TY  - JOUR
AU  - Gojković, Zoran
AU  - Kilibarda, Milan
AU  - Brajović, Ljiljana
AU  - Marjanović, Miloš
AU  - Milutinović, Aleksandar
AU  - Ganić, Aleksandar
PY  - 2023
UR  - https://grafar.grf.bg.ac.rs/handle/123456789/3458
AB  - Open pit coal mining affects surrounding populated areas, resulting in terrain surface deformation. Surface deformation should be monitored as often as possible to control deformations and prevent potential incidents. This paper analyzes time series deformation estimated from the Sentinel-1 satellite images using the Persistent Scatterer Interferometry method to monitor subsidence rates caused by open pit mining activities. It is possible to measure deformations using classical geodetic methods, but those are rarely used in practice because they are time-consuming and expensive for application in large areas. Using the open access radar images from the Sentinel-1 mission, 513 images from the repository were downloaded between October 2016 and the end of December 2020. We present the processing steps in detail in order to establish a workflow for the automated processing of vertical displacement estimation using open source tools; a total of 402 images were processed: 215 images belonged to the ascending satellite orbit, 187 images belonged to the descending orbit, and 111 images were rejected because of adverse weather conditions. The PS InSAR technique has never been used for the mines of the Republic of Serbia or for land surveying practices related to deformation monitoring. The results based on the Sentinel-1 images were compared with results from geodetic leveling and with neotectonic uplift trends. The trend lines of vertical displacement obtained from PS and corresponding leveling are significantly similar (a Pearson correlation of 85% with a p-value of 0.015). The final evaluation reported results of vertical displacements at the leveling benchmark of −3.4 mm/year with the PS InSAR method and −2.7 mm/year with the leveling method. A comparison of the PS vertical displacements with a settlement model fits reasonably, suggesting that the measurements are valid. As four years of PS time series data is insufficient to establish undisputable conclusions on the neotectonics uplift, extending the time series (covering at least a decade) implies that this approach will become attractive in future neotectonic uplift trend estimations. This study illustrates not only the ability of Sentinel-1 data in mapping vertical deformations, but the obtained results could also be used for geohazard monitoring and land monitoring in general for the area of interest.
PB  - MDPI
T2  - Remote Sensing
T1  - Ground Surface Subsidence Monitoring Using Sentinel-1 in the “Kostolac” Open Pit Coal Mine
IS  - 10
SP  - 2519
VL  - 15
DO  - 10.3390/rs15102519
ER  - 

@article{
author = "Gojković, Zoran and Kilibarda, Milan and Brajović, Ljiljana and Marjanović, Miloš and Milutinović, Aleksandar and Ganić, Aleksandar",
year = "2023",
abstract = "Open pit coal mining affects surrounding populated areas, resulting in terrain surface deformation. Surface deformation should be monitored as often as possible to control deformations and prevent potential incidents. This paper analyzes time series deformation estimated from the Sentinel-1 satellite images using the Persistent Scatterer Interferometry method to monitor subsidence rates caused by open pit mining activities. It is possible to measure deformations using classical geodetic methods, but those are rarely used in practice because they are time-consuming and expensive for application in large areas. Using the open access radar images from the Sentinel-1 mission, 513 images from the repository were downloaded between October 2016 and the end of December 2020. We present the processing steps in detail in order to establish a workflow for the automated processing of vertical displacement estimation using open source tools; a total of 402 images were processed: 215 images belonged to the ascending satellite orbit, 187 images belonged to the descending orbit, and 111 images were rejected because of adverse weather conditions. The PS InSAR technique has never been used for the mines of the Republic of Serbia or for land surveying practices related to deformation monitoring. The results based on the Sentinel-1 images were compared with results from geodetic leveling and with neotectonic uplift trends. The trend lines of vertical displacement obtained from PS and corresponding leveling are significantly similar (a Pearson correlation of 85% with a p-value of 0.015). The final evaluation reported results of vertical displacements at the leveling benchmark of −3.4 mm/year with the PS InSAR method and −2.7 mm/year with the leveling method. A comparison of the PS vertical displacements with a settlement model fits reasonably, suggesting that the measurements are valid. As four years of PS time series data is insufficient to establish undisputable conclusions on the neotectonics uplift, extending the time series (covering at least a decade) implies that this approach will become attractive in future neotectonic uplift trend estimations. This study illustrates not only the ability of Sentinel-1 data in mapping vertical deformations, but the obtained results could also be used for geohazard monitoring and land monitoring in general for the area of interest.",
publisher = "MDPI",
journal = "Remote Sensing",
title = "Ground Surface Subsidence Monitoring Using Sentinel-1 in the “Kostolac” Open Pit Coal Mine",
number = "10",
pages = "2519",
volume = "15",
doi = "10.3390/rs15102519"
}

Gojković, Z., Kilibarda, M., Brajović, L., Marjanović, M., Milutinović, A.,& Ganić, A.. (2023). Ground Surface Subsidence Monitoring Using Sentinel-1 in the “Kostolac” Open Pit Coal Mine. in Remote Sensing
MDPI., 15(10), 2519.
https://doi.org/10.3390/rs15102519

Gojković Z, Kilibarda M, Brajović L, Marjanović M, Milutinović A, Ganić A. Ground Surface Subsidence Monitoring Using Sentinel-1 in the “Kostolac” Open Pit Coal Mine. in Remote Sensing. 2023;15(10):2519.
doi:10.3390/rs15102519 .

