Showing papers in "Giscience & Remote Sensing in 2014"
TL;DR: In this paper, a modified normalized difference built-up index (NDBI) has been used for mapping urban builtup areas using Landsat Thematic Mapper (TM) data.
Abstract: The normalized difference built-up index (NDBI) has been useful for mapping urban built-up areas using Landsat Thematic Mapper (TM) data. The applicability of this index to the newer Landsat-8 Operational Land Imager (OLI) data was examined during this study, and a new method for built-up area extraction has been proposed. OLI imagery of urban areas of Lahore, Pakistan, was used to extract built-up areas through a modified NDBI approach and the proposed built-up area extraction method (BAEM). Instead of using individual bands, BAEM employed principal component analysis images of the highly correlated bands pertinent to NDBI computation. Through integration of temperature data, normalized difference vegetation index (NDVI) and modified normalized difference water index (MNDWI), BAEM was able to improve the overall accuracy of built-up area extraction by 11.84% compared to the modified NDBI approach. Rather than employing the binary NDBI, NDVI and MNDWI images, continuous images of these indices were used, ...
196 citations
TL;DR: Unmanned aerial vehicles have become popular platforms for remote-sensing applications, particularly when spaceborne technology, manned airborne techniques, and in situ methods are not as efficient as discussed by the authors,.
Abstract: Unmanned aerial vehicles have become popular platforms for remote-sensing applications, particularly when spaceborne technology, manned airborne techniques, and in situ methods are not as efficient...
168 citations
TL;DR: In this paper, the authors attempt to estimate the quality of coastal waters using a water quality assessment system, and they find that coastal waters are one of the most vulnerable marine systems to environmental pollution, and it is very important to operationally monitor coastal water quality.
Abstract: Since coastal waters are one of the most vulnerable marine systems to environmental pollution, it is very important to operationally monitor coastal water quality. This study attempts to estimate t...
128 citations
TL;DR: In this article, the relationship between land cover patterns and surface temperature was examined using random forest as well as simple linear regression for two urban sites in Denver, Colorado, USA, and the results showed that only trees and roads and parking lots showed significant spatial metrics affecting surface temperature using both the methods.
Abstract: The relationship between land cover patterns and surface temperature was examined using random forest as well as simple linear regression for two urban sites in Denver, Colorado, USA. Among four land cover types of buildings, trees, grass, and roads and parking lots, only trees and roads and parking lots show significant spatial metrics affecting surface temperature using both the methods. For trees, total class area seems the most important factor affecting surface temperature (R2 = 0.47; percentage of increased mean standard error when mean patch area is excluded %IncMSE = 5.35 for Site B in July), followed by aggregation metrics measuring physical connectedness (R2 for patch cohesion index = 0.42) and patch isolation (%IncMSE for mean Euclidean nearest neighbor distance = 6.01 for Site A in July). For roads and parking lots, the existence of dominantly large patches is the most important factor (R2 for range in patch area = 0.40, for largest patch index = 0.40, for Site B in July), followed by total cl...
84 citations
TL;DR: In this article, the authors compared the performance of National Agriculture Imagery Program (NAIP) orthophotography and RapidEye satellite imagery for high-resolution mapping of mining and mine reclamation within a coal surface mine in the southern coalfields of West Virginia, USA.
Abstract: National Agriculture Imagery Program (NAIP) orthophotography is a potentially useful data source for land cover classification in the United States due to its nationwide and generally cloud-free coverage, low cost to the public, frequent update interval, and high spatial resolution. Nevertheless, there are challenges when working with NAIP imagery, especially regarding varying viewing geometry, radiometric normalization, and calibration. In this article, we compare NAIP orthophotography and RapidEye satellite imagery for high-resolution mapping of mining and mine reclamation within a mountaintop coal surface mine in the southern coalfields of West Virginia, USA. Two classification algorithms, support vector machines and random forests, were used to classify both data sets. Compared to the RapidEye classification, the NAIP classification resulted in lower overall accuracy and kappa and higher allocation disagreement and quantity disagreement. However, the accuracy of the NAIP classification was improved by...
