Search

The assessment of the potential use of renewable energy resources requires reliable and precise data inputs for sustainable energy planning on a regional, national and local scale. In this study, we examine high spatial resolution grids of potential insolation and solar duration in order to determine the location of potential solar power plants in Montenegro. Grids with a 25-m spatial resolution of potential solar radiation and duration were produced based on observational records and publicly available high-resolution digital elevation model provided by the European Environment Agency. These results could be further used for the estimation and selection of a specific location for solar panels. With an average annual potential insolation of 1800 kWh/m² and solar duration of over 2000 h per year for most of its territory, Montenegro is one of the European countries with the highest potential for the development, production, and consumption of solar energy.

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.

The goal of this study is to analyse the predictive performance of the random forest machine learning technique in comparison to commonly used hedonic models based on multiple regression for the prediction of apartment prices. A data set that includes 7407 records of apartment transactions referring to real estate sales from 2008–2013 in the city of Ljubljana, the capital of Slovenia, was used in order to test and compare the predictive performances of both models. Apparent challenges faced during modelling included (1) the non-linear nature of the prediction assignment task; (2) input data being based on transactions occurring over a period of great price changes in Ljubljana whereby a 28% decline was noted in six consecutive testing years; and (3) the complex urban form of the case study area. Available explanatory variables, organised as a Geographic Information Systems (GIS) ready dataset, including the structural and age characteristics of the apartments as well as environmental and neighbourhood information were considered in the modelling procedure. All performance measures (R2 values, sales ratios, mean average percentage error (MAPE), coefficient of dispersion (COD)) revealed significantly better results for predictions obtained by the random forest method, which confirms the prospective of this machine learning technique on apartment price prediction.

The representation of land use change (LUC) is often achieved by using data-driven methods that include machine learning (ML) techniques. The main objectives of this research study are to implement three ML techniques, Decision Trees (DT), Neural Networks (NN), and Support Vector Machines (SVM) for LUC modeling, in order to compare these three ML techniques and to find the appropriate data representation. The ML techniques are applied on the case study of LUC in three municipalities of the City of Belgrade, the Republic of Serbia, using historical geospatial data sets and considering nine land use classes. The ML models were built and assessed using two different time intervals. The information gain ranking technique and the recursive attribute elimination procedure were implemented to find the most informative attributes that were related to LUC in the study area. The results indicate that all three ML techniques can be used effectively for short-term forecasting of LUC, but the SVM achieved the highest agreement of predicted changes.

The behavior of reinforced concrete under long-term loading is an important topic when designing concrete structures. Creep and shrinkage of concrete and long-term deflections of concrete structures, mainly reinforced concrete beams, have been studied for many decades but because of the long-term nature of these tests, existing experiments are relatively scarce. More importantly, there are significant challenges when carrying out these tests. These include achieving optimal beam design to ensure a realistic stress distribution with a developed cracked state, measuring deflections from self-weight, adequately measuring elastic deflections and strains, and instantaneously applying the imposed load. The problem is exacerbated with the advent of sustainable structural concretes containing recycled and waste materials-green concretes; they possess specific properties and experimental results for these concretes are even scarcer. In this paper, an experimental setup, designed to test the structural behavior of reinforced concrete beams in a four-point bending test under long-term loading, is described. Six full-scale beams were produced from natural aggregate concrete, recycled aggregate concrete and high-volume fly ash concrete-two beams from each concrete type, one loaded after 7 and the other after 28 days. The load consisted of beam self-weight and imposed permanent load. The beam design procedure is explained, which enabled an adequate stress distribution and crack formation with a minimum imposed load. A method was developed to use geodetic equipment and measurements to determine the deflection from self-weight and a special support and loading structure were designed to enable instant imposed load application and the measurement of elastic deflections and strains. The complete test setup, equipment and procedure are explained and the advantages and deficiencies of this approach are discussed.

This paper presents possibilities of applying the geographically weighted regression method in mapping population change index. During the last decade, this contemporary spatial modeling method has been increasingly used in geographical analyses. On the example of the researched region of Timocka Krajina (defined for the needs of elaborating the Regional Spatial Plan), the possibilities for applying this method in disaggregation of traditional models of population density, which are created using the choropleth maps at the level of statistical spatial units, are shown. The applied method is based on the use of ancillary spatial predictors which are in correlation with a targeted variable, the population change index. For this purpose, spatial databases have been used such as digital terrain model, distances from the network of I and II category state roads, as well as soil sealing databases. Spatial model has been developed in the GIS software environment using commercial GIS applications, as well as open source GIS software. Population change indexes for the period 1961-2002 have been mapped based on population census data, while the data on planned population forecast have been used for the period 2002-2027.

During the last decade, the development of computational technique has influenced wider implementation of numerical methods in different software applications, which are oriented to processing, presentation, and analysis of spatial data. This is particularly the case for geostatistical methods, which were developed for analysis of the data, which include spatial components. Those methods provide analytical processing and description of spatial continuity, which is an important characteristic for numerous natural phenomena. Implementation of classical statistical methods does not allow the perception of spatial distribution of natural phenomena. The development GIS (Geographical Information Systems) applications, especially geostatistical modules, enabled a lot of users dealing with spatial modeling and analysis to apply them in their work.