Gojković, Zoran, Kilibarda, Milan, Brajović, Ljiljana, Marjanović, Miloš, Milutinović, Aleksandar, Ganić, Aleksandar, "Ground Surface Subsidence Monitoring Using Sentinel-1 in the “Kostolac” Open Pit Coal Mine" in Remote Sensing, 15, no. 10 (2023):2519,
https://doi.org/10.3390/rs15102519 . .

TY  - CHAP
AU  - Abolmasov, Biljana
AU  - Marjanović, Miloš
AU  - Đurić, Uroš
AU  - Krušić, Jelka
PY  - 2023
UR  - https://grafar.grf.bg.ac.rs/handle/123456789/3376
AB  - The University of Belgrade, Faculty of Mining and Geology has been involved in landslide risk reduction activities at the national, regional, and site-specific levels in Serbia for decades. Since 2011 the Faculty has had several activities closely connected with the International Consortium on Landslides, including the International Programme on Landslides Projects 181, 210 and 248, as well as World Centre of Excellency (WCoE) from 2017. In the past decade the Faculty of Mining and Geology was involved in several national, regional and local projects funded by the People of Japan, UNDP and The World Bank on landslide risk reduction in Serbia, Bosnia and Herzegovina and North Macedonia. They all closely involved many stakeholders from national to local authorities including Ministries, Local Self Governments, Public Enterprises, Emergency Offices and Civil Protec-tion units. In this report, the activities of WCoE for national and local authorities on landslide risk reduction will be presented.
PB  - Springer, Cham
T2  - Progress in Landslide Research and Technology
T1  - An Integrated Approach to Landslides Risk Management for Local and National Authorities
EP  - 360
IS  - 2
SP  - 355
VL  - 2
DO  - 10.1007/978-3-031-44296-4_20
ER  - 

@inbook{
author = "Abolmasov, Biljana and Marjanović, Miloš and Đurić, Uroš and Krušić, Jelka",
year = "2023",
abstract = "The University of Belgrade, Faculty of Mining and Geology has been involved in landslide risk reduction activities at the national, regional, and site-specific levels in Serbia for decades. Since 2011 the Faculty has had several activities closely connected with the International Consortium on Landslides, including the International Programme on Landslides Projects 181, 210 and 248, as well as World Centre of Excellency (WCoE) from 2017. In the past decade the Faculty of Mining and Geology was involved in several national, regional and local projects funded by the People of Japan, UNDP and The World Bank on landslide risk reduction in Serbia, Bosnia and Herzegovina and North Macedonia. They all closely involved many stakeholders from national to local authorities including Ministries, Local Self Governments, Public Enterprises, Emergency Offices and Civil Protec-tion units. In this report, the activities of WCoE for national and local authorities on landslide risk reduction will be presented.",
publisher = "Springer, Cham",
journal = "Progress in Landslide Research and Technology",
booktitle = "An Integrated Approach to Landslides Risk Management for Local and National Authorities",
pages = "360-355",
number = "2",
volume = "2",
doi = "10.1007/978-3-031-44296-4_20"
}

Abolmasov, B., Marjanović, M., Đurić, U.,& Krušić, J.. (2023). An Integrated Approach to Landslides Risk Management for Local and National Authorities. in Progress in Landslide Research and Technology
Springer, Cham., 2(2), 355-360.
https://doi.org/10.1007/978-3-031-44296-4_20

Abolmasov B, Marjanović M, Đurić U, Krušić J. An Integrated Approach to Landslides Risk Management for Local and National Authorities. in Progress in Landslide Research and Technology. 2023;2(2):355-360.
doi:10.1007/978-3-031-44296-4_20 .

Abolmasov, Biljana, Marjanović, Miloš, Đurić, Uroš, Krušić, Jelka, "An Integrated Approach to Landslides Risk Management for Local and National Authorities" in Progress in Landslide Research and Technology, 2, no. 2 (2023):355-360,
https://doi.org/10.1007/978-3-031-44296-4_20 . .