56 citations
TL;DR: In this paper, the potential of high-spatial and high-spectral resolution satellite data to map and monitor salt-marsh vegetation communities of Micalo Island of New South Wales, Australia was assessed.
Abstract: Information on wetland condition can be used for various decision-making processes for better management of this vital resource. Salt marshes are complex ecosystems that are not well mapped and understood. This research was conducted to assess the potential of high-spatial and high-spectral resolution satellite data to map and monitor salt-marsh vegetation communities of Micalo Island of New South Wales, Australia. The aim of the study was to determine whether different salt-marsh vegetation species could be differentiated using high-spectral and high-spatial resolution imagery and whether these could be linked to wetland condition. To compare sensor capabilities in discriminating salt-marsh vegetation, high-spatial data sets from Quickbird and high-spectral data sets from Hyperion were used. A hybrid unsupervised and supervised classification procedure was used to assess the wetland mapping potential of the Quickbird and Hyperion data. The supervised classification results had greater overall and within-...
41 citations
TL;DR: In this article, the classification of successional stages by conducting a comparative analysis of classification algorithms (maximum likelihood classifier, artificial neural network, ANN, KNN, support vector machine, SVM, classification tree analysis, CTA, and object-based classification) on varying remote-sensing data sets (Landsat and ALOS PALSAR) was conducted.
Abstract: Research on separation of successional stages has been an active topic for the past two decades because successional vegetation plays an important role in the carbon budget and restoration of soil fertility in the Brazilian Amazon. This article examines classification of successional stages by conducting a comparative analysis of classification algorithms (maximum likelihood classifier – MLC, artificial neural network – ANN, K-nearest neighbour – KNN, support vector machine – SVM, classification tree analysis – CTA, and object-based classification – OBC) on varying remote-sensing data-sets (Landsat and ALOS PALSAR). Through this research we obtained the following four major conclusions: (1) Landsat data provide higher classification accuracy than ALOS PALSAR data, and individual PALSAR data cannot effectively separate successional stages; (2) Fusion of Landsat and PALSAR data provides better classification than individual sensor data; (3) Depending on the data-set, the best classification algorithm varies...
41 citations
TL;DR: In this article, total suspended sediment (TSS) data concentrations are retrieved from two sets of satellite ocean color data (the Moderate Resolution Imaging Spectroradiometer (MODIS) onboard Aqua and the Korean G...
Abstract: Total suspended sediment (TSS) data concentrations are retrieved from two sets of satellite ocean color data (the Moderate Resolution Imaging Spectroradiometer (MODIS) onboard Aqua and the Korean G...
37 citations
TL;DR: In this article, the authors used a series of cases to estimate the digital elevation model (DEM) and identify the landslide scarps, especially potential landslide scars hidden in the forest.
Abstract: Recognition of geomorphic features, such as landslide scarps, is the first key step for landslide risk assessment and mitigation. Geomorphic features can be identified from high-resolution digital elevation model (DEM). Light Detection and Ranging (LiDAR) is a useful tool to collect high-density point elevation data from ground surfaces. LiDAR ground points are used to generate high-resolution DEMs. However, LiDAR sample sizes and interpolation methods are critical parameters for DEM estimation under various land cover types. To discuss the effect of the parameters, this study used a series of cases to estimate the DEMs and identify the landslide scarps, especially potential landslide scarps hidden in the forest.Results show that LiDAR sample size affects the visual identification rate of the landslide scarps. The point density of LiDAR data controls the level of detail that can be resolved in the LiDAR-derived DEM. Given low-density LiDAR ground points, the DEM accuracy is the worst, especially in dense ...
37 citations
TL;DR: In this article, the areas of potential suitable habitat for Siberian cranes in Poyang Lake natural wetland were evaluated using 11 scenes of Landsat TM/ETM+ images.
