gases emissions and reducing the planet’s biodiversity. This paper presents the utility of Self-Organizing Maps (SOM) neural network method in the process to extract LUCC information from EO Data Cubes infrastructures, using image time series analysis. Most classification techniques to create LUCC maps from satellite image time series are based on supervised learning methods. In this context, SOM is used as a method to assess land use and cover samples and to evaluate which spectral bands and vegetation indexes are best suitable for the separability of land use and cover classes. A case study is described in this work and shows the potential of SOM in this application.


Self-Organizing Maps Earth Observation Data Cubes Analysis Satellite image time series Land Use and Cover Changes 


  1. 1.
    Nativi S, Mazzetti P, Craglia M (2017) A view-based model of data-cube to support big Earth data systems interoperability. Big Earth Data 1:75–99CrossRefGoogle Scholar
  2. 2.
    Lewis A, Oliver S, Lymburner L, Evans B, Wyborn L, Mueller N, Wu W (2017) The Australian geoscience data cube — foundations and lessons learned. Remote Sens Environ 202:276–292CrossRefGoogle Scholar
  3. 3.
    Soille P, Burger A, De Marchi D, Kempeneers P, Rodriguez D, Syrris V, Vasilev V (2018) A versatile data-intensive computing platform for information retrieval from big geospatial data. Future Gener Comput Syst 81:30–40CrossRefGoogle Scholar
  4. 4.
    FAO: Sepal repository (2018). Accessed 14 Dec 2018
  5. 5.
    Suepa T, Qi J, Lawawirojwong S, Messina P (2016) Understanding spatio-temporal variation of vegetation phenology and rainfall seasonality in the monsoon Southeast Asia. Environ Res 147:621–629CrossRefGoogle Scholar
  6. 6.
    Pasquarella J, Holden E, Kaufman L, Woodcock E (2016) From imagery to ecology: leveraging time series of all available landsat observations to map and monitor ecosystem state and dynamics. Remote Sens Ecol Conserv 2(3):152–170CrossRefGoogle Scholar
  7. 7.
    Gomez C, White C, Wulder A (2016) Optical remotely sensed time series data for land cover classification: a review. J Photogram Remote Sens 116:55–72CrossRefGoogle Scholar
  8. 8.
    Bagan H, Wang Q, Watanabe M, Yang Y, Ma J (2005) Land cover classification from Modis EVI time-series data using SOM neural network. Int J Remote Sens 26:4999–5012CrossRefGoogle Scholar
  9. 9.
    Siam L (2013) Soft supervised self-organizing mapping (3SOM) for improving land cover classification with MODIS time-series. PhD thesis, Michigan State University, MichiganGoogle Scholar
  10. 10.
    Maus V, Camara G, Cartaxo R, Sanchez A, Ramos M, Queiroz G (2016) A time-weighted dynamic time warping method for land-use and land-cover mapping. IEEE J Sel Top Appl Earth Observ Remote Sens 9(8):3729–3739CrossRefGoogle Scholar
  11. 11.
    Huete A, Didan K, Miura T, Rodriguez E, Gao X, Fereira L (2002) Overview of the radiometric and biophysical performance of the MODIS vegetation indices. Remote Sens Environ 86:195–213CrossRefGoogle Scholar
  12. 12.
    Picoli M, Camara G, Sanches I, Simoes R, Carvalho A, Maciel A, Coutinho A, Esquerdo J, Antunes J, Begotti R, Arvor D, Almeida C (2018) Big Earth observation time series analysis for monitoring Brazilian agriculture. ISPRS J Photogram Remote Sens 145:328–339CrossRefGoogle Scholar
  13. 13.
    Boles H, Xiao X, Liu J, Zhang Q, Munktuya S, Chen S, Ojima D (2004) Land cover characterization of temperate East Asia using multi-temporal vegetation sensor data. Remote Sens Environ 90(4):477–489CrossRefGoogle Scholar
  14. 14.
    Udelhoven T, Stellmes M, Rodes A (2015) Assessing rainfall-EVI relationships in the Okavango catchment employing MODIS time series data and distributed lag models. In: Revealing land surface dynamics. Remote sensing time series. Springer, Cham, pp 225–245Google Scholar
  15. 15.
    Wehrens R, Buydens L (2007) Self and super-organizing maps in R: the Kohonen package. J Stat Softw 21:1–19CrossRefGoogle Scholar
  16. 16.
    Camara G, Simoes R, Andrade P, Maus V, Sanchez A, Assis L, Santos L, Ywata A, Maciel A, Vinhas L, Ferreira K, Queiroz G (2018) Sits e-sensing/sits: Version 1.12.5, December 2018.

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  1. 1.National Institute for Space Research (INPE)São Jose dos CamposBrazil

Personalised recommendations