TY  - CONF
AU  - Vukićević, Mirjana
AU  - Mašović, Snežana
AU  - Hajdin, Rade
AU  - Jocković, Sanja
AU  - Marjanović, Miloš
AU  - Pujević, Veljko
AU  - Obradović, Nikola
PY  - 2023
UR  - https://grafar.grf.bg.ac.rs/handle/123456789/3348
AB  - One of the key problems that occurs in the management of the maintenance of state transport infrastructure facilities is the lack of systematized and updated information on the condition of the elements of infrastructure facilities such as the condition of embankments, bridges, tunnels, retaining structures etc. Systematized information enables rational, efficient maintenance, timely reactions that will reduce the risk of building failures and increase traffic safety. In addition, such an approach contributes to the optimization of the allocation of budget funds for that purpose and the rational use of available technical resources. Management of the maintenance process of retaining structures requires the formation of a unique (central) database that will record all retaining structures that meet the prescribed criteria for recording and systematically monitor their condition over time. This paper presents the methodology for the formation and development of a database of retaining structures, using examples of good practice.
PB  - Српско друштво за путеве “Via Vita”
C3  - PROCEEDINGS The 7th Scientific-Expert Meeting “Road and Environment”, Vrnjacka Banja, Serbia, May 24-26, 2023.
T1  - Methodology for the formation and development of the database of retaining structures
SP  - 242
UR  - https://hdl.handle.net/21.15107/rcub_grafar_3348
ER  - 

@conference{
author = "Vukićević, Mirjana and Mašović, Snežana and Hajdin, Rade and Jocković, Sanja and Marjanović, Miloš and Pujević, Veljko and Obradović, Nikola",
year = "2023",
abstract = "One of the key problems that occurs in the management of the maintenance of state transport infrastructure facilities is the lack of systematized and updated information on the condition of the elements of infrastructure facilities such as the condition of embankments, bridges, tunnels, retaining structures etc. Systematized information enables rational, efficient maintenance, timely reactions that will reduce the risk of building failures and increase traffic safety. In addition, such an approach contributes to the optimization of the allocation of budget funds for that purpose and the rational use of available technical resources. Management of the maintenance process of retaining structures requires the formation of a unique (central) database that will record all retaining structures that meet the prescribed criteria for recording and systematically monitor their condition over time. This paper presents the methodology for the formation and development of a database of retaining structures, using examples of good practice.",
publisher = "Српско друштво за путеве “Via Vita”",
journal = "PROCEEDINGS The 7th Scientific-Expert Meeting “Road and Environment”, Vrnjacka Banja, Serbia, May 24-26, 2023.",
title = "Methodology for the formation and development of the database of retaining structures",
pages = "242",
url = "https://hdl.handle.net/21.15107/rcub_grafar_3348"
}

Vukićević, M., Mašović, S., Hajdin, R., Jocković, S., Marjanović, M., Pujević, V.,& Obradović, N.. (2023). Methodology for the formation and development of the database of retaining structures. in PROCEEDINGS The 7th Scientific-Expert Meeting “Road and Environment”, Vrnjacka Banja, Serbia, May 24-26, 2023.
Српско друштво за путеве “Via Vita”., 242.
https://hdl.handle.net/21.15107/rcub_grafar_3348

Vukićević M, Mašović S, Hajdin R, Jocković S, Marjanović M, Pujević V, Obradović N. Methodology for the formation and development of the database of retaining structures. in PROCEEDINGS The 7th Scientific-Expert Meeting “Road and Environment”, Vrnjacka Banja, Serbia, May 24-26, 2023.. 2023;:242.
https://hdl.handle.net/21.15107/rcub_grafar_3348 .

Vukićević, Mirjana, Mašović, Snežana, Hajdin, Rade, Jocković, Sanja, Marjanović, Miloš, Pujević, Veljko, Obradović, Nikola, "Methodology for the formation and development of the database of retaining structures" in PROCEEDINGS The 7th Scientific-Expert Meeting “Road and Environment”, Vrnjacka Banja, Serbia, May 24-26, 2023. (2023):242,
https://hdl.handle.net/21.15107/rcub_grafar_3348 .