Abstract: Assessment of habitat quality for wetland-obligate wildlife and endangered species of waterfowl is essential particularly in the changing environment. In this study, the areas of potential suitable habitat for Siberian cranes in Poyang Lake natural wetland were evaluated using 11 scenes of Landsat TM/ETM+ images. Habitat quality was assessed against six landscape indices. Results indicate that the optimum water level for habitats of Siberian cranes in Poyang Lake wetland would be about 12 m. Potential suitable habitat areas would be reduced from about 2300 km2 at 5 m lake level to 530 km2 at 15.6 m lake level. Landscape indices revealed that a higher water level would not be suitable for conservation of Siberian cranes. The proposed Poyang Lake Dam should be operated to control water levels for providing a favorable habitat condition for wintering migratory birds. It would create an unfavorable condition to the wintering habitats for Siberian cranes in Poyang Lake wetland if the dam would maintain the lak...
37 citations
TL;DR: In this article, the utility of using Lidar data to estimate number of trees, tree height and crown width within Barksdale Air Force Base forest management area, Bossier City, Louisiana.
Abstract: Estimating tree characteristics with field plots located in remote and inaccessible areas can be a costly and timely endeavor. Light Detection and Ranging (Lidar) remote sensing allowing for the estimation of the 3-dimensional structure of forest vegetation offers an alternative to traditional ground based forest measurements. This project assessed the utility of using Lidar data to estimate number of trees, tree height and crown width within Barksdale Air Force Base forest management area, Bossier City, Louisiana. Two programs, Lidar Data Filtering and Forest Studies (Tiffs) and Lidar Analyst were used to derive forest measurements, which were compared to field measurements. Based on Root Mean Square Error (RMSE), Lidar Analyst (3.81 trees) performed better than Tiffs (5.71 trees) at estimating average tree count per plot. Tiffs was better at deriving average tree height than Lidar Analyst with an RMSE of 19.08 feet to Lidar Analyst’s RMSE of 21.20 feet. Lidar Analyst, with a RMSE of 25.41 feet, was bett...
TL;DR: In this article, the authors analyzed methodologies based on airborne LiDAR (light detection and ranging) technology of low pulse density points (0.5m−2) for height and volume quantification of olive trees in Viver (Spain).
Abstract: The aim of this study is to analyze methodologies based on airborne LiDAR (light detection and ranging) technology of low pulse density points (0.5 m−2) for height and volume quantification of olive trees in Viver (Spain). A total of 29 circular plots, each with a radius of 20 m, were sampled and their volumes and heights were obtained by dendrometric methods. For these estimations, several statistics derived from LiDAR data were calculated in each plot. Regression models were used to predict volume and height. The results showed good performance for estimating volume (R2 = 0.70) and total height (R2 = 0.67).
TL;DR: In this paper, the Hyperspectral Imager for the Coastal Ocean (HICO) was used to derive chlorophyll-a (chl-a) based on the normalized difference NCI in two Gulf of Mexico coastal estuaries.
Abstract: The Hyperspectral Imager for the Coastal Ocean (HICO) was used to derive chlorophyll-a (chl-a) based on the normalized difference chlorophyll index (NDCI) in two Gulf of Mexico coastal estuaries. C...
TL;DR: In this paper, the authors retrieved the vegetation water content equivalent water thickness (EWT) information and the relevant parameters for the land surface from full-band TM remote sensing data and analyzed the effects of surface water heat flux and surface covering on the EWT via studies of the regional land cover status and the combined EWT with land surface parameters.
