Fernando Shinji Kawakubo

Mapping changes in coastline geomorphic features using Landsat TM and ETM+ imagery: examples in southeastern Brazil

Multitemporal Landsat Thematic Mapper (TM) and Enhanced Thematic Mapper Plus (ETM+) imagery was used to assess coastline morphological changes in southeastern Brazil. A spectral linear mixing approach (SLMA) was used to estimate fraction imagery representing amounts of vegetation, clean water (a proxy for shade) and soil. Fraction abundances were related to erosive and depositional features. Shoreline, sandy banks (including emerged and submerged banks) and sand spits were highlighted mainly by clean water and soil fraction imagery. To evaluate changes in the coastline geomorphic features, the fraction imagery generated for each data set was classified in a contextual approach using a segmentation technique and ISOSEG, an unsupervised classification. Evaluation of the classifications was performed visually and by an error matrix relating ground-truth data to classification results. Comparison of the classification results revealed an intense transformation in the coastline, and that erosive and depositional features are extremely dynamic and subject to change in short periods of time.

Land-use and vegetation-cover mapping of an indigenous land area in the state of Mato Grosso (Brazil) based on spectral linear mixing model, segmentation and region classification

A spectral linear-mixing model using Landsat ETM+ imagery was undertaken to estimate fraction images of green vegetation, soil and shade in an indigenous land area in the state of Mato Grosso in the central-western region of Brazil. The fraction images were used to classify different types of land use and vegetation cover. The fraction images were classified by the following two methods: (a) application of a segmentation based on the region-growing technique; and (b) grouping of the regions segmented using the per-region unsupervised classifier named ISOSEG. Adopting a 75% threshold, ISOSEG generated 44 clusters that were grouped into eight land-use and vegetation-cover classes. The mapping achieved an average accuracy of 83%, showing that the methodology is efficient in mapping areas of great land-use and vegetation-cover diversity, such as that found in the Brazilian cerrado (savanna).

Use of fraction imagery, segmentation and masking techniques to classify land-use and land-cover types in the Brazilian Amazon

This work presents a procedure for classifying land-use and land-cover (LULC) types in the Brazilian Amazon. Fraction imagery representing proportions of green vegetation, soil, and shade was estimated using all six reflective bands of the Landsat-5 Thematic Mapper (TM1 to TM5 and TM7) through the linear spectral mixing model (LSMM). The fraction information registered at pixel level was then related to different types of land classes following three principal procedures: (1) selecting an image or image group as input for segmentation; (2) application of sequences of masking techniques to address the segmentation of preselected areas in order to obtain better image partitioning; and (3) application of an unsupervised classifier by region, named Isoseg, to group the segmented regions. Isoseg is a clustering algorithm that calculates the centre of each class using the covariance matrix and the average vector of the regions. An assessment of the classification was performed visually and by error matrix, relating reference data points to classification results. The results showed that fraction images were effective in highlighting the different types of LULC. Several tests were conducted to evaluate the efficacy of the masking technique in the process for extracting information. The results showed that the use of masks significantly improves the segmentation results. However, in the Isoseg classification process, the masking technique was not able to avoid omission and commission errors between classes of similar structures. On comparing the results obtained in this work with a Maximum Likelihood classification, it was found that adopting the procedures described resulted in increases of 10% in average and global accuracy, and 18% in average reliability. Furthermore, a reduction was observed in the variability of errors created in the classification.

Mapping coffee crops in southeastern Brazil using spectral mixture analysis and data mining classification

ABSTRACT The task of mapping coffee crops using multispectral data sets is not yet a trivial routine. This is because coffee fields are extremely heterogeneous in terms of spectral reflectance. This study therefore aims to contribute to the mapping of coffee crops using multispectral imagery with 23.5 m spatial resolution taken by the Linear Imaging Self Scanner (LISS III) instrument on board the Indian Remote Sensing (IRS) satellite system. The section of land covered by this study is a traditional coffee-producing province located in the south of the State of Minas Gerais, southeastern Brazil. Whereas the pixel mixture effect was managed using spectral mixture analysis (SMA), the classification was carried out using data mining (DM) techniques. The decision tree (DT) outcomes were evaluated using a simple and qualitative method based on the elements of photointerpretation. In total, eight land-use and land-cover (LULC) types were mapped, including three classes of coffee-growing land expressing different phenological conditions and management. These were named ‘Production Coffee’, ‘Mixed Coffee’, and ‘Old/Pruned Coffee’. The results showed that the methodology was effective for mapping LULC types, as the workflow adopted simplified image interpretation and offered improvements in the classification performance. Despite the coffee-cultivation classes having a large spectral variability, which increases the chances of classification errors, not many confusions were observed involving the three coffee classes mapped with other categories of use. This therefore shows that the method was efficient in isolating the coffee classes (with an accuracy greater than 70%) from other categories of use. Comparing the results obtained in this work with a conventional maximum-likelihood (ML) classification, the results revealed that when using the methodology described, the confusions between classes were less dispersed and an improvement of approximately 10% was observed in the mapping of the Production Coffee class.

