Modeling Urban Land Use Changes Using Support Vector Machines          下载免费PDF全文

Mileva Samardžić‐Petrović  Suzana Dragićević  Miloš Kovačević  Branislav Bajat 《Transactions in GIS》2016,20(5):718-734

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.  相似文献   

Stratigraphic and lithologic characteristics of Pleistocene fluvial deposits in the Danube and Sava riparian area near Belgrade (Serbia)     

D. Nenadić  T. Gaudenyi  K. Bogićević  R. Tošović 《Stratigraphy and Geological Correlation》2016,24(4):427-437

The Quaternary sediments in the Danube and Sava riparian area near Belgrade have a considerable thickness. Several categories of deposits (fluvial-lacustrine, fluvial and aeolian) of Pliocene and Quaternary age have been identified. Their thickness, granulometric composition and paleontological features change depending on the distance from the recent Danube and Sava riverbeds. The Pleistocene fluvial deposits are underlain by sediments of the Late Miocene (Sarmatian and Pannonian) or the Plio-Pleistocene age, and are overlain by fluvial-palustrine deposits of the Pleistocene age and recent alluvial deposits. Pleistocene fluvial deposits that form a major part of the Quaternary sediments, have a great significance, since they are proved to be excellent collectors of ground water. Although these deposits are at lower altitudes in the area of Srem, they could be correlated with the high Danube and Morava terraces in Serbia and Drava in Croatia on the basis of their lithologic and paleontological features.  相似文献   

Integration of GIS and video surveillance     

Aleksandar Milosavljević  Dejan Rančić  Aleksandar Dimitrijević  Bratislav Predić  Vladan Mihajlović 《International journal of geographical information science》2016,30(10):2089-2107

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.  相似文献   

Seismic response and vulnerability of historical Trakošćan Castle,Croatia using HVSR method     

Davor Stanko  Snježana Markušić  Stjepan Strelec  Mario Gazdek 《Environmental Earth Sciences》2016,75(5):368

  相似文献   

Occurrence and distribution of selected potentially toxic elements in soils of playing sites: a case study from Bratislava,the capital of Slovakia     

Edgar Hiller  Lucia Lachká  Ľubomír Jurkovič  Ondrej Ďurža  Katarína Fajčíková  Jaroslav Vozár 《Environmental Earth Sciences》2016,75(20):1390

  相似文献   

Exploring the spatial distribution patterns of South African Cape hakes using generalised additive models     

A Grüss  D Yemane  TP Fairweather 《African Journal of Marine Science》2016,38(3):395-409

We developed delta generalised additive models (GAMs) to predict the spatial distribution of different size classes of South African hakes, Merluccius capensis and M. paradoxus, using demersal trawl survey data and geographical (latitude and longitude) and environmental features (depth, temperature, bottom dissolved oxygen and sediment type). Our approach consists of fitting, for each hake size class, two independent models, a binomial GAM and a quasi-Poisson GAM, whose predictions are then combined using the delta method. Delta GAMs were validated using an iterative cross-validation procedure, and their predictions were then employed to produce distribution maps for the southern Benguela. Delta GAM predictions confirmed existing knowledge about the spatial distribution patterns of South African hakes, and brought new insights into the factors influencing the presence/absence and abundance of these species. Our GAM approach can be used to produce distribution maps for spatially explicit ecosystem models of the southern Benguela in a rigorous and objective way. Ecosystem models are critical features of the ecosystem approach to fisheries, and distribution maps constructed using our GAM approach will enable a reliable allocation of species biomasses in spatially explicit ecosystem models, which will increase trust in the spatial overlaps and, therefore, the trophic interactions predicted by these models.  相似文献   

Pico- and Nanophytoplankton Dynamics in Two Coupled but Contrasting Coastal Bays in the NW Mediterranean Sea (France)     

Floriane Delpy  Bruno Serranito  Jean-Louis Jamet  Gérald Grégori  Christophe Le Poupon  Dominique Jamet 《Estuaries and Coasts》2018,41(7):2039-2055

Due to its ecological context, the Toulon bay represents a site of scientific interest to study temporal plankton distribution, particularly pico- and nanophytoplankton dynamics. A monthly monitoring was performed during a two-year cycle (October 2013–December 2015) at two coupled sampling sites, referred to as Little and Large bays, which had different morphometric characteristics and human pressures. Flow cytometry analyses highlighted the fact that pico- and nanophytoplankton were more abundant in the eutrophic Little bay. Furthermore, it evidenced two community structures across the Toulon bays: at times, a co-dominance of picoeukaryotes, nanoeukaryotes, Synechococcus 1-like cells and Prochlorococcus-like cells was found, and at other times, a Synechococcus 1-like dominated community existed. The alternation of one structure or the other can be explained by a combined action of temperature regime, nutrient conditions and degree of contamination. This study showed that pico- and nanophytoplankton dynamics were mainly driven by temperature in both sites, as in other temperate Mediterranean regions. Thus, the community was mainly composed of picoeukaryotes and Prochlorococcus-like cells in the winter (<?15 °C), while it was dominated by Synechococcus 1-like cells in the summer (>?20 °C). Additionally, the multiple human stressors in the Little bay seemed to affect the increase in abundance of Synechococcus 1-like cells as they were preferentially observed in the Large bay.  相似文献   

Were merely storm-landslides driven by the 2015-2016 Niño in the Mendoza River valley?     