Abstract: This article retrieved the vegetation water content equivalent water thickness (EWT) information and the relevant parameters for the land surface from full-band TM remote sensing data. The effects of surface water heat flux and surface covering on the EWT were analyzed via studies of the regional land cover status and the combined EWT with land surface parameters. This article also analyzed the roles and limitations of EWT in drought monitoring combined with classification of the regional drought and regional water stress index (RWSI). From the results, the following conclusions were reported. (1) The spatial distribution of the EWT is closely related to the vegetation, and the EWT is able to monitor the regional water conditions to a certain extent. (2) The distribution of the EWT is affected significantly by the density of vegetation cover, land surface temperature and evapo-transpiration. (3) The correlation between the NDVI (or fractional vegetation cover) and the EWT differs under different vegetation coverage conditions. (4) The evapo-transpiration of the ecological environment is closely tied to the EWT such that the changes in evapo-transpiration affect the EWT significantly. (5) The ability of the EWT to monitor regional drought is conditional, and therefore no significant indication exists that can be used to monitor moderate to severe drought conditions.
TL;DR: In this article, the authors evaluated the use of remote sensing for macronutrient assessment in loblolly pine (Pinus taeda) in North Carolina and Virginia, using spectral reflectance and partial least squares regression (PLSR).
Abstract: Given the economic importance of loblolly pine (Pinus taeda) in the southeastern US, there is a need to establish efficient methods of detecting potential nutrient deficiencies that may limit productivity. This study evaluated the use of remote sensing for macronutrient assessment in loblolly pine. Reflectance-based models were developed at two spatial scales: (1) a natural nutrient gradient across the species’ range, and (2) localized fertilization and genotype treatments in North Carolina and Virginia. Fascicles were collected regionally from 237 samples of 3 flushes at 18 sites, and locally from 72 trees with 2 fertilization treatments and 6 genotypes. Sample spectral reflectance was calculated using a spectroradiometer, and nutrient concentrations were measured with dry combustion and wet chemical digestion. Results were analyzed statistically using nutrient correlations with reflectance and common vegetation indices, and partial least squares regression (PLSR). PLSR performed well at the regional sca...
TL;DR: In this paper, a linear transformation approach was proposed to minimize the influence of variability in the understory to accurately estimate percent tree canopy cover (TCC) from RapidEye satellite data, which was modeled as a function of the Normalized Difference Vegetation Index (NDVI), NDRE, NDVIadj, and NDREadj as explanatory variables.
Abstract: Variability in understory structure is an important problem in estimating tree canopy cover (TCC) with satellite imagery. Differences between understory structure due to the composition and configuration of herbaceous/shrub species often produce different vegetation index values despite these areas having the same TCC. This study offers a linear transformation approach to minimizing the influence of variability in the understory to accurately estimate percent TCC from RapidEye satellite data. TCC was modeled as a function of the Normalized Difference Vegetation Index (NDVI), Normalized Difference Red-Edge Index (NDRE), adjusted (linear transformed) NDVI (NDVIadj), and adjusted NDRE (NDREadj) using simple linear regression. The coefficient of determination of validation () of the models using NDVI, NDRE, NDVIadj, and NDREadj as explanatory variables were, respectively, 0.50 (RMSEvld = 9.64%), 0.38 (RMSEvld = 10.7%), 0.78 (RMSEvld = 6.61%), and 0.73 (RMSEvld = 7.23%). These results showed that the linear tr...
TL;DR: In this article, a hybrid simultaneous-classification and one-by-one classification approach was used to classify urban land covers from 1-meter, 4-band NAIP images.
Abstract: A map showing various urban features, such as buildings, roads, and vegetation, is useful for a variety of urban planning applications. The objective of this study was to incorporate road and parcel GIS data as well as relevant expert knowledge to classify different urban land covers from 1-meter, 4-band NAIP images. Based on a hybrid simultaneous-classification and one-by-one-classification approach, a total of 14 urban classes are classified. The classification map has an overall accuracy of 90%, demonstrating a noticeable improvement over past comparable studies on detailed urban land cover classification.
TL;DR: The authors performed a detailed multi-scale assessment of the MIrAD over the state of Nebraska to determine the thematic accuracy of classified irrigation patterns at various spatial scales (i.e., landscape, field, and subfield) and over various crop types.
