Luciano Vieira Dutra

A Comparison of Multisensor Integration Methods for Land Cover Classification in the Brazilian Amazon

Many data fusion methods are available, but it is poorly understood which fusion method is suitable for integrating Landsat Thematic Mapper (TM) and radar data for land cover classification. This research explores the integration of Landsat TM and radar images (i.e., ALOS PALSAR L-band and RADARSAT-2 C-band) for land cover classification in a moist tropical region of the Brazilian Amazon. Different data fusion methods—principal component analysis (PCA), wavelet-merging technique (Wavelet), high-pass filter resolution-merging (HPF), and normalized multiplication (NMM)—were explored. Land cover classification was conducted with maximum likelihood classification based on different scenarios. This research indicates that individual radar data yield much poorer land cover classifications than TM data, and PALSAR L-band data perform relatively better than RADARSAT-2 C-band data. Compared to the TM data, the Wavelet multisensor fusion improved overall classification by 3.3%-5.7%, HPF performed similarly, but PCA and NMM reduced overall classification accuracy by 5.1%-6.1% and 7.6%-12.7%, respectively. Different polarization options, such as HH and HV, work similarly when used in data fusion. This research underscores the importance of selecting a suitable data fusion method that can preserve spectral fidelity while improving spatial resolution.

Schistosomiasis risk estimation in Minas Gerais State, Brazil, using environmental data and GIS techniques

The influence of climate and environmental variables to the distribution of schistosomiasis has been assessed in several previous studies. Also Geographical Information System (GIS), is a tool that has been recently tested for better understanding the spatial disease distribution. The objective of this paper is to further develop the GIS technology for modeling and control of schistosomiasis using meteorological and social variables and introducing new potential environmental-related variables, particularly those produced by recently launched orbital sensors like the Moderate Resolution Imaging Spectroradiometer (MODIS) and the Shuttle Radar Topography Mission (SRTM). Three different scenarios have been analyzed, and despite of not quite large determination factor, the standard deviation of risk estimates was considered adequate for public health needs. The main variables selected as important for modeling purposes was topographic elevation, summer minimum temperature, the NDVI vegetation index, and the social index HDI91.

Land Use and Land Cover Mapping in the Brazilian Amazon Using Polarimetric Airborne P-Band SAR Data

In September 2000, an airborne synthetic aperture radar (SAR) mission acquired unprecedented full polarimetric P-band data over the Tapajos National Forest (Para State), which is an area in the Brazilian Amazon which has been continuously monitored in the last three decades. Eight land use/cover classes were identified, namely, primary forest, regeneration older than 25 years, regeneration between 12 and 25 years, regeneration between 6 and 12 years, regeneration younger than six years, crops/pasture, bare soil, and floodplain (FP). The objective of this paper is to analyze the potential of full polarimetric P-band data in distinguishing different land use/cover classes with a minimum established Kappa value of 75%, using the latest development on SAR statistical characterization. The iterated conditional mode (ICM) contextual classifier was applied to amplitude, intensity images, biomass index, and some polarimetric parameters (entropy, alpha angle, and anisotropy) extracted from the polarimetric P-band data. As the accuracy obtained for eight classes was not acceptable, another two sets, with five and four classes, were formed by the combination of the previous ones. They were defined by confusion matrix analysis and by the graphical analysis of average backscatter values, entropy, [alpha] angle, and anisotropy images and by the H/alpha plans of the land use samples. The classification accuracy with four classes (three levels of biomass plus FP) was then considered acceptable with a Kappa value of 76.81%, using the ICM classification with the adequate bivariate distribution for the HV and VV channels.

Spatial distribution of Biomphalaria mollusks at São Francisco River Basin, Minas Gerais, Brazil, using geostatistical procedures.

Geostatistics is used in this work to make inferences about the presence of the species of Biomphalaria (B. glabrata, B. tenagophila and/or B. straminea), intermediate hosts of Schistosoma mansoni, at the São Francisco River Basin, in Minas Gerais, Brazil. One of these geostatistical procedures, known as indicator kriging, allows the classification of categorical data, in areas where the data are not available, using a punctual sample set. The result is a map of species and risk area definition. More than a single map of the categorical attribute, the procedure also permits the association of uncertainties of the stochastic model, which can be used to qualify the inferences. In order to validate the estimated data of the risk map, a fieldwork in five municipalities was carried out. The obtained results showed that indicator kriging is a rather robust tool since it presented a very good agreement with the field findings. The obtained risk map can be thought as an auxiliary tool to formulate proper public health strategies, and to guide other fieldwork, considering the places with higher occurrence probability of the most important snail species. Also, the risk map will enable better resource distribution and adequate policies for the mollusk control. This methodology will be applied to other river basins to generate a predictive map for Biomphalaria species distribution for the entire state of Minas Gerais.

Land use/cover classification in the Brazilian Amazon using satellite images

Land use/cover classification is one of the most important applications in remote sensing. However, mapping accurate land use/cover spatial distribution is a challenge, particularly in moist tropical regions, due to the complex biophysical environment and limitations of remote sensing data per se. This paper reviews experiments related to land use/cover classification in the Brazilian Amazon for a decade. Through comprehensive analysis of the classification results, it is concluded that spatial information inherent in remote sensing data plays an essential role in improving land use/cover classification. Incorporation of suitable textural images into multispectral bands and use of segmentation-based method are valuable ways to improve land use/cover classification, especially for high spatial resolution images. Data fusion of multi-resolution images within optical sensor data is vital for visual interpretation, but may not improve classification performance. In contrast, integration of optical and radar data did improve classification performance when the proper data fusion method was used. Of the classification algorithms available, the maximum likelihood classifier is still an important method for providing reasonably good accuracy, but nonparametric algorithms, such as classification tree analysis, has the potential to provide better results. However, they often require more time to achieve parametric optimization. Proper use of hierarchical-based methods is fundamental for developing accurate land use/cover classification, mainly from historical remotely sensed data.