TY  - CONF
AU  - Berisavljević, Zoran
AU  - Marjanović, Miloš
AU  - Đurić, Uroš
PY  - 2023
UR  - https://grafar.grf.bg.ac.rs/handle/123456789/3237
AB  - U radu su prikazani rezultati geotehničkih istraživanja za potrebe izgradnje visećeg pešačkog mosta preko klisure reke Đetinje u Užicu. Predviđeno je da most, sistema prednapregnute trake, omogući prelaz pešacima sa desne dolinske strane na stranu Starog grada, koja je opasana strmom liticom (cca. 40 m visine). Za potrebe formiranja geotehničkog modela i strukturnog sklopa krečnjačke stenske mase korišćen je postupak fotogrametrijskog snimanja dronom. Predviđeno je da se zatežuća sila (od oko 30 MN), koju most prenosi na obalni stub, prihvati i prenese na stensku masu sistemom prednapregnutih ankera. U tom pogledu izvršena su ispitivanja nosivosti dva sidra, koja su ugrađena u subhorizontalne bušotine. Rezultati numeričkih analiza i uspešan test nosivosti sidara pokazuju da je stenska masa u stanju da izdrži sile zatezanja od mostovske konstrukcije. Pomeranja obalnog stuba su nekoliko mm u slučaju pretpostavke o kontinualnoj stenskoj masi. Kada se eksplicitno u analizu uvedu pukotine pomeranja su oko 6 cm. Ovi rezultati se morju verifikovati kroz odgovarajući monitoring tokom izgradnje mosta.
AB  - This study shows the results of geotechnical investigations performed for the construction of pedestrian suspension bridge, crossing the Đetinja river in the town of Užice. The prestressed ribbon type bridge should connect the right bank of the river with the the vertical cliff (approx. 40 m high) where the Old town is located. Geotechnical model of the limestone rock mass and joint network model are formed by utilization of drone photogrammetry. The tensile force (approx. 30 MN) induced on the bridge pillar should be accepted and transfered to the rock mass by the system of prestressed anchors. Two investigation test were performed on anchors installed in sub-horizontal boreholes. Successful anchor load test and numerical analysis showed that the rock mass is capable of sustaining tensile force induced by the bridge structure. Displacements of the bridge abutment are approx. several mm for an assumption of isotropic rock mass behaviour. If joints are applied explicitly the displacements are in the order of 6 cm. These findings have to be confirmed by monitoring during the construction stage.
PB  - Savez građevinskih inženjera Srbije
C3  - Zbornik radova Međunarodno naučno-stručnog savetovanja Geotehnički aspekti građevinarstva i zemljotresno inženjerstvo
T1  - Geotehnički aspekti izgradnje visećeg pešačkog mosta u starom gradu u Užicu
T1  - Geotechnical aspects of construction of stressed ribbon bridge in Užice old town
EP  - 125
SP  - 115
UR  - https://hdl.handle.net/21.15107/rcub_grafar_3237
ER  - 

@conference{
author = "Berisavljević, Zoran and Marjanović, Miloš and Đurić, Uroš",
year = "2023",
abstract = "U radu su prikazani rezultati geotehničkih istraživanja za potrebe izgradnje visećeg pešačkog mosta preko klisure reke Đetinje u Užicu. Predviđeno je da most, sistema prednapregnute trake, omogući prelaz pešacima sa desne dolinske strane na stranu Starog grada, koja je opasana strmom liticom (cca. 40 m visine). Za potrebe formiranja geotehničkog modela i strukturnog sklopa krečnjačke stenske mase korišćen je postupak fotogrametrijskog snimanja dronom. Predviđeno je da se zatežuća sila (od oko 30 MN), koju most prenosi na obalni stub, prihvati i prenese na stensku masu sistemom prednapregnutih ankera. U tom pogledu izvršena su ispitivanja nosivosti dva sidra, koja su ugrađena u subhorizontalne bušotine. Rezultati numeričkih analiza i uspešan test nosivosti sidara pokazuju da je stenska masa u stanju da izdrži sile zatezanja od mostovske konstrukcije. Pomeranja obalnog stuba su nekoliko mm u slučaju pretpostavke o kontinualnoj stenskoj masi. Kada se eksplicitno u analizu uvedu pukotine pomeranja su oko 6 cm. Ovi rezultati se morju verifikovati kroz odgovarajući monitoring tokom izgradnje mosta., This study shows the results of geotechnical investigations performed for the construction of pedestrian suspension bridge, crossing the Đetinja river in the town of Užice. The prestressed ribbon type bridge should connect the right bank of the river with the the vertical cliff (approx. 40 m high) where the Old town is located. Geotechnical model of the limestone rock mass and joint network model are formed by utilization of drone photogrammetry. The tensile force (approx. 30 MN) induced on the bridge pillar should be accepted and transfered to the rock mass by the system of prestressed anchors. Two investigation test were performed on anchors installed in sub-horizontal boreholes. Successful anchor load test and numerical analysis showed that the rock mass is capable of sustaining tensile force induced by the bridge structure. Displacements of the bridge abutment are approx. several mm for an assumption of isotropic rock mass behaviour. If joints are applied explicitly the displacements are in the order of 6 cm. These findings have to be confirmed by monitoring during the construction stage.",
publisher = "Savez građevinskih inženjera Srbije",
journal = "Zbornik radova Međunarodno naučno-stručnog savetovanja Geotehnički aspekti građevinarstva i zemljotresno inženjerstvo",
title = "Geotehnički aspekti izgradnje visećeg pešačkog mosta u starom gradu u Užicu, Geotechnical aspects of construction of stressed ribbon bridge in Užice old town",
pages = "125-115",
url = "https://hdl.handle.net/21.15107/rcub_grafar_3237"
}

Berisavljević, Z., Marjanović, M.,& Đurić, U.. (2023). Geotehnički aspekti izgradnje visećeg pešačkog mosta u starom gradu u Užicu. in Zbornik radova Međunarodno naučno-stručnog savetovanja Geotehnički aspekti građevinarstva i zemljotresno inženjerstvo
Savez građevinskih inženjera Srbije., 115-125.
https://hdl.handle.net/21.15107/rcub_grafar_3237

Berisavljević Z, Marjanović M, Đurić U. Geotehnički aspekti izgradnje visećeg pešačkog mosta u starom gradu u Užicu. in Zbornik radova Međunarodno naučno-stručnog savetovanja Geotehnički aspekti građevinarstva i zemljotresno inženjerstvo. 2023;:115-125.
https://hdl.handle.net/21.15107/rcub_grafar_3237 .