Abstract: Accurate and timely information about the geographic distribution of irrigated cropland is important for a range of applications including crop assessments, water resources management, drought monitoring, and environmental modeling. In the United States, a consistent, seamless irrigated agricultural lands map was not available until the development of the 250-m moderate resolution imaging spectroradiometer (MODIS) irrigated agriculture data-set (MIrAD), which was developed from time-series MODIS normalized difference vegetation index, county-level crop area statistics, and land use/land cover (LULC) data using an automated county-level classification approach. This study performed a detailed multi-scale assessment of the MIrAD over the state of Nebraska, which is extensively irrigated, to determine the thematic accuracy of classified irrigation patterns at various spatial scales (i.e., landscape, field, and subfield) and over various crop types. The MIrAD was found to map comparable irrigated cropland pat...
TL;DR: In this paper, the authors examined the relation between temperature trends and vegetation change in Las Vegas and found that in an arid environment, new housing developments that have an increase in vegetation have a cooling affect.
Abstract: This research examines the relation between temperature trends and vegetation change in Las Vegas. A temperature time series is modeled as a superposition of a linear trend and an annual cycle. The model is used to estimate the multi-annual temperature rate of change, which is related to changes in vegetation cover. The change in vegetation cover is estimated using an annual average normalized difference vegetation index (NDVI). The model reveals a general trend of decreasing temperature in Las Vegas from 2000 to 2010. This decrease is less than 0.2 Kelvin per year (K/yr) in older housing developments; however, areas developed during the past decade (North Las Vegas and Southern Highlands) exhibit a decrease of greater than 0.2 K/yr. This temperature change has a correlation of −0.655 with changes in the annual average NDVI. Results reveal that in an arid environment, new housing developments that have an increase in vegetation have a cooling affect. The long-term trend reveals a warming trend. This resea...
TL;DR: In this article, the authors extracted and mapped six land surface phenological metrics including: (1) the peak normalized difference vegetation index (NDVI), (2) peak date, (3) start of season, (4) end of season (EOS), and (5) length of growing season (LOS), and cumulative NDVI from 2000 to 2009 using Moderate-Resolution Imaging Spectroradiometer (MODIS) images covering the United States (US) Great Plains.
Abstract: We extracted and mapped six land surface phenological metrics including: (1) the peak normalized difference vegetation index (NDVI), (2) peak date, (3) start of season (SOS), (4) end of season (EOS), (5) length of growing season (LOS), and (6) cumulative NDVI from 2000 to 2009 using Moderate-Resolution Imaging Spectroradiometer (MODIS) images covering the United States (US) Great Plains. Their patterns relative to monthly precipitation, maximum temperature, minimum temperature, and dew points were analyzed using multiple linear regression, stepwise selection, and geographically weighted regression (GWR) analysis. Both peak NDVI and cumulative NDVI had similar spatial patterns. Their values decreased along an east to west gradient. Peak date and SOS also showed compatible patterns. The southeastern Great Plains had the earliest SOS, peak date, and the longest LOS, given its warmer temperatures and greater precipitation. Dew points in March and October as well as the maximum temperature in April highly infl...
TL;DR: In this paper, urban development trend in contiguous United States based on metropolitan areas (MAs), using two scaled measurements for 1990, 2000 and 2010, was investigated, and the authors found that DMSP-OLS nighttime stable lights data are effective for delineating extent of developed areas, and both measurements show the growth of developed land have slowed from 1990 to 2010.
Abstract: We investigated urban development trend in contiguous United States based on metropolitan areas (MAs), using two scaled measurements for 1990, 2000 and 2010. Linear population density (LPD) was used to compare the same MA over time. Population area growth index (PAGI) was adopted to compare different MAs at the same time. We found that (1) DMSP-OLS nighttime stable lights data are effective for delineating extent of developed areas; (2) both measurements show the growth of developed land have slowed from 1990 to 2010; (3) both measurements show clear regional pattern in urban development in contiguous United States.
TL;DR: In this paper, a geospatial approach for detecting and characterizing the non-stationarity of land-change patterns and examining its potential effect on land change modeling accuracy is presented.
