Ljubomir Gigović’s research while affiliated with National Defense University and other places

This paper presents the application of the spatial model in assessing the threat of critical infrastructure from potential terrorist mini Unmanned Aerial Vehicles (UAV) attacks. The proposed model is based on the combined use of the Geographic Information System with Fuzzy Multicriteria Overlay Weighted Least Cost Path (GIS-FMWO-LCP) and analysis of the best-worst flight path assessment of UAVs. The model was applied to the case study of critical infrastructure in the southern Serbia. The implementation of the model showed that out of a total of 12 test sites, 67% are suitable for the use of mini-UAVs in a potential terrorist attack. The proposed spatial model can be successfully used in the assessment of the threat of terrorist attacks of mini-UAVs in a similar geographical area. Also, the proposed model is suitable for planning the flight of UAVs for the needs of transport and assistance in technological and natural disasters, fire protection monitoring.

In this study, we developed multiple hybrid machine-learning models to address parameter optimization limitations and enhance the spatial prediction of landslide susceptibility models. We created a geographic information system database, and our analysis results were used to prepare a landslide inventory map containing 359 landslide events identified from Google Earth, aerial photographs, and other validated sources. A support vector regression (SVR) machine-learning model was used to divide the landslide inventory into training (70%) and testing (30%) datasets. The landslide susceptibility map was produced using 14 causative factors. We applied the established gray wolf optimization (GWO) algorithm, bat algorithm (BA), and cuckoo optimization algorithm (COA) to fine-tune the parameters of the SVR model to improve its predictive accuracy. The resultant hybrid models, SVR-GWO, SVR-BA, and SVR-COA, were validated in terms of the area under curve (AUC) and root mean square error (RMSE). The AUC values for the SVR-GWO (0.733), SVR-BA (0.724), and SVR-COA (0.738) models indicate their good prediction rates for landslide susceptibility modeling. SVR-COA had the greatest accuracy, with an RMSE of 0.21687, and SVR-BA had the least accuracy, with an RMSE of 0.23046. The three optimized hybrid models outperformed the SVR model (AUC = 0.704, RMSE = 0.26689), confirming the ability of metaheuristic algorithms to improve model performance.

Hazards and disasters have always negative impacts on the way of life. Landslide is an overwhelming natural as well as man-made disaster that causes loss of natural resources and human properties throughout the world. The present study aimed to assess and compare the prediction efficiency of different models in landslide susceptibility in the Kysuca river basin, Slovakia. In this regard, the fuzzy decision-making trial and evaluation laboratory combining with the analytic network process (FDEMATEL-ANP), Naïve Bayes (NB) classifier, and random forest (RF) classifier were considered. Initially, a landslide inventory map was produced with 2000 landslide and non-landslide points by randomly divided with a ratio of 70%:30% for training and testing respectively. The geospatial database for assessing the landslide susceptibility was generated with the help of 16 landslide conditioning factors by allowing for topographical, hydrological, lithological, and land cover factors. The ReliefF method was considered for determining the significance of selected conditioning factors and inclusion in the model building. Consequently, the landslide susceptibility maps (LSMs) were generated using the FDEMATEL-ANP, Naïve Bayes (NB) classifier, and random forest (RF) classifier models. Finally, the area under curve (AUC) and different arithmetic evaluation were used for validating and comparing the results and models. The results revealed that random forest (RF) classifier is a promising and optimum model for landslide susceptibility in the study area with a very high value of area under curve (AUC = 0.954), lower value of mean absolute error (MAE = 0.1238) and root mean square error (RMSE = 0.2555), and higher value of Kappa index (K = 0.8435) and overall accuracy (OAC = 92.2%).