Digital terrain models (DTMs) represent segments of spatial data bases related to presentation of terrain features and landforms. Square grid elevation models (DEMs) have emerged as the most widely used structure during the past decade because of their simplicity and simple computer implementation. They have become an important segment of Topographic Information Systems (TIS), storing natural and artificial landscape in forms of digital models. This kind of a data structure is especially suitable for morph metric terrain evaluation and analysis, which is very important in environmental and urban planning and Earth surface modeling applications. One of the most often used functionalities of Geographical information systems software packages is indivisibility or view shed analysis of terrain. Indivisibility determination from analog topographic maps may be very exhausting, because of the large number of profiles that have to be extracted and compared. Terrain representation in form of the DEMs databases facilitates this task. This paper describes simple algorithm for terrain view shed analysis by using DEMs database structures, taking into consideration the influence of uncertainties of such data to the results obtained thus far. The concept of probability maps is introduced as a mean for evaluation of results, and is presented as thematic display.

The overview of the contemporary data acquisition methods for Digital Terrain Models (DTM), as well as the accuracy of data provided by these methods, are given in this article. The procedure of the accuracy estimation for DTM which is produced by digitizing of topographic maps and test points obtained by GPS technology and aerophotogrammetric terrain surveying, is presented.

Digital terrain models (DTM) have recently become products which substitute standard methods for the terrain relief presentation. As a part of a Geographic Information Systems (GIS) they represent not only a data base related to heights that are used for terrain visualization by the means of interpolation routines for the generation of contours, or terrain presentation by the 3D meshes, but also a useful data base in many GIS and other applications. Numerous users of DTMs should also be supplied with information of DTM quality. This is obtained by the statistical analysis of residuals between generated height and heights of the control points called ground truth. The results of this analysis might be compulsorily part of metadata base for all DTMs products.

This paper outlines a methodology used to disaggregate a census population in order to more accurately determine the population distribution over a regional area or a state scale. Data regarding population distributions are usually accessible at the level of individual census designation places and are usually mapped as aggregated polygons by the choropleth method with the assumption of a homogeneous distribution of population within a cartographic unit. In contrast, dasymetric mapping provides a more reliable view into the allocation of inhabitants, which can be of significant importance when estimating population distributions. Coupling this methodology with the GIS environment and a free open access database of soil sealing facilitates the acquisition of population surface models for human and urban geography applications.

Case study addresses NW slopes of Fruska Gora Mountain, Serbia. Landslide activity is quite notorious in this region, especially along the Danube's right river bank, and recently intensified seismicity coupled with atmospheric precipitation might be critical for triggering new landslide occurrences. Hence, it is not a moment too soon for serious landslide susceptibility assessment in this region. State-of-the-art approaches had been taken into consideration, cutting down to the Support Vector Machine (SVM) and k-Nearest Neighbor (k-NN) algorithms, trained upon expert based model of landslide susceptibility (a multi-criteria analysis). The latter involved Analytical Hierarchy Process (AHP) for weighting influences of different input parameters. These included elevation, slope angle, aspect, distance from flows, vegetation cover, lithology, and rainfall, to represent the natural factors of the slope stability. Processed in a GIS environment (as discrete or float raster layers) trough AHP, those parameters yielded susceptibility pattern, classified by the entropy model into four classes. Subsequently the susceptibility pattern has been featured as training set in SVM and k-NN algorithms. Detailed fitting involved several cases, among which SVM with Gaussian kernel over geo-dataset (coordinates and input parameters) reached the highest accuracy (88%) outperforming other considered cases by far.

We are witnessing nowadays that the last decade of the past century, as well as the first years of the present one, have brought technology expansion with respect to spatial data gathering and processing which makes a physical basis for management of spatial development. This has resulted in enlargement of the spatial data market. New technologies, presented in computer applications, have greatly expanded the number of users of these products. The philosophy of spatial data collecting has changed; analogue maps and plans printed on paper have been replaced by digital data bases which enable their presentation in a way that is the best for a particular user. Further, digital spatial data bases provide the possibility of their further upgrading by users. The two aspects, with respect to circumstances mentioned above, are very important in the process of data bases production and distribution. Firstly, the users of these data bases should be the ones who decide which of the available bases could satisfy their requirements, or in other words, what is the data quality level necessary for a certain application. On the other hand, the visualization of digital data bases could often mislead, since review of data bases could present data with better accuracy then the actual one. Thus, certain methods that would point to a quality of the selected data in the process of their analysis should be available to users. Specific, already adopted international standards, or specially developed procedures and methodologies, so called de facto standards, could be used in this data processing, enabling the estimation of these data quality. The development of Open GIS concept requires the adoption of widely accepted standards for spatial data quality. It is recommended that ISO standards should be accepted, firstly TC211 standards which are related to geographic information and geomatics. The realization of projects on ISO standards should be finished by 2006, so, all participants of these data bases should be both familiar with this project and ready to adapt to the given solutions. The basic components defining quality of data bases are explained by this work, and the results of the standardization regarding the procedures and methodology of their quality assessment, obtained so far, are also presented.