Abstract: The non-stationarity of land-change patterns can potentially affect the accuracy of a spatially explicit land-change projection. Thus, methods for understanding this phenomenon are urgently needed. This paper presents a geospatial approach for detecting and characterizing the non-stationarity of land-change patterns and examining its potential effect on land-change modeling accuracy. It proposes two types of non-stationarity of land-change patterns, viz., non-stationarity+ and non-stationarity–. The former is characterized by an increase in the rate of land change, for example, non-built to built, across the calibration and simulation intervals along the gradient of an explanatory variable, for example, slope, while the latter is characterized by a decrease.
TL;DR: In this paper, an objective approach for quantifying the amount of mangrove loss caused by expansion of shrimp farms in three villages of Krabi Province, Thailand is presented, where Landsat images from three time periods of shrimp farm development (pre-shrimp farms - 1989, development - 2001, and post-development -2007) were analyzed using unsupervised classification algorithm.
Abstract: This paper presents an objective approach for quantifying the amount of mangrove loss caused by expansion of shrimp farms in three villages of Krabi Province, Thailand. Landsat images from three time periods of shrimp farm development (pre-shrimp farms – 1989, development – 2001, and post-development – 2007) were analyzed using unsupervised classification algorithm. A post-classification change detection comparison approach revealed only moderate mangrove exploitation and shrimp farms, which displaced a variety of land-cover types in addition to mangroves. In some cases, there was a detectable cycle of use and replenishment of mangroves and a lack of the boom-bust cycle of shrimp farming that other parts of Thailand experienced.
TL;DR: In this article, a two-part approach for extracting buildings from airborne laser scanning (ALS) point clouds is presented, where building objects are extracted from ALS data by a marked point process using the Gibbs energy model of buildings and sampled by a reversible jump Markov chain Monte Carlo algorithm.
Abstract: Automatic extraction of buildings from airborne laser scanning (ALS) point clouds is essential for 3D building reconstruction. This paper presents a two-part approach for extracting buildings from ALS data. First, building objects are extracted from ALS data by a marked point process using the Gibbs energy model of buildings and sampled by a reversible jump Markov chain Monte Carlo algorithm. Second, a refinement operation is performed to filter the non-building points and false building objects before extracting buildings from the detected building objects. Experimental results and evaluation using ISPRS benchmark data-sets showed the robustness of the proposed method.
TL;DR: Differentiation between benthic habitats, particularly seagrass and macroalgae, using satellite data is complicated because of water column effects plus the presence of chlorophyll-a in both seagra as mentioned in this paper.
Abstract: Differentiation between benthic habitats, particularly seagrass and macroalgae, using satellite data is complicated because of water column effects plus the presence of chlorophyll-a in both seagra
TL;DR: In this article, the authors presented an automatic procedure to compare distribution maps for marine species, using point-to-point and Kappa statistic, and compared global scale maps by applying a solution based on cloud computing, and demonstrated the effectiveness of their approach by a practical use case and the efficiency by comparing it with a sequential computation.
Abstract: Automated comparison of heterogeneous geographical distribution maps detects statistical or punctual differences between these maps. The maps’ contents are heterogeneous; they can differ in format, resolution and scale. In this paper, the comparison is applied to species distributions in geographic areas. We present an automatic procedure to compare distribution maps for marine species. The comparison calculates the similarities at two different granularities, a detailed one that relies on point-to-point comparisons and a more general one using Kappa statistic. Furthermore, our method compares global scale maps by applying a solution based on cloud computing. We demonstrate the effectiveness of our approach by a practical use case and the efficiency by comparing it with a sequential computation. The method allows, for instance, marine biologists and fisheries managers to compare maps. The efficiency allows employing it in interactive systems that need to produce results in short time.
TL;DR: In this paper, spectral and textural attributes from the Advanced Land Imager (ALI)/EO-1 for land-cover mapping and inspected their correlation with biophysical parameters of primary and secondary forests from Eastern Amazon.
