%0 Conference Proceedings
%4 sid.inpe.br/mtc-m16d/2019/
%2 sid.inpe.br/mtc-m16d/2019/
%@issn 2179-4847
%T Evaluating growing self-organizing maps for satellite image time series clustering
%D 2019
%8 11 -13 nov. 2019
%A Adeu, Rodrigo S. S.,
%A Ferreira, Karine Reis,
%A Andrade, Pedro Ribeiro de,
%A Santos, Lorena,
%@affiliation Embraer
%@affiliation Instituto Nacional de Pesquisas Espaciais (INPE)
%@affiliation Instituto Nacional de Pesquisas Espaciais (INPE)
%@affiliation Instituto Nacional de Pesquisas Espaciais (INPE)
%@electronicmailaddress rodrigo.sales@embraer.com.br
%@electronicmailaddress karine.ferreira@inpe.br
%@electronicmailaddress pedro.andrade@inpe.br
%@electronicmailaddress lorena.santos@inpe.br
%E Lisboa Filho, Jugurta,
%E Monteiro, Antonio Miguel Vieira,
%B Simpósio Brasileiro de Geoinformática, 20 (GEOINFO)
%C São José dos Campos
%S Anais do 20º Simpósio Brasileiro de Geoinformática
%I Instituto Nacional de Pesquisas Espaciais (INPE)
%J São José dos Campos
%1 Instituto Nacional de Pesquisas Espaciais (INPE)
%K geoinformatica.
%X In recent years, analysis of time series extracted from Earth observation satellite images has been widely used to produce land use and cover information. In time series analysis, clustering is a common technique performed to discover patterns on data sets. Self-Organizing Maps (SOM) neural network is a suitable method for such task. However, a critical limitation of SOM is that its map structure size must be predetermined. This limitation has been addressed by Growing SOM method. This paper presents an ongoing work on evaluating Growing SOM for Earth observation satellite image time series clustering.
%@language pt
%3 243-248.pdf