Applications of Neural Networks in Processing and Regionalization of Radiation Data

  • Ladislav Metelka
  • Stanislava Kliegrova
Conference paper


Regionalization of the fields of climatological characteristics may be regarded as one of the most important tasks in data preparation and processing for TRY (Test Reference Years) determination. Broad spectrum of measured climatological characteristics may lead in extremely large number of their possible mutual combinations. But only some characteristics and their combinations are important for technical usage. Moreover, the optimal combination of climatological characteristics is strongly user-dependent.


Neural Network Global Radiation Climatological Characteristic Multilayer Perceptron Neural Network Kohonen Network 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. StatSoft, Inc. (1999). STATISTICA for Windows [Computer program manual]. Tulsa, OK: StatSoft, Ine., 2300 East 14th Street, Tulsa, OK 74104, phone: (918) 749-1119, fax: (918) 749-2217, email: info@statsoft.eom, WEB: http://www.statsoft.eomGoogle Scholar

Copyright information

© Springer-Verlag Wien 2001

Authors and Affiliations

  • Ladislav Metelka
  • Stanislava Kliegrova
    • 1
  1. 1.Branch Hradec KrálovéCzech Hydrometeorological InstituteHradec Králové-Svobodné DvoryCzech Republic

Personalised recommendations