Berisavljević, Zoran, Marjanović, Miloš, Đurić, Uroš, "Geotehnički aspekti izgradnje visećeg pešačkog mosta u starom gradu u Užicu" in Zbornik radova Međunarodno naučno-stručnog savetovanja Geotehnički aspekti građevinarstva i zemljotresno inženjerstvo (2023):115-125,
https://hdl.handle.net/21.15107/rcub_grafar_3237 .

TY  - CHAP
AU  - Abolmasov, Biljana
AU  - Stanković, Ranka
AU  - Marjanović, Miloš
AU  - Vulović, Nikola
AU  - Đurić, Uroš
PY  - 2023
UR  - https://grafar.grf.bg.ac.rs/handle/123456789/3377
AB  - In the framework of the project “Mainstreaming Climate Resilience in the Road Transportation Management in Serbia (CliRtheRoads)”, a complex mapping tool was developed to support the Government of Serbia and Public Enterprise Roads of Serbia in climate change adaptation planning and management. The software solution comprises of: a web portal for data entry and management for authorised users; a publicly available web-GIS application; a mobile GIS application; and a back-end database. This paper briefly overviews the system, focusing on the landslide data model. Therein, the main system and software solution breakthrough is automatizing the estimation of investment costs of engineering and non-engineering measures recommended at affected locations along the road network. A retrospective on its applicability and user feedback is also included. The objective was to facilitate seamless road management by providing necessary data in a simple, understandable fashion, indicating which locations on the road network have higher priority. The introduced level of automation allows easier decision-making and investment planning.
PB  - Springer, Cham
T2  - Progress in Landslide Research and Technology
T1  - CliRtheRoads: An Integrated Approach to Landslide Risk Management on Roads in Serbia
EP  - 409
IS  - 2
SP  - 403
VL  - 2
DO  - 10.1007/978-3-031-44296-4_23
ER  - 

@inbook{
author = "Abolmasov, Biljana and Stanković, Ranka and Marjanović, Miloš and Vulović, Nikola and Đurić, Uroš",
year = "2023",
abstract = "In the framework of the project “Mainstreaming Climate Resilience in the Road Transportation Management in Serbia (CliRtheRoads)”, a complex mapping tool was developed to support the Government of Serbia and Public Enterprise Roads of Serbia in climate change adaptation planning and management. The software solution comprises of: a web portal for data entry and management for authorised users; a publicly available web-GIS application; a mobile GIS application; and a back-end database. This paper briefly overviews the system, focusing on the landslide data model. Therein, the main system and software solution breakthrough is automatizing the estimation of investment costs of engineering and non-engineering measures recommended at affected locations along the road network. A retrospective on its applicability and user feedback is also included. The objective was to facilitate seamless road management by providing necessary data in a simple, understandable fashion, indicating which locations on the road network have higher priority. The introduced level of automation allows easier decision-making and investment planning.",
publisher = "Springer, Cham",
journal = "Progress in Landslide Research and Technology",
booktitle = "CliRtheRoads: An Integrated Approach to Landslide Risk Management on Roads in Serbia",
pages = "409-403",
number = "2",
volume = "2",
doi = "10.1007/978-3-031-44296-4_23"
}

Abolmasov, B., Stanković, R., Marjanović, M., Vulović, N.,& Đurić, U.. (2023). CliRtheRoads: An Integrated Approach to Landslide Risk Management on Roads in Serbia. in Progress in Landslide Research and Technology
Springer, Cham., 2(2), 403-409.
https://doi.org/10.1007/978-3-031-44296-4_23

Abolmasov B, Stanković R, Marjanović M, Vulović N, Đurić U. CliRtheRoads: An Integrated Approach to Landslide Risk Management on Roads in Serbia. in Progress in Landslide Research and Technology. 2023;2(2):403-409.
doi:10.1007/978-3-031-44296-4_23 .

Abolmasov, Biljana, Stanković, Ranka, Marjanović, Miloš, Vulović, Nikola, Đurić, Uroš, "CliRtheRoads: An Integrated Approach to Landslide Risk Management on Roads in Serbia" in Progress in Landslide Research and Technology, 2, no. 2 (2023):403-409,
https://doi.org/10.1007/978-3-031-44296-4_23 . .

