Application of Self-Organizing Maps to the Maritime Environment

  • Victor J. A. S. LoboEmail author
Conference paper
Part of the Lecture Notes in Geoinformation and Cartography book series (LNGC)


Self-Organizing Maps (SOMs), or Kohonen networks, are widely used neural network architecture. This paper starts with a brief overview of how SOMs can be used in different types of problems. A simple and intuitive explanation of how a SOM is trained is provided, together with a formal explanation of the algorithm, and some of the more important parameters are discussed. Finally, an overview of different applications of SOMs in maritime problems is presented.


Self-organizing maps SOM Kohonen networks 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Kohonen T (2001) Self-Organizing Maps. 3rd ed. Information Sciences. Berlin-Heidelberg: SpringerCrossRefGoogle Scholar
  2. 2.
    Fu L (1994) Neural Networks in Computer Intelligence. Singapore: McGraw HillGoogle Scholar
  3. 3.
    Niang A, et al. (2003) Automatic neural classification of ocean color reflectance spectra at the top of the atmosfphere with introduction of expert knowledge. J Remote Sensing of Environment 86: 257-271CrossRefGoogle Scholar
  4. 4.
    Kohonen T (1982) Clustering, Taxonomy, and Topological Maps of Patterns. In: Proceedings of the 6th International Conference on Pattern RecognitionGoogle Scholar
  5. 5.
    Kohonen T (1988) The 'neural' phonetic typewriter. J Computer 21(3): 11-22CrossRefGoogle Scholar
  6. 6.
    MacQueen J (1967) Some methods for classification and analysis of multivariate observation. In: 5th Berkeley Symposium on Mathematical Statistics and Probability, University of California PressGoogle Scholar
  7. 7.
    Loyd SP (1982) Least Squares quantization in PCM. J Transactions on Information Theory 28(2): 129-137CrossRefGoogle Scholar
  8. 8.
    Selim SZ and Ismail MA (1984) k-means type algorithms: a generalized convergence theorem and characterization of local optimality. J Trans. Pattern Analysis and Machine Intelligence 6: 81-87CrossRefGoogle Scholar
  9. 9.
    Bacao F, Lobo V, and Painho M (2005) Self-organizing Maps as Substitutes for K-Means Clustering. In: Sunderam VS, et al (eds) Lecture Notes in Computer Science, Springer-Verlag: Berlin Heidelberg, pp 476-483Google Scholar
  10. 10.
    Sammon JWJ (1969) A Nonlinear Mapping for Data Structure Analysis. J Transactions on Computers, C-18(5): 401-409CrossRefGoogle Scholar
  11. 11.
    Ultsch A and Siemon HP (1990) Kohonen's Self-Organizing Neural Networks for Exploratory Data Analysis. In: Intl. Neural Network Conf. INNC90, ParisGoogle Scholar
  12. 12.
    Altinel IK, Aras N, and Oommen BJ (2000) Fast, Efficiente and accurate solutions to the Hamiltonian path problem using neural approaches. J Computers & Operations Research 27: 461-494CrossRefGoogle Scholar
  13. 13.
    Henriques R (2006) Cartogram creation using self-organizing maps. In: ISEGI, New University of Lisbon: Lisbon. p 144Google Scholar
  14. 14.
    Haykin S (1999) Neural Networks: A Comprehensive Foundation. 2 edGoogle Scholar
  15. 15.
    Martinetz TM, Berkovich SG, and Schulten KJ (1993) Neural-Gas network for vector quantization and its application to time-series prediction. J Transactions on Neural Networks 4(4): 558-569CrossRefGoogle Scholar
  16. 16.
    Kohonen T (1995) Self-Organizing Maps. 1st ed, Berlin-Heidelberg: SpringerCrossRefGoogle Scholar
  17. 17.
    Erwin E, Obermeyer K, Schulten K (1991) Convergence properties of self-organizing maps. In: Kohonen T, et al (eds) Artificial Neural Networks, Elsevier, pp 409-414Google Scholar
  18. 18.
    Ritter H, Martinetz TM, Schulten K (1992) Neural Computation and Self-Organizing Maps: an introduction. Addison-WesleyGoogle Scholar
  19. 19.
    Ultsch A (2005) Clustering with SOM: U*C. In: WSOM 2005, ParisGoogle Scholar
  20. 20.
    Kangas JA, Kohonen TK, Laaksonem JT (1990) Variants of Self-Organizing Maps. J Transactions on Neural Networks 1(1): 93-99CrossRefGoogle Scholar
  21. 21.