Abstract: We analysed spectral and textural attributes from the Advanced Land Imager (ALI)/EO-1 for land-cover mapping and inspected their correlation with biophysical parameters of primary and secondary forests from Eastern Amazon. An artificial neural network (ANN) technique selected the most relevant spectral/textural attributes, which were combined for classification of the ALI scene. From the ANN land-cover map, areas classified as primary forest (PF), initial (SS1), intermediate (SS2) and advanced (SS3) stages of secondary succession were studied. Biophysical parameters were determined from field inventory of 40 sample plots. Results showed an overall classification accuracy of 79% using reflectance and 89% using the combined data set. The combined data set included the reflectance of ALI bands 3–9 and the texture metrics mean (bands 3–4; 6–8) and dissimilarity (band 8). The reflectance of the near-infrared/shortwave infrared bands and their texture mean decreased from SS1 to SS3/PF. The gradient between prim...
TL;DR: In this article, a correction method for false topographic perception phenomena is presented, which combines the orthoimage and the correctly shaded digital elevation model (DEM) to provide the correct three-dimensional visualization of the relief.
Abstract: The pseudoscopic effect in satellite imagery causes perception problems for rugged terrain. The topographic relief is perceived in reverse in images with southeast illumination because of the position of land shadows and the mechanisms of human vision and depth perception. This article presents a correction method for false topographic perception phenomena. Superposition of the orthoimage and the correctly shaded digital elevation model (DEM) provides the correct three-dimensional visualization of the relief. This study demonstrates the applicability of this processing technique for the correction of such effects to provide cartography with a more useful interpretation. The resolution of the DEM employed should be in accordance with the spatial resolution of each image. The opacity level proposed for the overlapping DEM is 50%, 30% and 45% for each image type. The selection of the most appropriate local incidence angle is determined by the level of terrain roughness in the work area.
TL;DR: In this article, the dynamics of cropping systems in a typical agricultural river basin in the state of Mato Grosso were analyzed from 2000 to 2010 using Landsat satellite images and time series of Moderate Resolution Imaging Spectroradiometer vegetation index profiles.
Abstract: The last few decades have been marked by important changes in the Brazilian agriculture, especially with respect to crop-management practices. This study aimed to analyze the dynamics of cropping systems in a typical agricultural river basin in the state of Mato Grosso. Landsat satellite images and time series of Moderate Resolution Imaging Spectroradiometer vegetation index profiles were analyzed from 2000 to 2010. First, we assessed the horizontal expansion that occurred in the agricultural areas. Subsequently, using the product MOD13Q1, some metrics were established to identify the vertical intensification of soil use (single- or double-cropping systems). Results showed stagnation in the expansion of new deforested areas for agriculture in the 2003/2004 growing season, with simultaneous vertical intensification of agriculture. The adoption of the double-cropping system (e.g., soybean/corn and soybean/cotton) expanded by 266% during the studied period and reached 56% of the croplands in the 2009/2010 gr...
TL;DR: The SCEMA was tested using satellite images from the Landsat Thematic Mapper sensor of Landsat 5 for the Amazon region and indicates that cross-entropy minimization by pixel results in a consistent segmenta...
Abstract: A general-purpose unsupervised segmentation algorithm based on cross-entropy minimization by pixel was developed; this algorithm, known as the SCEMA (Segmentation Cross-Entropy Minimization Algorithm), starts from an initial segmentation and iteratively searches the best statistical model, estimating the probability density of the image to reduce the cross-entropy with respect to the previous iteration. The SCEMA was tested using satellite images from the Landsat Thematic Mapper sensor of Landsat 5 for the Amazon region (12 images for testing and 15 for validation). Theme classes identified in the image were (1) water, (2) vegetation, and (3) agriculture. Using the Kappa index and other statistics parameters, the comparison of classifications is made with the following segmentation methods: (1) cross-entropy minimization by pixel, (2) cross-entropy minimization by region, (3) K-means, and (4) maximum likelihood. The results indicate that cross-entropy minimization by pixel results in a consistent segmenta...