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.     

Border effects on household dissolution in the Banat Region,Yugoslavia

Abstarct The article recognizes two border effects on average size of households: the past and the present one.Both the incidence and the long-standing tradition of the multifamily and multigenerational households in the past time have been attributed to the influence of Turkish and Austrian state regulations in the period when the area was a part of the Military Border.An attempt is made to estimate the share of vital and spatial mobility factors. In the contemporary process of household dissolution the impact of vital mobility decreases and the impact of spatial mobility increases going from the center towards the periphery.An earlier version of this paper was presented at the Regional Conference of the International Geographical Union, held in Prague in 1994.     

Characterizing the dead time of the ECLAIRs camera on board the mission SVOM

French (CNES) and Chinese (CNSA) space agencies collaborate to build the SVOM (Space-based multi-band Variable Object Monitor) mission due to be launched in 2021 to study gamma-ray bursts and high-energy transients. The SVOM prime instrument, ECLAIRs, will detect and localize GRBs autonomously as well as provide a spectral and temporal characterization of the GRB prompt emission. ECLAIRs is expected to detect around 200 GRBs during the 3 year nominal lifetime of the mission. ECLAIRs is a wide-field (\(\sim 2 \text {sr}\)) coded mask camera with a detection plane made of 8 independent sectors of 800 Schottky CdTe detectors working in the 4-150 keV energy range. Each sector is connected to independent readout electronics. In this paper, we focus on the study of the temporal performance and we estimate how dead time will affect bright transient lightcurves. We discuss the analytical model based on simulations over a large range of source count rates on a dedicated test bench. We show that dead time will not significantly affect ECLAIRs data, even for the brightest GRBs (3.7% of lost counts for a count rate of 10⁵ counts.s^??1 over the detection plane in the energy range 4?150 keV) and our model can nicely correct the parts of the lightcurves which are the most affected by dead time effects for very bright GRBs.     

Alpine tectono‐metamorphic history of the continental units from Vardar zone: the Kopaonik Metamorphic Complex (Dinaric‐Hellenic belt,Serbia)

The easternmost zone of the Dinaric‐Hellenic belt is represented by the Vardar Zone, in which the Kopaonik Metamorphic Complex (KMC) is regarded as the lowermost unit. This complex is topped by the unmetamorphosed Brzece unit and is intruded by the Oligocene Kopaonik Intrusive complex. The KMC is characterized by a stratigraphy that includes metapelites and meta‐carbonates of Late Triassic age, associated with metabasites. It is characterized by a complex deformation history that comprises four phases: D1 to D4. The D1 phase structures occur only as relict structures, whereas the D2 phase structures are represented by isoclinal F2 folds, associated with a well‐developed S2 foliation. The estimated P‐T conditions for the D1 and D2 metamorphism are consistent with the upper greenschist facies. The D3 phase is characterized by west‐verging thrusts associated with upright folds. In contrast, the D4 phase is characterized by open folds (F4) associated with low‐angle normal faults. The D1 and D2 deformation phases developed during the shortening related to continental collision, whereas the subsequent D3 and D4 phases can be related to the progressive exhumation of the KMC. The D4 phase probably developed during extensional tectonics during and after emplacement of the Kopaonik Intrusive Complex. The data show that the continental units belonging to the Vardar zone had a long‐lived deformation history that was more complex that previously thought. Copyright © 2009 John Wiley & Sons, Ltd.     

Refugees and village renewal in Yugoslavia

Using statistics collected by UNHCR and the Serbian government, the paper examines aspects of the refugee problem in FR Yugoslavia whose war-affected population amounted to 646 066 persons in 1996 (a figure that is almost certainly an underestimate). Relatively few refugees will return to their homes even with a political settlement because so many homes are damaged or destroyed. Many people would like to settle in Western Europe and some have already succeeded (especially in Scandinavia where asylum seekers from Former Yugoslavia accounted for 80 percent of the applications in January-September 1993). But regulations are being tightened and asylum seekers are now facing deportation. Housing refugees in FRY is expensive (only 350 refugees got new homes and permanent citizenship in 1994), but some exchanges have been arranged between Serbs arriving from Croatia and Croats established in Vojvodina who are willing to move in the opposite direction. The most promising solution discussed in the paper is resettlement in border villages which have experienced steady depopulation since the Second World War. Houses are available for refurbishment and arable land is cheap. The resettlement of refugee farmers could make an immediate impact on food production and over the longer term there could be sustained economic growth in the context of a newly-constituted Euroregion. Such a strategy would make a virtue out of necessity by helping the refugees and the border regions which have had their potential enhanced by cross-border cooperation. This revised version was published online in July 2006 with corrections to the Cover Date.     

Spatio-temporal regression kriging model of mean daily temperature for Croatia

High resolution gridded mean daily temperature datasets are valuable for research and applications in agronomy, meteorology, hydrology, ecology, and many other disciplines depending on weather or climate. The gridded datasets and the models used for their estimation are being constantly improved as there is always a need for more accurate datasets as well as for datasets with a higher spatial and temporal resolution. We developed a spatio-temporal regression kriging model for Croatia at 1 km spatial resolution by adapting the spatio-temporal regression kriging model developed for global land areas. A geometrical temperature trend, digital elevation model, and topographic wetness index were used as covariates together with measurements from the Croatian national meteorological network for the year 2008. This model performed better than the global model and previously developed models for Croatia, based on MODIS land surface temperature images. The R2 was 97.8% and RMSE was 1.2 °C for leave-one-out and 5-fold cross-validation. The proposed national model still has a high level of uncertainty at higher altitudes leaving it suitable for agricultural areas that are dominant in lower and medium altitudes.     

Problems of regional population growth in Serbia

The paper considers regional differences in population growth in Serbia and highlights the contrast that has emerged between Kosovo and Metohia and the other regions of the country since World War Two. Due to continuing high fertility coupled with declining mortality, growth in Kosovo and Metohia has been three times greater than in Serbia Proper and five times greater than in Voivodina, regions which have been following closely the European demographic transition. Since the population in Kosovo and Metohia is overwhelmingly Albanian these divergent demographic trends are sharpening ethnic tension as the demographic weight of the Serbs decreases in the country as a whole. At the same time the dominance of the Albanians within the province may well contribute to the independence struggle. Since the maintenance of high fertility, with a relatively slow decline - even in comparison with Albania - could be linked with externalities, it is suggested that a solution might be found in more autonomous development for the province which might bring an increase in local responsibility for sustainable development and a decrease in the currently high level of demographic investment. This revised version was published online in July 2006 with corrections to the Cover Date.     

Mapping average annual precipitation in Serbia (1961–1990) by using regression kriging

The appearence of geostatistics and geographical information systems has made it possible to analyze complex spatial patterns of meteorological elements over large areas in the applied climatology. The objective of this study is to use geostatistics to characterize the spatial structure and map the spatial variation of average values of precipitation for a 30-year period in Serbia. New, recently introduced, geostatistical algorithms facilitate utilization of auxiliary variables especially remote sensing data or freely available global datasets. The data from Advanced Spaceborn Thermal Emission and Reflection Radiometer global digital elevation model are incorporated as ancillary variables into spatial prediction of average annual precipitation using geostatistical method known as regression kriging. The R ² value of 0.842 proves high performance result of the prediction of the proposed method.