@InProceedings{SilvaAHDMDMCS:2023:LaUsLa,
author = "Silva, Gabriel M{\'a}ximo da and Arai, Egidio and Hoffmann,
T{\^a}nia Beatriz and Duarte, Valdete and Martini, Paulo Roberto
and Dutra, Andeise Cerqueira and Mataveli, Guilherme Augusto
Verola and Cassol, Henrique Lu{\'{\i}}s Godinho and Shimabukuro,
Yosio Edemir",
affiliation = "{Instituto Nacional de Pesquisas Espaciais (INPE)} and {Instituto
Nacional de Pesquisas Espaciais (INPE)} and {Instituto Nacional de
Pesquisas Espaciais (INPE)} and {Instituto Nacional de Pesquisas
Espaciais (INPE)} and {Instituto Nacional de Pesquisas Espaciais
(INPE)} and {Instituto Nacional de Pesquisas Espaciais (INPE)} and
{Instituto Nacional de Pesquisas Espaciais (INPE)} and {Instituto
Nacional de Pesquisas Espaciais (INPE)} and {Instituto Nacional de
Pesquisas Espaciais (INPE)}",
title = "Land Use and Land Cover Classification in S{\~a}o Paulo, Brazil,
Using Landsat-8 OLI Images and Derived Specral Indices",
booktitle = "Proceedings...",
year = "2023",
organization = "IEEE International Geoscience and Remote Sensing Symposium",
publisher = "IEEE",
keywords = "LULC, Image classification, Random, Forest, Linear Spectral Mixing
Model.",
abstract = "This article presents a land use and land cover (LULC)
classification map based on Random Forest (RF) classifier
algorithm in the S{\~a}o Paulo State (Brazil), using Landsat-8
OLI data. The method consists in using time series images from
January to December of 2020 based on the spectral and temporal
characteristics of the LULC classes. We performed the
classification class by class considering: water, urban area,
forest, agriculture, forest plantation and pasture. Then, we
pre-processed the selected images based on the spectral
characteristics of the targets to highlight each LULC class. After
that, the classification was performed using RF for each class
individually and then we composed the final map with all LULC
classes. The results showed a global accuracy of 89.10%, kappa
value of 0.8692, producer accuracies greater than 79.80% and user
accuracies greater than 76.82% for the classes mapped. Therefore,
the method is consistent allowing to minimize the classification
errors facilitating the posclassification edition of individual
classes mapped.",
conference-location = "Pasadena",
conference-year = "2023",
label = "lattes: 2801941520834407 1 SilvaAHDMDMCS:2023:LaUsLa",
language = "en",
targetfile = "Land use and Land Cover Classification.pdf",
urlaccessdate = "04 jun. 2024"
}