    Bação F, Lobo V, Painho M (2005) The Self-Organizing Map, the Geo-SOM, and relevant variants for geosciences. J Computers and Geosciences 31(2): 155-163CrossRefGoogle Scholar
  22. 22.
    Ambroise C et al (1996) Analyzing dissimilarity matrices via Kohonen maps. In: 5th Conference of the International Federation of Classification Societies (IFCS 1996). Kobe, JapanGoogle Scholar
  23. 23.
    Cottrell M, Ibbou S, Letremy P (2004) SOM-based algorithms for qualitative variables. J Neural Networks 17(8-9): 1149-1167CrossRefGoogle Scholar
  24. 24.
    Lobo V, Bandeira N, Moura-Pires F (1998) Distributed Kohonen networks for Passive Sonar Based Classification. In: FUSION 98, Las Vegas, NV, USAGoogle Scholar
  25. 25.
    Lourenço F, Lobo V, Bação F (2004) Binary-based similarity measures for categorical data and their application in Self-Organizing Maps. In: JOCLAD 2004, XI Jornadas de Classificação e Análise de Dados, LisbonGoogle Scholar
  26. 26.
    Guimarães G, Lobo V, Moura-Pires F (2002) A taxonomy of Self-organizing Maps for temporal sequence processing. J Intelligent Data Analysis 7(4)Google Scholar
  27. 27.
    Bacao F, Lobo V, Painho M (2008) Applications of Different Self-Organizing Map Variants to Geographical Information Science Problems. In: Agarwal P, Skupin A (eds) Self-Organizing Maps, Applications in Geographic Information Science, John Wiley & Sons: Chichester, p 205Google Scholar
  28. 28.
    Bação F, Lobo V, Painho M (2005) Geo-SOM and its integration with geographic information systems. In: WSOM 05, 5th Workshop On Self-Organizing Maps, ParisGoogle Scholar
  29. 29.
    Koikkalainen P, Oja E (1990) Self-organizing hierarchical feature maps. In: International Joint Conference on Neural Networks (IJCNN'90), Washington, DC, USAGoogle Scholar
  30. 30.
    Kemke C, Wichert A (1993) Hierarchical Self-Organizing Feature Maps for Speech Recognition. In: World Conference on Neural Networks (WCNN'93), Lawrence Erlbaum, HillsdaleGoogle Scholar
  31. 31.
    Fritzke B (1991) Let it Grow - Self-organizing Feature Maps With Problem Dependent Cell Structure. In: ICANN-91, Helsinki, Elsevier Science PublGoogle Scholar
  32. 32.
    Fritzke B (1996) Growing Self-organizing Networks - Why? In: ESANN'96 European Symposium on Artificial Neural NetworksGoogle Scholar
  33. 33.
    Fritzke B (1995) A growing neural gas network learns topologies, in Advances. In: Tesauro G, Touretzky DS, Leen TK (eds), Neural Information Processing Systems, MIT Press: Cambridge MA, pp 625-632Google Scholar
  34. 34.
    Hammer B, Hasenfuss A, Villmann T (2007) Magnification control for batch neural gas. J Neurocomputing 70(7-9): 1225-1234CrossRefGoogle Scholar
  35. 35.
    Heskes T (1999) Energy Functions for Self-Organizing Maps. In: Oja E and Kaski S (eds) Kohonen Maps, Elsvier: Amsterdam, pp 303-316CrossRefGoogle Scholar
  36. 36.
    Bishop CM, Svensen M, and Williams CKI (1998) GTM: The Generative Topographic Mapping. J Neural Computation 10(1): 215-234CrossRefGoogle Scholar
  37. 37.
    Mather PM, Tso B, Koch M (1998) An evaluation of Landsat TM spectral data and SAR-derived textural information for lithological discrimination in the Red Sea Hills, Sudan. J International Journal of Remote Sensing 19(4): 587-604CrossRefGoogle Scholar
  38. 38.
    Villmann T, Merenyi E, Hammer B (2003) Neural maps in remote sensing image analysis. J Neural Networks 16(3-4): 389-403CrossRefGoogle Scholar
  39. 39.
    Richardson AJ, Risien C, Shillington FA (2003) Using self-organizing maps to identify patterns in satellite imagery. J Progress in Oceanography 59(2-3): 223-239CrossRefGoogle Scholar
  40. 40.
