Modeling Urban Land Use Changes Using Support Vector Machines

Support Vector Machines (SVM) is a machine learning (ML) algorithm commonly applied to the classification of remotely sensing data and more recently for modeling land use changes. However, in most geospatial applications the current literature does not elaborate on specifications of the SVM method with respect to data sampling, attribute selection and optimal parameters choices. Therefore the main objective of this study is to present and investigate the SVM technique for modeling urban land use change. The SVM model building procedure is presented together with the detailed evaluation of the output results with respect to the choice of datasets, attributes and the change of SVM parameters. Geospatial datasets containing nine land use classes and spatial attributes for the Municipality of Zemun, Republic of Serbia were used for years 2001, 2003, 2007 and 2011. The Correlation‐based Feature Subset method, kappa coefficient, Area Under Receiver Operating Characteristic Curve (AUC) and kappa simulation were used to perform the model evaluation and compare the model outputs with the real land use datasets. The obtained results indicate that the SVM‐based models perform better when implementing balanced data sampling, reduced data sets to informative subsets of attributes and properly identify the optimal learning parameters.     

Tectono-sedimentary evolution of the Miocene Oued Dayr Formation (Ghomaride Complex,Internal Domain of the Maghrebian Rif Belt,Morocco)

This work deals with sedimentological, petrographic, and structural analyses of a middle Miocene late-orogenic sedimentary cycle, denoted Oued Dayr Formation, recognized in the Rifian sector of the Maghrebian Chain (Morocco). The analyzed Formation (75 m thick) starts with 15–20 m of light colored polymict conglomerates, with minor sandstone beds, lying on the Paleozoic basement and Mesozoic cover of the Ghomaride Nappe. Facies analysis indicates a fining-upward deposition in a marine environment characterized by increasing deepening, reflecting a subsidence rate that exceeds sedimentary supply. Petrographic analysis points out that sandstones are represented by litharenites originated by erosion of recycled orogen. The conglomerates pebbles and cobbles consist of Alpine low- to high-grade metamorphic rocks as metarenites, phyllites, mylonitic quartzites, micaschists, augen gneisses deriving from the exhumed deep metamorphic basement, the overlying metasedimentary of the Sebtide Nappes and of sedimentary rocks as sandstones, jaspes, limestones, and shales deriving from the Ghomaride Nappes and their sedimentary cover. Data reveal mixed provenance indicating that the Oued Dayr Formation was fed by the Internal Nappes stack of the Maghrebian Chain. Structural analysis shows that the Oued Dayr Formation accumulated in a Thrust-Top basin, during an early extension (D₀ phase), recorded by synsedimentary normal faults within middle Langhian deposits on the rear of the Internal Nappes stack. Subsequent ductile and brittle compressional (D₁, D₂, D₃) and extensional (D₄) deformation phases occurred during and/or after the stacking, exhumation, and early unroofing of Sebtide Complex coeval with the opening of the western Mediterranean back-arc basins since middle Miocene time.     

The influence of physical and biological processes on the ichthyoplankton communities in the Gulf of Sirte (Southern Mediterranean Sea)

This paper reports on the first study on the ichthyoplankton community structure in the Gulf of Sirte and its spatial distribution in relation to environmental conditions and zooplankton abundance. The results make an important contribution to the future management of fisheries in this unexplored, but much exploited, area. Biological samples were collected in July 2008 using a Bongo40 net. In total, 1914 larvae were found and 1652 of these were identified. In particular, bathypelagic taxa were the most abundant, followed by demersal, mesopelagic, pelagic and epipelagic taxa. The ichthyoplankton community had a patchwork distribution influenced by oligotrophic conditions, the bottom depth and oceanographical features. The results suggest that environmental forcings were able to transport the ichthyoplankton to productive areas. Indeed, maximum fish egg densities were found in coastal stations in correspondence with the Atlantic Tunisian Current inflow, whereas larvae were mainly concentrated in the east side of the Gulf, probably as a result of advection by the anticyclonic circulation. Additionally, the distribution patterns of the total larvae density and the different assemblages were well matched with the abundance of the zooplankton, probably determining final larval survival, growth and recruitment.     

Ontogenic variation and effect of collection procedure on leaf biomechanical properties of Mediterranean seagrass Posidonia oceanica (L.) Delile

Leaf mechanical traits are important to understand how aquatic plants fracture and deform when subjected to abiotic (currents or waves) or biotic (herbivory attack) mechanical forces. The likely occurrence of variation during leaf ontogeny in these traits may thus have implications for hydrodynamic performance and vulnerability to herbivory damage, and may be associated with changes in morphologic and chemical traits. Seagrasses, marine flowering plants, consist of shoot bundles holding several leaves with different developmental stages, in which outer older leaves protect inner younger leaves. In this study we examined the long‐lived seagrass Posidonia oceanica to determine ontogenic variation in mechanical traits across leaf position within a shoot, representing different developmental stages. Moreover, we investigated whether or not the collection procedure (classical uprooted shoot versus non‐destructive shoot method: cutting the shoot without a portion of rhizome) and time span after collection influence mechanical measurements. Neither collection procedure nor time elapsed within 48 h of collection affected measurements of leaf biomechanical traits when seagrass shoots were kept moist in dark cool conditions. Ontogenic variation in mechanical traits in P. oceanica leaves over intermediate and adult developmental stages was observed: leaves weakened and lost stiffness with aging, while mid‐aged leaves (the longest and thickest ones) were able to withstand higher breaking forces. In addition, younger leaves had higher nitrogen content and lower fiber content than older leaves. The observed patterns may explain fine‐scale within‐shoot ecological processes of leaves at different developmental stages, such as leaf shedding and herbivory consumption in P. oceanica.     

Integration of GIS and video surveillance

This paper discusses the integration of three-dimensional (3D) geographic information systems (GIS) and video surveillance systems using augmented reality (AR) techniques. The motivation for this integration is to overcome problems faced by conventional video surveillance systems. Explicit information concerning which camera currently monitors what area in such systems is missing; therefore, insight into the situation depends heavily on the operator’s training and experience. To ensure the complete coordination and monitoring of a situation in a system with multiple cameras, it is necessary to introduce a single reference system. GIS arises as a natural solution because it not only provides a solid ground truth but also provides semantic information that can be highly important in certain video surveillance applications. To integrate information into a GIS application, that information must be georeferenced. Based on our previous research regarding the addition of georeferencing information to surveillance video, this paper introduces models that can be applied to help integrate video and GIS. With an analogy to Milgram’s continuum between the real world and virtual reality, and analogous to the augmented reality and augmented virtuality in Milgram’s continuum, two models of integration are defined here: GIS-augmented video and video-augmented GIS. Then, we define the architecture of GIS-based video surveillance based on these proposed integration models, and finally, a prototype is implemented. The implemented prototype serves as a basis for analysing possible applications of real-world systems based on the integration of GIS and video.