Abstract 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 current literature does not elaborate on specifications SVM method with respect sampling, attribute selection optimal parameters choices. Therefore main objective this study present investigate technique urban change. The model building procedure presented together...

The representation of land use change (LUC) is often achieved by using data-driven methods that include machine learning (ML) techniques. main objectives 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 compare these techniques find the appropriate data representation. applied on case municipalities City Belgrade, Republic Serbia, historical geospatial sets considering nine...

Landslide Susceptibility Assessment is becoming a very productive research area, wherein different modeling approaches are practiced to delineate zones of the high-low likelihood landslide occurrence. However, there no strong consensus on which approach most adequate. The reason behind lack general view performance could be partially explained by particularity each study. To evaluate efficiency they need applied under same conditions for study area. Herein, we examined three approaches,...

Land use changes play an important role in interactions between human and physical systems, have significant impacts on the environment at local, regional global scales. change is a complex process so developing dynamic models to represent challenging task. Decision Trees (DT) Machine Learning (ML) method with capability extract trends generate representative model using historical geospatial data. While DT used remote sensing as image classification method, it not sufficiently examined land...

Flow-type landslides are not typical in this region of the Balkans. However, after Tamara cyclone event 2014, numerous such occurrences have been observed Serbia. This paper presents initial results a detailed investigation into debris flows Serbia, comparing findings from two programs: RAMMS DBF and Geoflow SPH. Located Western Selanac flow is complex characterized by significant depths block entrainment zone. Previous field investigations utilized ERT surveys, supplemented laboratory...

This paper presents possibilities of applying the geographically weighted regression method in mapping population change index. During last decade, this contemporary spatial modeling has been increasingly used geographical analyses. On example researched region Timočka Krajina (defined for needs elaborating Regional Spatial Plan), disaggregation traditional models density, which are created using choropleth maps at level statistical units, shown. The applied is based on use ancillary...

Monitoring is important for assessing the stability of ground and confirming validity design during construction operation structures.The ideal monitoring system projects in Rock Geotechnical Engineering would be able to monitor behavior small extensive areas continuously automatically with high accuracy.In addition, costs low easy handle.Satellite technology has potential realize above by combining it conventional geotechnical instruments.In this paper, satellite displacement monitoring,...

<jats:p>The Umka landslide is one of the biggest inhabited active landslides in Serbia. The landslideactivity has been monitored for a period longer than 85 years, by various geotechnical and geodetictechniques. Since 2010, activity continuously automated permanentGlobal Navigation Satellite System (GNSS) based monitoring system real time. Furthermore,since 2018 GNSS kinematic positioning set ofcharacteristic points as well UAV (Unmanned Aerial Vehicle) photogrammetry....

Abstract Leva reka debris flow (Kraljevo area, Serbia) was triggered by extreme rainfall in May 2014 Serbia. A Huge amount of weathered Cretaceous flysch material formed dam, over 10m high, and made a lake on (about 150m long, 5m deep). Debris appears an active ravine with the occasional stream flow. The is about 400m 100 wide at widest part, 30 m deep deepest main part. Digital Elevation Model orthophoto images were obtained UAV survey very high resolution as detailed topographic input...

This paper is dedicated to modeling extreme TEC values at the territory of Serbia. For values, we consider maximum from peak 11-year cycle solar activity in years 2013, 2014 and 2015 for days winter summer solstice autumnal vernal equinox. The average (Total Electron Content) between 10 12 UT (Universal Time) were treated. As basic data all processing, used GNSS (Global Navigation Satellite System) observation obtained by three permanent stations located Those data, accept as...

We demonstrate the use of Facebook's Prophet (usually just called Prophet) model for short-term air quality forecasting at Belgrade-Zeleno brdo monitoring station. To address missing data, we applied minimally-altering data distribution imputation techniques. Linear interpolation proved effective gaps (1–3 hours), hourly mean method mid-term (24–26 and Hermite polynomial long-term (132–148 hours). The most significant change was a 3.4% shift in skewness. Partitioning time series enabled...

<p>Project "Devils’ town Erosion MONITORing - DEMONITOR" involves the monitoring of accessible earth pillars in area Devil’s town, by using a combination several non‐invasive methods. Terrestrial laser scanning (TLS) and photogrammetric imaging with unmanned aircraft (UAV) as platform showed great solutions for 3D modeling this site erosion monitoring. In work it is shown that manual free flight mode UAV gave much better results...