Analysis and estimative of schistosomiasis prevalence for the state of Minas Gerais, Brazil, using multiple regression with social and environmental spatial data

The aim of this work is to establish a relationship between schistosomiasis prevalence and social-environmental variables, in the state of Minas Gerais, Brazil, through multiple linear regression. The final regression model was established, after a variables selection phase, with a set of spatial variables which contains the summer minimum temperature, human development index, and vegetation type variables. Based on this model, a schistosomiasis risk map was built for Minas Gerais.

Mapping recent deforestation in the Brazilian Amazon using simulated L-band MAPSAR images

Brazilian Amazon Forest biomes are presently under intensive land cover conversion from natural vegetation to agriculture. Timely detection of recent deforestation through orbital remote sensing is a critical requirement for an operational land cover monitoring system in order to provide information to the regulatory systems and decision makers. Optical images present drawbacks for operation in the moist tropics and synthetic aperture radar (SAR) data are a real alternative. The feasibility of using multipolarized L‐band images simulating the Multi‐Application Purpose SAR (MAPSAR) satellite was examined for the detection of recent deforestation in the Tapajós region. The discrimination of recent deforestation from other land cover classes was evaluated through a quantitative analysis based on Jeffreys–Matusitas (JM) distances derived from training samples using amplitude values and supported by field survey. The investigation confirmed the possibility of the discrimination of recently deforested classes from other classes based on the L‐band images as proposed in the MAPSAR.

Multitemporal analysis of land use/land cover JERS-1 backscatter in the Brazilian tropical rainforest

The temporal evolution of L-band microwave backscatter for several land cover types in the Tapajos National Forest is analysed using JERS-1. Five images were acquired from 1993 to 1997. Samples of the studied land cover types were identified after analysis of a Landsat Thematic Mapper (TM) dataset of 12 images obtained from 1984 to 1999. The following land cover types were investigated: bare soil, agriculture, pastures, forest regrowth from 1 to 23-year-old and primary forest. Backscatter behaviour of regrowth stands is influenced by the previous land use and by human impacts such as fire and selective logging. This selective logging can be mechanized or not, because people who live in the Amazon usually cut trees to build houses, bridges, fences, etc. Backscatter of young regrowth stands on sites immediately abandoned after slash and burn increases at a faster rate than young regrowth on sites abandoned after some years of agriculture. Backscatter of old regrowth stands also behaves differently where there are disturbances such as fire or selective logging. In the presence of such disturbances, one finds an oscillating pattern over time, while undisturbed forest shows either a progressive trend or a stable pattern, depending on the age of the stand.

A geoprocessing approach for studying and controlling schistosomiasis in the state of Minas Gerais, Brazil

Geographical information systems (GIS) are tools that have been recently tested for improving our understanding of the spatial distribution of disease. The objective of this paper was to further develop the GIS technology to model and control schistosomiasis using environmental, social, biological and remote-sensing variables. A final regression model (R(2) = 0.39) was established, after a variable selection phase, with a set of spatial variables including the presence or absence of Biomphalaria glabrata, winter enhanced vegetation index, summer minimum temperature and percentage of houses with water coming from a spring or well. A regional model was also developed by splitting the state of Minas Gerais (MG) into four regions and establishing a linear regression model for each of the four regions: 1 (R(2) = 0.97), 2 (R(2) = 0.60), 3 (R(2) = 0.63) and 4 (R(2) = 0.76). Based on these models, a schistosomiasis risk map was built for MG. In this paper, geostatistics was also used to make inferences about the presence of Biomphalaria spp. The result was a map of species and risk areas. The obtained risk map permits the association of uncertainties, which can be used to qualify the inferences and it can be thought of as an auxiliary tool for public health strategies.

The roles of textural images in improving land-cover classification in the Brazilian Amazon

Texture has long been recognized as valuable in improving land-cover classification, but how data from different sensors with varying spatial resolutions affect the selection of textural images is poorly understood. This research examines textural images from the Landsat Thematic Mapper (TM), ALOS (Advanced Land Observing Satellite) PALSAR (Phased Array type L-band Synthetic Aperture Radar), the SPOT (Satellite Pour l’Observation de la Terre) high-resolution geometric (HRG) instrument, and the QuickBird satellite, which have pixel sizes of 30, 12.5, 10/5, and 0.6 m, respectively, for land-cover classification in the Brazilian Amazon. GLCM (grey-level co-occurrence matrix)-based texture measures with various sizes of moving windows are used to extract textural images from the aforementioned sensor data. An index based on standard deviations and correlation coefficients is used to identify the best texture combination following separability analysis of land-cover types based on training sample plots. A maximum likelihood classifier is used to conduct the land-cover classification, and the results are evaluated using field survey data. This research shows the importance of textural images in improving land-cover classification, and the importance becomes more significant as the pixel size improved. It is also shown that texture is especially important in the case of the ALOS PALSAR and QuickBird data. Overall, textural images have less capability in distinguishing land-cover types than spectral signatures, especially for Landsat TM imagery, but incorporation of textures into radiometric data is valuable for improving land-cover classification. The classification accuracy can be improved by 5.2–13.4% as the pixel size changes from 30 to 0.6 m.