@InProceedings{XimenesAmar:2011:MaEcDi,
author = "Ximenes, Arimat{\'e}a de Carvalho and Amaral, Silvana",
affiliation = "{Instituto Nacional de Pesquisas Espaciais - INPE} and {Instituto
Nacional de Pesquisas Espaciais - INPE}",
title = "Mapeamento das Ecorregi{\~o}es do Distrito Florestal
Sustent{\'a}vel da BR-163 na Amaz{\^o}nia Brasileira com uso de
redes neurais",
booktitle = "Anais...",
year = "2011",
editor = "Epiphanio, Jos{\'e} Carlos Neves and Galv{\~a}o, L{\^e}nio
Soares",
pages = "3094--3102",
organization = "Simp{\'o}sio Brasileiro de Sensoriamento Remoto, 15. (SBSR).",
publisher = "Instituto Nacional de Pesquisas Espaciais (INPE)",
address = "S{\~a}o Jos{\'e} dos Campos",
keywords = "Self-Organizing Maps, Ecoregions, Neural Network, geoprocessing,
ecorregi{\~o}es, Mapas AutoOrganiz{\'a}veis, geoprocessamento,
redes neurais.",
abstract = "Sustainable Forest District (DFS) is a geo-economic and social
complex that aims the integration between local development and
activities based in forest sustainable exploration. This work was
developed in the scope of PIME project (Projeto Integrado
MCT-EMBRAPA) created to evaluate the social, economic and
environmental impacts of the DFS created along BR-163 road.
Contributing to the biodiversity study group, this paper presents
the methodology and the results from terrestrial ecoregions
mapping for the BR-163 DFS. The Self-Organizing Maps (SOM)
algorithm, based on neural network technique, used GIS layers of
altitude, slope, drainage-density, tree cover percentage (MODIS
TREE), and latitude as environmental variables for the mapping.
The distribution of SOM layers-components indicated absence of
spatial correlation between the selected variables. After final
edition, the ecoregions map divided the area of 167,174 km 2 of
the DFS in 14 ecoregions. Altitude and latitude variables,
considered as climate variable proxies, were mainly responsible
for the north-south ecoregions subdivision. Drainage-density
variable was responsible for defining ecoregions along Tapajos
River. In general, the Kappa value obtained from the discriminant
analysis (0.8) indicates good separability between ecoregions
limits. The BR-163 DFS ecoregion map is available for free
download, in order to obtain feedbacks from other dataset
comparisons, and to promote discussions about local environmental
heterogeneity and biodiversity.",
conference-location = "Curitiba",
conference-year = "30 abr. - 5 maio 2011",
isbn = "{978-85-17-00056-0 (Internet)} and {978-85-17-00057-7 (DVD)}",
language = "pt",
organisation = "Instituto Nacional de Pesquisas Espaciais (INPE)",
ibi = "3ERPFQRTRW/3A4SM35",
url = "http://urlib.net/ibi/3ERPFQRTRW/3A4SM35",
targetfile = "p0430.pdf",
type = "Ecologia, Biodiversidade e An{\'a}lise de Bacias",
urlaccessdate = "09 maio 2024"
}