Stella M. Moreiras  Ivan Vergara Dal Pont  Diego Araneo 《Landslides》2018,15(5):997-1014

Since Holocene time, above-mean precipitations recorded during the El Niño warm ENSO phase have been linked to the occurrence of severe debris flows in the arid Central Andes. The 2015–2016 El Niño, for its unusual strength, began driving huge and dangerous landslides in the Central Andes (32°) in the recent South Hemisphere summer. The resulting damages negatively impacted the regional economy. Despite this, causes of these dangerous events were ambiguously reported. For this reason, a multidisciplinary study was carried out in the Mendoza River valley. Firstly, a geomorphological analysis of affected basins was conducted, estimating morphometric parameters of recorded events such as velocity, stream flow, and volume. Atmospheric conditions during such events were analyzed, considering precipitations, snow cover, temperature range, and the elevation of the zero isotherm. Based on our findings, the role of El Niño on the slope instability in the Central Andes is more complex in the climate change scenario. Even though some events were effectively triggered by intense summer rainstorm following expectations, the most dangerous events were caused by the progressive uplifting of the zero isotherm in smaller basins where headwaters are occupied by debris rock glaciers. Our research findings give light to the dynamic coupled system ENSO–climate change–landslides (ECCL) at least in this particular case study of the Mendoza River valley. Landslide activity in this Andean region is driven by wetter conditions linked to the ENSO warm phase, but also to progressive warming since the twentieth century in the region. This fact emphasizes the future impact of the natural hazards on Andean mountain communities.  相似文献   

3rd Regional Symposium on Landslides in the Adriatic-Balkan Region (3rd ReSyLAB)—a final report     

Mateja Jemec Auflič  Matjaž Mikoš  Timotej Verbovšek  Željko Arbanas  Snježana Mihalić Arbanas 《Landslides》2018,15(2):381-384

The 3rd Regional Symposium on Landslides in the Adriatic-Balkan Region (3rd ReSyLAB) was held in Ljubljana, Slovenia, from June 11 to 13, 2017, with 70 participants from nine countries (Austria, Bosnia and Hercegovina, Croatia, Czech Republic, Italy, Republic of Macedonia, Serbia, Slovenia, Spain)—scientists, engineers, researchers, students, experts, politicians, and other decision-makers working in the area of landslide risk reduction in the region. The ReSyLAB is a biannual event organized by the Adriatic-Balkan Network of the International Consortium on Landslides (ICL ABN). Being an important form of activities of this ICL regional network comprising of six ICL members from four countries, it was also a contribution of the International Consortium on Landslides (ICL) to the implementation of the Sendai Framework for Disaster Risk Reduction 2015–2030. This article reports on the main outcomes of the 3rd ReSyLAB Symposium. Altogether, 41 abstracts were published in the symposium book of abstracts, and the symposium proceedings with over 20 reviewed full papers are under preparation to be printed early in 2018. During the 3rd ReSyLAB, a five invited keynote lectures have been presented, and 28 oral presentations are given to the audience. An important part of the symposium was a Round Table entitled “Enhancing cooperation between landslide research community and end users.” On the last day of the symposium, over 30 experts participated in two post-symposium study tours in Slovenia.  相似文献   

The Oeschinensee rock avalanche,Bernese Alps,Switzerland: a co-seismic failure 2300 years ago?     

Patrizia Köpfli  Lorenz M. Grämiger  Jeffrey R. Moore  Christof Vockenhuber  Susan Ivy-Ochs 《Swiss Journal of Geoscience》2018,111(1-2):205-219

Landslide deposits dam Lake Oeschinen (Oeschinensee), located above Kandersteg, Switzerland. However, past confusion differentiating deposits of multiple landslide events has confounded efforts to quantify the volume, age, and failure dynamics of the Oeschinensee rock avalanche. Here we combine field and remote mapping, topographic reconstruction, cosmogenic surface exposure dating, and numerical runout modeling to quantify salient parameters of the event. Differences in boulder lithology and deposit morphology reveal that the landslide body damming Oeschinensee consists of debris from both an older rock avalanche, possibly Kandertal, as well as the Oeschinensee rock avalanche. We distinguish a source volume for the Oeschinensee event of 37 Mm³, resulting in an estimated deposit volume of 46 Mm³, smaller than previous estimates that included portions of the Kandertal mass. Runout modeling revealed peak and average rock avalanche velocities of 65 and 45 m/s, respectively, and support a single-event failure scenario. ³⁶Cl surface exposure dating of deposited boulders indicates a mean age for the rock avalanche of 2.3 ± 0.2 kyr. This age coincides with the timing of a paleo-seismic event identified from lacustrine sediments in Swiss lakes, suggesting an earthquake trigger. Our results help clarify the hazard and geomorphic effects of rare, large rock avalanches in alpine settings.  相似文献