Anthony M. Filippi

Access Regimes and Regional Land Change in the Brazilian Cerrado, 1972–2002

We examine how access regimes, defined by a set of interrelated institutions and organizations, facilitated the flow of production resources and benefits that resulted in patterns of land change in the Brazilian Cerrado. We analyzed remotely sensed data (Landsat MSS, TM, +ETM) for three time periods (1972/1973–1986, 1986–1992, 1992–2002) with qualitative and archival data for eastern Mato Grosso state. Overall we found that land privately colonized was cleared more rapidly and extensively than lands under no colonization scheme. We also identified significant spatial variability in Cerrado conversion within and outside colonization areas and variability of annual rates of Cerrado conversion during each period. We explain that farmers in the Cerrado engaged in land-leasing and production contracts and worked through cooperatives and firms to marshal resources, including credit, technology, and inputs, which, in turn, influenced land-use decisions and regional patterns of land-cover change. We conclude that a mesoscale analytical framework that examines how land managers access natural and productive resources provides useful insights to explain the processes that cause patterns of high-input agricultural expansion.

Support Vector Machine-Based Endmember Extraction

Introduced in this paper is the utilization of support vector machines (SVMs) to semiautomatically perform endmember extraction from hyperspectral data. The strengths of SVM are exploited to provide a fast and accurate calculated representation of high-dimensional data sets that may consist of multiple distributions. Once this representation is computed, the number of distributions can be determined without prior knowledge. For each distribution, an optimal transform can be determined that preserves informational content while reducing the data dimensionality and, hence, the computational cost. Finally, endmember extraction for the whole data set is accomplished. Results indicate that this SVM-based endmember extraction algorithm has the capability of semiautonomously determining endmembers from multiple clusters with computational speed and accuracy while maintaining a robust tolerance to noise.

River-flow boundary delineation from digital aerial photography and ancillary images using Support Vector Machines

Delineation of river-flow boundaries constitutes an important step in various river-related studies, including river hydraulic modeling, flow-width estimations, and river and floodplain habitat mapping and assessment. Increasing the level of automation of delineation of flow boundaries from synoptic remote-sensing images provides great potential, by reducing the labor cost, especially for studies focusing on long river reaches and those examining flow changes over time. This article investigates the boundary delineation of river channel flow from aerial photographs using Support Vector Machine (SVM) and image-derived ancillary data layers. It also includes a quantitative evaluation of delineation accuracy. The findings show that SVM performs satisfactory delineations of the boundaries, and the ancillary data layers generated using edge detectors and spatial domain texture statistics particularly increase delineation accuracy. Moreover, a multiscale evaluation scheme allows for examining the performance of SVM for the whole river reach, as well as that for the subriver sections with varied geomorphic and environmental conditions.

Effects of virtualization on a scientific application running a hyperspectral radiative transfer code on virtual machines

The topic of system-level virtualization has recently begun to receive interest for high performance computing (HPC). This is in part due to the isolation and encapsulation offered by the virtual machine. These traits enable applications to customize their environments and maintain consistent software configurations in their virtual domains. Additionally, there are mechanisms that can be used for fault tolerance like live virtual machine migration. Given these attractive benefits to virtualization, a fundamental question arises, how does this effect my scientific application? We use this as the premise for our paper and observe a real-world scientific code running on a Xen virtual machine. We studied the effects of running a radiative transfer simulation, Hydrolight, on a virtual machine. We discuss our methodology and report observations regarding the usage of virtualization with this application.

Geographically Adaptive Inversion Model for Improving Bathymetric Retrieval From Satellite Multispectral Imagery

Optical remote sensing imagery offers a cost-effective alternative to echo sounding and bathymetric light detection and ranging surveys for deriving high density bottom depth estimates for coastal and inland water bodies. The common practice of previous studies has been to calibrate a single global bathymetric inversion model for an entire image scene. The performance of conventional global models is limited when the bottom type and water quality vary spatially within the scene. To address the inadequacy of the conventional global models, this paper presents a geographically adaptive inversion model to better estimate bottom depth. Although the general mathematical form of the geographically adaptive model is the same, model parameters are optimally determined within a geographical region or a local area, in contrast to the entire scene in the global inversion model. By using high-resolution IKONOS and moderate-resolution Landsat satellite images, we demonstrated that regionally and locally calibrated inversion models can effectively address the problems introduced by spatial heterogeneity in water quality and bottom type, and provide significantly improved bathymetric estimates for more complex coastal waters.

Hyperspectral agricultural mapping using support vector machine-based endmember extraction (SVM-BEE).

Extracting endmembers from remotely-sensed images of vegetated areas can present difficulties. In this research, we applied a recently-developed endmember-extraction algorithm based on Support Vector Machines to the problem of semi-autonomous estimation of vegetation endmembers from a hyperspectral image. This algorithm, referred to as Support Vector Machine-Based Endmember Extraction (SVM-BEE), accurately and rapidly yields a computed representation of hyperspectral data that can accommodate multiple distributions. The number of distributions is identified without prior knowledge, based upon this representation. Prior work established that SVM-BEE is robustly noise-tolerant and can semi-automatically estimate endmembers; synthetic data and a geologic scene were previously analyzed. Here we compared the efficacies of SVM-BEE, N-FINDR, and SMACC algorithms in extracting endmembers from a real, predominantly-agricultural scene. SVM-BEE estimated vegetation and other endmembers for all classes in the image, which N-FINDR and SMACC failed to do. SVM-BEE was consistent in the endmembers that it estimated across replicate trials. Spectral angle mapper (SAM) classifications based on SVM-BEE-estimated endmembers were significantly more accurate compared with those based on N-FINDR- and (in general) SMACC-endmembers. Linear spectral unmixing accrued overall accuracies similar to those of SAM.