    Hardman-Mountford NJ, et al (2003) Relating sardine recruitment in the Northern Benguela to satellite-derived sea surface height using a neural network pattern recognition approach. J Progress in Oceanography 59(2-3): 241-255CrossRefGoogle Scholar
  41. 41.
    Parikh JA, et al (1999) An evolutionary system for recognition and tracking of synoptic-scale storm systems. J Pattern Recognition Letters 20(11-13): 1389-1396CrossRefGoogle Scholar
  42. 42.
    Leloup JA, et al (2007) Detecting decadal changes in ENSO using neural networks. J Climate Dynamics 28(2-3): 147-162CrossRefGoogle Scholar
  43. 43.
    Liu Y, Weisberg RH, Shay L (2007) Current Patterns on the West Florida Shelf from Joint Self-Organizing Map Analyses of HF Radar and ADCP Data. J Journal of Atmospheric and Oceanic Technology 24: 702-712CrossRefGoogle Scholar
  44. 44.
    Cavazos T (2000) Using self-organizing maps to investigate extreme climate events: An application to wintertime precipitation in the Balkans. J Journal of Climate 13(10): 1718-1732CrossRefGoogle Scholar
  45. 45.
    Lin B, et al (2002) Neural networks in data analysis and modeling for detecting littoral oil-spills by airborne laser fluorosensor remote sensing. In: Conference on Ocean Remote Sensing and Applications, Hangzhou, Peoples R China: Spie-Int Soc Optical EngineeringGoogle Scholar
  46. 46.
    Liu YG, Weisberg RH, He RY (2006) Sea surface temperature patterns on the West Florida Shelf using growing hierarchical self-organizing maps. J Journal of Atmospheric and Oceanic Technology 23(2): 325-338CrossRefGoogle Scholar
  47. 47.
    Liu YG, Weisberg RH, Yuan YC (2008) Patterns of upper layer circulation variability in the South China Sea from satellite altimetry using the self-organizing map. J Acta Oceanologica Sinica 27: 129-144Google Scholar
  48. 48.
    Tozuka T, et al (2008) Tropical Indian Ocean variability revealed by self-organizing maps. J Climate Dynamics 31(2-3): 333-343CrossRefGoogle Scholar
  49. 49.
    Marques NC, Chen N (2003) Border detection on remote sensing satellite data using self-organizing maps. In: 11th Portuguese Conference on Artificial Intelligence, Beja, Portugal: Springer-Verlag BerlinGoogle Scholar
  50. 50.
    Chazottes A, et al (2006) Statistical analysis of a database of absorption spectra of phytoplankton and pigment concentrations using self-organizing maps. J Applied Optics 45(31): 8102-8115CrossRefGoogle Scholar
  51. 51.
    Solidoro C, et al (2007) Understanding dynamic of biogeochemical properties in the northern Adriatic Sea by using self-organizing maps and k-means clustering. J Journal of Geophysical Research-Oceans 112(C7): 13Google Scholar
  52. 52.
    Liu YG, Weisberg RH (2005) Patterns of ocean current variability on the West Florida Shelf using the self-organizing map. J Journal of Geophysical Research-Oceans 110(C6): 12Google Scholar
  53. 53.
    Reusch DB, Alley RB (2006) Antarctic sea ice: a self-organizing map-based perspective. In: International Symposium on Cryospheric Indicators of Global Climate Change, Cambridge, ENGLAND: Int Glaciological SocGoogle Scholar
  54. 54.
    Kropp J, Klenke T (1997) Phenomenological pattern recognition in the dynamical structures of tidal sediments from the German Wadden Sea. J Ecological Modelling 103(2-3): 151-170CrossRefGoogle Scholar
  55. 55.
    Cassano EN, et al (2006) Classification of synoptic patterns in the western Arctic associated with extreme events at Barrow, Alaska, USA. J Climate Research 30(2): 83-97CrossRefGoogle Scholar
  56. 56.
    Hewitson BC, Crane RG (2002) Self-organizing maps: applications to synoptic climatology. J Climate Research 22(1): 13-26CrossRefGoogle Scholar
  57. 57.
    Kubo M, Muramoto K (2007) Classification of clouds in the Japan Sea area using NOAA AVHRR satellite images and self-organizing map. In: IEEE International Geoscience and Remote Sensing Symposium (IGARSS), Barcelona, SPAINGoogle Scholar
  58. 58.
    Reusch DB, Alley RB, Hewitson BC (2007) North Atlantic climate variability from a self-organizing map perspective. J Journal of Geophysical Research-Atmospheres 112(D2): 20Google Scholar
  59. 59.
