ITEMS

modern scholarly publishers in the finest tradition

Journals

	Search

Journal of Automation and Information Sciences

ISSN for PRINT: 1064-2315

Institutional price:	$2573.00
Issues per year:	12

Best Paper Award Selection - Editorial Board Site

2007, Volume39

84 pages

DOI: 10.1615/JAutomatInfScien.v39.i12

Issue price - $238.00

Determination of Inundated Territories on the Basis of Integration of Heterogeneous Data

Nataliya N. Kussul
Institute of Space Research of National Academy of Sciences of Ukraine and National Space Agency of Ukraine, Kyiv, Ukraine

Eugene A. Lupian
Institute of Space Research of Russian Academy of Sciences, Moscow, Russia

Andrey Yu. Shelestov
Institute of Space Research of National Academy of Sciences of Ukraine and National Space Agency of Ukraine, Kiev, Ukraine

Sergey V. Skakun
Institute of Space Research of National Academy of Sciences of Ukraine and National Space Agency of Ukraine, Kiev, Ukraine

Yuriy G. Tishchenko
Institute of Radio Engineering and Electronics of Russian Academy of Sciences, Fryazino, Russia

Ladislav Hluchy
Institute of Informatics of Slovac Academy of Sciences, Bratislava, Slovakia

ABSTRACT

We propose a new approach for determination of inundated territories on the basis of radiolocation and optical satellite data. For segmentation and classification of satellite images we use neural networks, namely, self-organizing Kohonen maps. The suggested approach was verified using data of ERS-2 satellite at the time of flood on Tisza river in March 2001. The obtained in this way information can supplement data, which are used on solving monitoring problems for agriculture.