TY  - CONF
AU  - Marjanović, Miloš
AU  - Sandić, Cvjetko
AU  - Đurić, Uroš
AU  - Abolmasov, Biljana
PY  - 2023
UR  - https://grafar.grf.bg.ac.rs/handle/123456789/3357
AB  - Although without official standardization, landslide susceptibility models (LSM) have entered preliminary stages of design and planning practice worldwide. As design and planning itself undergoes from lower to higher level of detail, different scales of LSM apply. Nevertheless, the LSMs are mainly produced in regional scales, whereas national and local are rarely available. Limitations of downscaling and upscaling LSMs are considered herein, by comparing LSMs coming from continental scale on one hand, and regional scale on the other, while the validation was performed using national scale model (Figure 1) at 30 m pixel resolution. Pan- European model (Wilde et al. 2018) is downscaled from 200 to 30 m pixel resolution using re-gridding method based on various interpolation techniques (linear, spline, Kriging) over the area of the City of Doboj in Republic of Srpska (Bosnia and Herzegovina). The LSM for the City of Doboj (Sandić et al. 2023) was upscaled from 5 to 30 m resolution using various resampling techniques (nearest neighbor, bilinear interpolation and cubic convolution). All maps were made using heuristic or combined heuristic approaches with standard landslide conditioning factors as raster inputs (geological, geomorphological, environmental, etc.). The best performing downscaling option was spline interpolation, while cubic convolution gave the best match against the referent LSM for the upscaling. Other downscaling variants tend to pixelate the map at 30 m resolution, whereas upscaling was not that considerably affected by technique choice. For large scale urban planning and preliminary design it is important to avoid pixilation as much as possible and smoothen the susceptibility classes so they can be compared against various elements, such as road and railway network features (higher-order curves, bridges, tunnels) and urban fabric footprints (housing, industrial, infrastructure). Results indicate that downscaling can be misleading and should be avoided if there is time and resource to perform appropriate local or regional scale LSM.
PB  - OIC S.r.l., Viale della Giovine Italia, 17, 50122 Firenze, Italy
C3  - 6th World Landslide Forum, Florence, Italy, 14-17 November 2023, Abstract book
T1  - Upscaling and downscaling landslide susceptibility maps
UR  - https://hdl.handle.net/21.15107/rcub_grafar_3357
ER  - 

@conference{
author = "Marjanović, Miloš and Sandić, Cvjetko and Đurić, Uroš and Abolmasov, Biljana",
year = "2023",
abstract = "Although without official standardization, landslide susceptibility models (LSM) have entered preliminary stages of design and planning practice worldwide. As design and planning itself undergoes from lower to higher level of detail, different scales of LSM apply. Nevertheless, the LSMs are mainly produced in regional scales, whereas national and local are rarely available. Limitations of downscaling and upscaling LSMs are considered herein, by comparing LSMs coming from continental scale on one hand, and regional scale on the other, while the validation was performed using national scale model (Figure 1) at 30 m pixel resolution. Pan- European model (Wilde et al. 2018) is downscaled from 200 to 30 m pixel resolution using re-gridding method based on various interpolation techniques (linear, spline, Kriging) over the area of the City of Doboj in Republic of Srpska (Bosnia and Herzegovina). The LSM for the City of Doboj (Sandić et al. 2023) was upscaled from 5 to 30 m resolution using various resampling techniques (nearest neighbor, bilinear interpolation and cubic convolution). All maps were made using heuristic or combined heuristic approaches with standard landslide conditioning factors as raster inputs (geological, geomorphological, environmental, etc.). The best performing downscaling option was spline interpolation, while cubic convolution gave the best match against the referent LSM for the upscaling. Other downscaling variants tend to pixelate the map at 30 m resolution, whereas upscaling was not that considerably affected by technique choice. For large scale urban planning and preliminary design it is important to avoid pixilation as much as possible and smoothen the susceptibility classes so they can be compared against various elements, such as road and railway network features (higher-order curves, bridges, tunnels) and urban fabric footprints (housing, industrial, infrastructure). Results indicate that downscaling can be misleading and should be avoided if there is time and resource to perform appropriate local or regional scale LSM.",
publisher = "OIC S.r.l., Viale della Giovine Italia, 17, 50122 Firenze, Italy",
journal = "6th World Landslide Forum, Florence, Italy, 14-17 November 2023, Abstract book",
title = "Upscaling and downscaling landslide susceptibility maps",
url = "https://hdl.handle.net/21.15107/rcub_grafar_3357"
}

Marjanović, M., Sandić, C., Đurić, U.,& Abolmasov, B.. (2023). Upscaling and downscaling landslide susceptibility maps. in 6th World Landslide Forum, Florence, Italy, 14-17 November 2023, Abstract book
OIC S.r.l., Viale della Giovine Italia, 17, 50122 Firenze, Italy..
https://hdl.handle.net/21.15107/rcub_grafar_3357

Marjanović M, Sandić C, Đurić U, Abolmasov B. Upscaling and downscaling landslide susceptibility maps. in 6th World Landslide Forum, Florence, Italy, 14-17 November 2023, Abstract book. 2023;.
https://hdl.handle.net/21.15107/rcub_grafar_3357 .