The present paper proposes a spatial model for the purpose of helping Decision Makers (DM) to select a location for Solar Power Plants (SPPs) in the Misrata District, Western Libya. In this regard, the use of the Geographic Information System (GIS), SWARA (Step-wise Weight Assessment Ratio Analysis), and DEMATEL (Decision-Making Trial and Evaluation Laboratory) multi-criteria methods is suggested. The goal of this paper is to develop a new multi-criteria spatial model to identify the best locations for Solar Power Plants (SPP). Such model considers six constraints and eight assessment criteria that are gathered into financial, social, and specialized measures. The hybrid SWARA-DEMATEL (SWA'TEL) model is utilized to assess the weight coefficients of the suggested criteria. The final suitability map is presented utilizing raster cells (alternatives) that are given values ranging from 1 (the least suitable) to 5 (the most appropriate). As the outcomes indicate, an area of 1 667 km 2 in Misrata is entirely fit for the SPPs establishment. A sensitivity analysis performed by changing the criteria weights shows that the model is useful in selecting appropriate locations for developing SPPs projects. The model could also be used effectively to help locate appropriate sites for solar farms being installed in other areas with similar geographical conditions.

Forest fire risk has increased globally during the previous decades. The Mediterranean region is traditionally the most at risk in Europe, but continental countries like Serbia have experienced significant economic and ecological losses due to forest fires. To prevent damage to forests and infrastructure, alongside other societal losses, it is necessary to create an effective protection system against fire, which minimizes the harmful effects. Forest fire probability mapping, as one of the basic tools in risk management, allows the allocation of resources for fire suppression, within a fire season, from zones with a lower risk to those under higher threat. Logistic regression (LR) has been used as a standard procedure in forest fire probability mapping, but in the last decade, machine learning methods such as fandom forest (RF) have become more frequent. The main goals in this study were to (i) determine the main explanatory variables for forest fire occurrence for both models, LR and RF, and (ii) map the probability of forest fire occurrence in Eastern Serbia based on LR and RF. The most important variable was drought code, followed by different anthropogenic features depending on the type of the model. The RF models demonstrated better overall predictive ability than LR models. The map produced may increase firefighting efficiency due to the early detection of forest fire and enable resources to be allocated in the eastern part of Serbia, which covers more than one-third of the country's area.

The article's main objective is to use GIS technology to identify potentially susceptible areas where landslides may occur by overlapping different spatial data. The following spatial data were used in the development of the GIS model of landslide susceptible areas: the slope, the aspect, the geological structure of the terrain, the topographical wetness index and the mean annual precipitation, as natural factors affecting the occurrence of landslides, such as land use, and the distance from roads, which are anthropogenic factors that affect landslides in certain areas. Two machine learning methods have been used to analyze the area's susceptibility to landslide appearance: support vector machine method and static neural RBF network method. The analysis of the results obtained confirmed that both machine learning methods yield very precise results.

In this paper selection locations for fire monitoring cameras were performed with the aim of their detection and reduction of the environmental damage they cause. The proposed model is based on the combined application of Geographic Information Systems (GIS) and Multi-criteria Decision Making (MCDM) using fuzzy logic and the Analytical Hierarchical Process (AHP) phase of a study in the forest area North Kučajska. The process was developed with the help of 8 criteria. In the first phase using GIS-Fuzzy AHP, a map of the FHI fire hazard index was made, while in the second, a selection of available antenna pillars for camera setup was made. The proposed method and the results of this paper can be used for the system of prediction of fire hazards at all levels of state administration.. Keywords: GIS, hazard, forest fire, multicriteria analysis.

Many problems in the analysis of natural terrain surface shapes and the construction of terrain maps to model them remain unsolved. Almost the whole process of thematic interpretation of aerospace information consists of a step-by-step grouping and further data conversion for the purpose of creating a completely definite, problematically oriented picture of the earth’s surface. In this article, we present application of a new method of drawing 3D visibility networks for pattern recognition and its application on terrain surfaces. For the determination of complexity of 3D surface terrain, we use fractal geometry method. We use algorithm for constructing the visibility network to analyse the topological property of networks used in complex terrain surfaces. Terrain models give a fast overview of a landscape and are often fascinating and overwhelmingly beautiful works by artists who invest all their interest and an immense amount of work and know-how, combined with a developed sense of the portrayed landscape, in creating them. At the end, we present modelling of terrain surfaces with topological properties of the visibility network in 3D space.