    Fukumi M, et al (2005) Drift ice detection using a self-organizing neural network. In: 9th International Conference on Knowledge-Based Intelligent Information and Engineering Systems, Melbourne, AUSTRALIA: Springer-Verlag BerlinGoogle Scholar
  60. 60.
    Uotila P, et al (2007) Changes in Antarctic net precipitation in the 21st century based on Intergovernmental Panel on Climate Change (IPCC) model scenarios. J Journal of Geophysical Research-Atmospheres 112(D10): 19Google Scholar
  61. 61.
    Chandrasekar V (2004) SOM of space borne precipitation radar rain profiles on global scale. In: IEEE International Geoscience and Remote Sensing Symposium, Anchorage, AKGoogle Scholar
  62. 62.
    Barros AP, Bowden GJ (2008) Toward long-lead operational forecasts of drought: An experimental study in the Murray-Darling River Basin. J Journal of Hydrology 357(3-4): 349-367CrossRefGoogle Scholar
  63. 63.
    Hyun K, et al (2005) Using an artificial neural network to patternize long-term fisheries data from South Korea. J Aquatic Sciences 67(3): 382-389Google Scholar
  64. 64.
    Chakraborty B, et al (2003) Application of artificial neural networks to segmentation and classification of topographic profiles of ridge-flank seafloor. J Current Science 85(3): 306-312Google Scholar
  65. 65.
    Ultsch A, Roske F (2002) Self-organizing feature maps predicting sea levels. Information Sciences 144(1-4): 91-125CrossRefGoogle Scholar
  66. 66.
    Barreto GA, Araújo AFR, Ritter HJ (2003) Self-Organizing Feature Maps for Modeling and Control of Robotic Manipulators. J Journal of Intelligent and Robotic Systems 36(4): 407-450CrossRefGoogle Scholar
  67. 67.
    Nishida S, et al (2004) Adaptive learning to environment using self-organizing map and its application for underwater vehicles. In: 4th International Symposium on Underwater Technology, Taipei, TAIWANGoogle Scholar
  68. 68.
    Ishii K, et al (2004) A self-organizing map based navigation system for an underwater robot. In: IEEE International Conference on Robotics and Automation, New Orleans, LAGoogle Scholar
  69. 69.
    Nishida S, et al (2007) Self-organizing decision-making system for AUV. In: 5th International Symposium on Underwater Technology/5th Workshop on Scientific Use of Submarine Cables and Related Technologies, Tokyo, JAPANGoogle Scholar
  70. 70.
    Patton R, Webb M, Gaj R (2001) Covert Operations Detection for maritime applications. J Canadian Journal of Remote Sensing 27(4): 306-319Google Scholar
  71. 71.
    Riveiro M, Falkman G, Ziemke T (2008) Visual analytics for the detection of anomalous maritime behavior. In: 12th International Conference Information Visualisation 2008, London, ENGLANDGoogle Scholar
  72. 72.
    Lobo V, Bacao F (2005) One dimensional Self-Organizing Maps to optimize marine patrol activities. In: Oceans 2005 Europe International Conference, Brest, FRANCEGoogle Scholar
  73. 73.
    Lobo V, Moura-Pires F (1995) Ship noise classification using Kohonen Networks. In: EANN 95, Helsinki, FinlandGoogle Scholar
  74. 74.
    Lobo V, Bandeira N, Moura-Pires F (1998) Ship Recognition using Distributed Self Organizing Maps. In: EANN 98, GibraltarGoogle Scholar
  75. 75.
    Lobo V (2002) Ship noise classification: a contrinution to prototype based classifier design, in: Departamento de Informatica, Universidade Nova de Lisboa, LisbonGoogle Scholar
  76. 76.
    Oliveira PM, et al (2002) Detection and Classification of Underwater Transients with Data Driven Methods Based on Time-Frequency Distributions and Non-Parametric Classifiers. In: MTS/IEEE Oceans'02, Biloxi, Mississipi, USAGoogle Scholar
  77. 77.
    Labonté G (1998) A SOM neural network that reveals continuous displacement fields. In: IEEE World Congress on Computational Intelligence, Anchorage, AK, USAGoogle Scholar
  78. 78.
    Ohmia K (2008) SOM-Based particle matching algorithm for 3D particle tracking velocimetry Applied Mathematics and Computation 205(2): 890-898Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2009

Authors and Affiliations

  1. 1.Portuguese Naval Academy, AlfeitePortugal

Personalised recommendations