Marjanović, Miloš, Sandić, Cvjetko, Đurić, Uroš, Abolmasov, Biljana, "Upscaling and downscaling landslide susceptibility maps" in 6th World Landslide Forum, Florence, Italy, 14-17 November 2023, Abstract book (2023),
https://hdl.handle.net/21.15107/rcub_grafar_3357 .

TY  - CONF
AU  - Abolmasov, Biljana
AU  - Stanković, Ranka
AU  - Vulović, Nikola
AU  - Marjanović, Miloš
AU  - Đurić, Uroš
PY  - 2023
UR  - https://grafar.grf.bg.ac.rs/handle/123456789/3356
AB  - Within the project Mainstreaming Climate Resilience in the Road Transportation Management in Serbia (CliRtheRoads), a complex software solution was developed to support Public Enterprise Roads of Serbia in climate change adaptation planning and management. The software solution comprises 1) web portal for data entry and management for authorised users 2) publicly available web GIS part 3) mobile GIS application and 4) back-end database (Figure 1). In order to store and process the data collected during field visits and surveys, the data base developed in project first phase (Valjevo test area), was modified to include new datasets and to store new datatypes (as floods), and new modules (as activity cost) for Kraljevo test area. Both test areas have been chosen due theirs diversified characteristics, many climate related hazards, and the fact they suffered greatly from disasters recently (Abolmasov et al. 2017, Abolmasov et al. 2021). The database was upgraded to new model aimed for maintaining legacy data from both test areas, but also for future infrastructure resilience projects based on same approach, to enable
that all data will be stored and mapped in a unified manner. The data model include 1) main concepts (entity types) for the instabilities, with detailed data comprising common and specific attributes, 2) storage of multimedia (mainly photo from field work, but possible video as well), 3) knowledge base with cost of activities, including catalogue per each entity type with job type and description, unit and total price, maintenance type (regular maintenance, rehabilitation, urgent maintenance), including recommending activities (system allow user to add specific activities, description and cost that is further calculated and aggregated with other data); 4) secondary data from other sources (other projects, legacy data and external resources), or from interpreted data. The data was stored in the PostgreSQL Database, a web application was developed (using PHP) to facilitate data input, maintain knowledge database and calculate cost of recommended activities. There is a total of 461 records with fully described instabilities (slides, falls, topples, flows), documented by large number of photographs from the field. Additionally, every record is supplemented by engineering solution to support field engineers or decision makers for better road management in climate changing conditions.
PB  - OIC S.r.l., Viale della Giovine Italia, 17, 50122 Firenze, Italy
C3  - 6th World Landslide Forum, Florence, Italy, 14-17 November 2023, Abstract book
T1  - A landslide data base model for ClirTheRoads project in Serbia
UR  - https://hdl.handle.net/21.15107/rcub_grafar_3356
ER  - 

@conference{
author = "Abolmasov, Biljana and Stanković, Ranka and Vulović, Nikola and Marjanović, Miloš and Đurić, Uroš",
year = "2023",
abstract = "Within the project Mainstreaming Climate Resilience in the Road Transportation Management in Serbia (CliRtheRoads), a complex software solution was developed to support Public Enterprise Roads of Serbia in climate change adaptation planning and management. The software solution comprises 1) web portal for data entry and management for authorised users 2) publicly available web GIS part 3) mobile GIS application and 4) back-end database (Figure 1). In order to store and process the data collected during field visits and surveys, the data base developed in project first phase (Valjevo test area), was modified to include new datasets and to store new datatypes (as floods), and new modules (as activity cost) for Kraljevo test area. Both test areas have been chosen due theirs diversified characteristics, many climate related hazards, and the fact they suffered greatly from disasters recently (Abolmasov et al. 2017, Abolmasov et al. 2021). The database was upgraded to new model aimed for maintaining legacy data from both test areas, but also for future infrastructure resilience projects based on same approach, to enable
that all data will be stored and mapped in a unified manner. The data model include 1) main concepts (entity types) for the instabilities, with detailed data comprising common and specific attributes, 2) storage of multimedia (mainly photo from field work, but possible video as well), 3) knowledge base with cost of activities, including catalogue per each entity type with job type and description, unit and total price, maintenance type (regular maintenance, rehabilitation, urgent maintenance), including recommending activities (system allow user to add specific activities, description and cost that is further calculated and aggregated with other data); 4) secondary data from other sources (other projects, legacy data and external resources), or from interpreted data. The data was stored in the PostgreSQL Database, a web application was developed (using PHP) to facilitate data input, maintain knowledge database and calculate cost of recommended activities. There is a total of 461 records with fully described instabilities (slides, falls, topples, flows), documented by large number of photographs from the field. Additionally, every record is supplemented by engineering solution to support field engineers or decision makers for better road management in climate changing conditions.",
publisher = "OIC S.r.l., Viale della Giovine Italia, 17, 50122 Firenze, Italy",
journal = "6th World Landslide Forum, Florence, Italy, 14-17 November 2023, Abstract book",
title = "A landslide data base model for ClirTheRoads project in Serbia",
url = "https://hdl.handle.net/21.15107/rcub_grafar_3356"
}