Multitemporal analysis of land use types using Landsat-5 TM images in the region of Alfenas, South of Minas Gerais, aiming the conservation of native forest fragments

Several studies have shown that native forest fragments surrounded by different land-use matrixes undergo different ecological pressures on fauna and flora. In light this, we studied the land-use and land-cover changes in the region of Alfenas, southern Minas Gerais state, aiming the conservation of forest fragments. Landsat-5 Thematic Mapper (TM) images, bands 1 to 5 and 7, from 1987 and 2011, were used. Image classification was achieved using the Geographic Data Mining Analyst (GeoDMA), a toolbox specially addressed for spatial data mining. To carry out this investigation, the following procedures were adopted: image segmentation, spectral and spatial features extraction, sampling, decision tree generation, classification, error edition, and analysis of land-use and land-cover changes by using a change detection matrix. The results showed the importance of complementarity of information available in each band for classifying different land use and land cover types. As for land use change, an increase of sugar cane, coffee and bare soil were registered on previously areas used for pasture. Such information are important, since they may support interpretations of ecological dynamics of forest fragments.

MAPEAMENTO DO DESMATAMENTO EM SÃO FÉLIX DO XINGÚ UTILIZANDO COMPOSIÇÃO COLORIDA MULTITEMPORAL DE IMAGENS FRAÇÕES SOMBRA

O objetivo deste trabalho consiste em mapear o avanco do desmatamento no municipio de Sao Felix do Xingu, Sul do Para (Amazonia Brasileira) usando imagens Landsat TM. A tecnica do modelo linear de mistura espectral (MLME) foi empregada para realcar as areas desmatadas. Tres imagens fracoes representando as proporcoes de solo exposto, vegetacao e sombra foram derivadas do MLME. O mapeamento do desmatamento foi feito utilizando os atributos da imagem-fracao sombra que e bem correlacionada com a estrutura do dossel florestal. Apos a segmentacao, as regioes foram agrupadas por um classificador nao-supervisionado por regioes ISOSEG. Palavras-chave: Desmatamento, modelo de mistura, imagem fracao-sombra, analise multitemporal. Abstract The aim of this work consists of mapping deforestation in Sao Felix do Xingu, Southern Para (Brazilian Amazon) using Landsat TM images. Three fraction images representing proportion of bare soil, vegetation, and shade were estimated from the Liner Spectral Mixture Model (LSMM). We choose in this study the shade fraction to discriminate cleared areas because it is well correlated with forest structure. While undisturbed tropical forests usually have medium proportion of shade, cleared areas have low shade content. After segmentation, the homogeneous regions were grouped using an unsupervised classifier named ISOSEG. Key words: Deforestation, Mixture model, Shade fraction image, Multi-temporal analysis. Resumen El objetivo del trabajo es mapear el progreso de la deforestacion en el municipio de Sao Felix do Xingu, Sur de Para (amazonia brasilena), utilizando imagenes Landsat TM. La tecnica del modelo lineal de mezcla espectral (MLME) fue empleada para reducir el volumen de datos y destacar las areas deforestadas. Tres imagenes-fraccion que representan las proporciones de suelo expuesto, vegetacion y sombra se derivaron del MLME. El mapeo de la deforestacion se ha hecho utilizando los atributos del imagen-fraccion sombra que se correlaciona bien con la estructura de la cubierta forestal: mientras que las zonas de bosques intactas tienen un medio coeficiente de sombra (en funcion de la rugosidad de la cubierta), el barbecho, las areas de pastizales y suelo desnudo poseen una baja proporcion en sus estructuras. Despues de la segmentacion, las regiones se combinaron con un clasificador no supervisado por regiones denominado como ISOSEG. Palabras clave: Deforestacion, Modelo de mezcla espectral, Imagenes-fraccion sombra.

MAPEAMENTO DA QUALIDADE DE VIDA URBANA EM POUSO ALEGRE, SUL DE MINAS GERAIS

Este trabalho objetiva mapear a qualidade de vida urbana no municipio de Pouso Alegre – Minas Gerais. A metodologia utilizada consiste na elaboracao de tres indices: indice de qualidade ambiental, indice socioeconomico e indice de educacao, atraves do sistema de recuperacao de informacoes georreferenciadas Estatcart e do Sistema de Informacao Geografica ILWIS. Em seguida, estes tres indices sao combinados para gerar o indice de qualidade de vida. Os resultados mostraram que as regioes que apresentam maiores indices de qualidade de vida sao tambem as areas mais nobres da cidade. Por fim, foi possivel evidenciar os locais onde ha maior necessidade de investimentos publicos.

A florada do cafezal no sul de Minas Gerais

Tudo indica que o cafe chegou ao Brasil, mais precisamente em Belem, trazido clandestinamente da Guiana Francesa a pedido do governador do Maranhao e Grao Para no ano de 1727. No inicio, o seu cultivo era voltado para o consumo interno, mas se expandiu rapidamente para outros estados como Rio de Janeiro, Sao Paulo, Parana e Minas Gerais. No seculo XIX o cafe se tornou a base das exportacoes nacionais. O Brasil de hoje ainda e soberano na producao mundial de cafe, produzindo o dobro do segundo...