Hyperspectral remote sensing of aboveground biomass on a river meander bend using multivariate adaptive regression splines and stochastic gradient boosting

Research on aboveground biomass (AGB) retrieval via remote sensing in floodplain forests, in particular, is urgently needed for improved understanding of carbon cycling in such areas. AGB estimation is particularly challenging in floodplain forests, which are characterized by high spatial variability in AGB resulting from biogeomorphodynamic processes. In this study, we perform remote AGB retrieval for a deciduous riparian forest on a river meander bend based on hyperspectral/high-dimensional Hyperion bands and other input variables. We compare multivariate adaptive regression splines (MARS)-, stochastic gradient boosting (SGB)- and Cubist-based AGB estimates. Results show that MARS- and SGB-derived estimates are significantly more accurate than Cubist-based AGB. The most accurate MARS and SGB estimates have a coefficient of determination, R2, of 0.97 and 0.95, respectively, whereas the Cubist estimate with the lowest error has an R2 of 0.85. MARS and SGB AGB are not significantly different, however. These modelling approaches are applicable across scales and environments.

Effect of Continuum Removal on Hyperspectral Coastal Vegetation Classification Using a Fuzzy Learning Vector Quantizer

Continuum removal (CR) is often used for geologic mapping; however, more research is needed to better establish the utility of CR for vegetation classification, particularly when used with artificial neural networks (ANNs). In this paper, fuzzy learning vector quantization (FLVQ) was applied to hyperspectral Airborne Visible/Infrared Imaging Spectrometer imagery for coastal vegetation classification. FLVQ performance was compared with that of a multilayer perceptron (MLP), a self-organizing map (SOM), and an endmember-based algorithm [spectral feature fitting (SFF)]. The objective was to assess the effect of CR as an input vector-preprocessing step for ANN model development on classification accuracy. Compared with a related study, continuum intact (CI) reflectance data generally yielded higher classification accuracies than those based on CR. Thus, CR may not be a preferred preprocessing method for coastal vegetation mapping over broad wavelength ranges. MLP slightly outperformed FLVQ when applied to CI data, but FLVQ yielded higher accuracy than MLP with CR. However, there was no significant difference between them for both data treatments at the 95% confidence level. All ANNs tested yielded significantly higher classification accuracies than SFF. For model development, the 588-neuron FLVQ required only 8.2% of MLP training time, 27.8% of the 400-neuron SOM time, and 8.8% of the 729-neuron 3-D SOM time

Spatial scale management experiments using optical aerial imagery and LIDAR data synergy.

Computational trends toward shared services suggest the need to automatically manage spatial scale for overlapping applications. In three experiments using high-spatial-resolution optical imagery and LIDAR data to extract impervious, forest, and herbaceous classes, this study optimized C5.0 rule sets according to: (1) spatial scale within an image tile; (2) spatial scale within spectral clusters; and (3) stability of predicted accuracies based on cross validation. Alteration of the image segmentation scale parameter affected accuracy as did synergy with LIDAR derivatives. Within the tile examined, forest and herbaceous areas benefited more from optical and LIDAR synergy than did impervious surfaces.

Self-Organizing Map-based Applications in Remote Sensing

Remote sensing involves the collection of information about an object from a distance. Often remote-sensing instruments are mounted onboard an airor space-borne platform and typically record electromagnetic energy in specific wavelength intervals, or bands. The electromagnetic energy recorded over a given area contains information about surfaces reflecting or emitting energy. This information can be used for a variety of applications; for example, remote-sensing image analysis can extract thematic information such as land-cover types (Jensen, 2005). Artificial neural network (ANN) techniques have increasingly been employed in the analysis of remotely-sensed images. ANNs can be advantageous in digital image processing in that no assumption is made about the statistical properties of the images, and they are thus widely applicable to a variety of dataset types. In addition, ANNs learn adaptively through examples and have a high tolerance to noisy or incomplete data (Jensen, 2005). ANN model development can proceed via either supervised or unsupervised means, and if adequate training data are available, supervised training may be readily performed. However, obtaining reliable training data in remote-sensing applications is often problematic (Congalton and Green, 1999), as a remote sensor image typically covers a large area, and only a limited number of training locations can be sampled in the field due to cost, time, personnel requirements, and various other logistical constraints, including potential restrictions on access to the study area. Unsupervised image-processing methods— including unsupervised ANNs—can be of significant utility in such circumstances (Filippi et al., 2009). Unsupervised ANNs are used in situations where the correct outputs may not be known, or if it is desired that the network discover or categorize regularities or features in the training data on its own. There is no teacher signal (Hassoun, 1995). The unsupervised Kohonen self-organizing map (SOM) is a two-layer network, with an input fan-out layer, and an output layer (known as the Kohonen or competitive layer), and the method is based upon competitive learning. The Kohonen layer is comprised of a physical net of neurons located at fixed positions (i.e., intersections in a grid of square meshes). Adjacent neurons are assumed to have a Euclidean distance of unity. The input 14