Mileva Samardzic-Petrovic

Faculty of Civile Engineering, University of Belgrade · Department of geodesy and geoinformatics

Flow-type landslides are not typical in this region of the Balkans. However, after the Tamara cyclone event in 2014, numerous such occurrences have been observed in Serbia. This paper presents the initial results of a detailed investigation into debris flows in Serbia, comparing findings from two programs: RAMMS DBF and Geoflow SPH. Located in West...

Project "Devils’ town Erosion MONITORing - DEMONITOR" involves the monitoring of accessible earth pillars in the area of Devil’s town, by using a combination of several non‐invasive methods. Terrestrial laser scanning (TLS) and photogrammetric imaging with unmanned aircraft (UAV) as a platform showed as great solutions for 3D modeling of this site...

The Random Forest (RF) and K nearest neighbors (KNN) machine learning (ML) algorithms were evaluated for their ability to predict ophiolite occurrences, in the East Vardar Zone (EVZ) of central North Macedonia. A predictive map of the investigated area was created using three data sources: geophysical data (digital elevation model, gravity and geom...

Results of recent monitoring activities conducted from 2014 to 2019 are presented in the paper as a part of IPL 181 Project progress report. Recent monitoring activities are concentrated on several landslide monitoring techniques—automated GNSS monitoring system measurements, geodetic benchmark survey monitoring, UAV imaging, processing and analysi...

The main results of recent activities on IPL210 Project summarize rainfall event, rainfall-induced landslides and their characteristics including type of movement, type of material involved and state of activity in two different regions in Serbia both affected by same extreme rainfall event in May 2014. In both regions dominant type of movement was...

The Umka landslide is one of the biggest inhabited active landslides in Serbia. The Umka landslideactivity has been monitored for a period longer than 85 years, by various geotechnical and geodetictechniques. Since 2010, landslide activity has been continuously monitored by automated permanentGlobal Navigation Satellite System (GNSS) based monitori...

The main idea of this chapter is to address some of the key issues that were recognized in Machine Learning (ML) based Landslide Assessment Modeling (LAM). Through the experience of the authors, elaborated in several case studies, including the City of Belgrade in Serbia, the City of Tuzla in Bosnia and Herzegovina, Ljubovija Municipality in Serbia...

Leva reka debris flow (Kraljevo area, Serbia) was triggered by extreme rainfall in May 2014 in Serbia. A Huge amount of weathered Cretaceous flysch material formed debris dam, over 10m high, and made a lake on Leva reka (about 150m long, and 5m deep). Debris flow appears in an active ravine with the occasional stream flow. The debris flow is about...

One of the main tasks of data-driven modelling methods is to induce representative model of underlying spatial - temporal processes based on former-historical data and data mining approach. As relatively new methods, capable of solving complex nonlinear problems, like the land use changes/cover (LULC) and urban growth, their applications are attrac...

The latest applications of hedonic dwelling price models have included recent advances in spatial analysis that control for spatial dependence and heterogeneity. The study of spatial aspects of hedonic modelling pertains to spatial econometrics, which is relevant to this study because it clearly accounts for the influence and peculiarities related...

The representation of land use change (LUC) is often achieved 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, to compare these three ML techniques and...

Landslide Susceptibility Assessment is becoming a very productive research area, wherein different modeling approaches are practiced to delineate zones of the high-low likelihood of landslide occurrence. However, there is no strong consensus on which approach is the most adequate. The reason behind the lack of the general view on the performance of...

This paper is dedicated to modeling extreme TEC (Total Electron Content) values at the territory of Serbia. For the extreme TEC values, we consider the maximum values from the peak of the 11-year cycle of solar activity in the years 2013, 2014 and 2015 for the days of the winter and summer solstice and autumnal and vernal equinox. The average TEC v...

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...

Land use changes play an important role in interactions between human and physical systems, and have significant impacts on the environment at local, regional and global scales. Land use change is a complex process and so developing dynamic models to represent the process is a challenging task. Decision Trees (DT) is a Machine Learning (ML) method...

Infestations caused by the mountain pine beetle (MPB) can be seen as complex spatio-temporal process with severe ecological impacts on the forest environment. In order to manage and prevent the insect infestation and reduce significant forest loss it is necessary to improve knowledge about the infestation process. The main objective of this researc...

Solving the problem of publicly available census data disaggregation has preoccupied numerous researchers intensively. A noteworthy advance in the methodology was made thanks to the contemporary storage and presentation of spatial and socio-economic data in the GIS environment. It is also important that a large number of auxiliary databases (satell...

Solving the problem of publicly available census data disaggregation has preoccupied numerous researchers intensively. A noteworthy advance in the methodology was made thanks to the contemporary storage and presentation of spatial and socio-economic data in the GIS environment. It is also important that a large number of auxiliary databases (satell...

This paper examines a feasible solution for the preliminary assessment of potential damage costs for dwellings in areas prone to the risk of landslides and subsidence. The assessment uses different spatial layers as input parameters and concentrates on the implementation of different spatial databases that are already available as public data. Thes...

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 Timočka Krajina (defined for the needs of elaborating the Re...