Abolmasov, B., Stanković, R., Vulović, N., Marjanović, M.,& Đurić, U.. (2023). A landslide data base model for ClirTheRoads project in Serbia. in 6th World Landslide Forum, Florence, Italy, 14-17 November 2023, Abstract book
OIC S.r.l., Viale della Giovine Italia, 17, 50122 Firenze, Italy..
https://hdl.handle.net/21.15107/rcub_grafar_3356

Abolmasov B, Stanković R, Vulović N, Marjanović M, Đurić U. A landslide data base model for ClirTheRoads project in Serbia. in 6th World Landslide Forum, Florence, Italy, 14-17 November 2023, Abstract book. 2023;.
https://hdl.handle.net/21.15107/rcub_grafar_3356 .

Abolmasov, Biljana, Stanković, Ranka, Vulović, Nikola, Marjanović, Miloš, Đurić, Uroš, "A landslide data base model for ClirTheRoads project in Serbia" in 6th World Landslide Forum, Florence, Italy, 14-17 November 2023, Abstract book (2023),
https://hdl.handle.net/21.15107/rcub_grafar_3356 .

TY  - CONF
AU  - Marjanović, Miloš
AU  - Abolmasov, Biljana
AU  - Đurić, Uroš
AU  - Krušić, Jelka
AU  - Bogdanović, Snežana
PY  - 2022
UR  - https://grafar.grf.bg.ac.rs/handle/123456789/2662
AB  - Rockfalls are common in hilly and mountainous areas, especially along roads with engineered slopes and cuts. Such is the case for most of the state and local road routes in Central, Serbia, which was the subject in this case study. A road network of 276 km covering roughly 1700
km2 bewteen the cities of Kraljevo, Čačak and Ivanjica is presented. Assessing of such wide areas needs to be conducted from large to site-specific scale, i.e., using GIS spatial tools and 2D-3D stability models, respectively. The regional scale of assessment using GIS tools was in focus. The primary input was the Digital Terrain Model, obtained from open data ALOS mission at 12.5 m resolution, as well as appropriate sheets of geological maps at 100k scale. The first step was to delineate areas that can host unstable blocks by inspecting planar sliding kinematic condition against available data. These included raster data (slope angle and azimuth) but also, point-based data (discontinuities’ strike, dip and friction angle) which had to be estimated or interpolated across the area by various GIS operations. In total, there were nearly 5000 potential detachments delineated. Further step was to run the rockfall simulation by using these detachment zones as initiation sources in a simple kinetic model CONEFALL, standalone software. The output model simulated several thousands of rockfalls, with various runout distance (<650
m), velocity (<46.5 m/s) and energy (<540 kJ). When overlapped with the road network, this model revealed the road exposure to rockfall. Locations with runouts that reached the road lines make about 6.7 % of the total network length. Zones of estimated energies higher than serviceable threshold (300 kJ) occupy 0.9 % of the total and require additional remediation design. Presented analysis is a promising tool for supporting planning and decision making in the road management sector.
PB  - Faculty of Civil Engineering, University of Rijeka
PB  - Faculty of Mining, Geology and Petroleum Engineering, University of Zagreb
C3  - Proceedings of the 5th Regional Symposium on Landslides in the Adriatic-Balkan Region
T1  - Regional rockfall exposure assessment, experiences from Serbia
EP  - 150
SP  - 145
UR  - https://hdl.handle.net/21.15107/rcub_grafar_2662
ER  - 

@conference{
author = "Marjanović, Miloš and Abolmasov, Biljana and Đurić, Uroš and Krušić, Jelka and Bogdanović, Snežana",
year = "2022",
abstract = "Rockfalls are common in hilly and mountainous areas, especially along roads with engineered slopes and cuts. Such is the case for most of the state and local road routes in Central, Serbia, which was the subject in this case study. A road network of 276 km covering roughly 1700
km2 bewteen the cities of Kraljevo, Čačak and Ivanjica is presented. Assessing of such wide areas needs to be conducted from large to site-specific scale, i.e., using GIS spatial tools and 2D-3D stability models, respectively. The regional scale of assessment using GIS tools was in focus. The primary input was the Digital Terrain Model, obtained from open data ALOS mission at 12.5 m resolution, as well as appropriate sheets of geological maps at 100k scale. The first step was to delineate areas that can host unstable blocks by inspecting planar sliding kinematic condition against available data. These included raster data (slope angle and azimuth) but also, point-based data (discontinuities’ strike, dip and friction angle) which had to be estimated or interpolated across the area by various GIS operations. In total, there were nearly 5000 potential detachments delineated. Further step was to run the rockfall simulation by using these detachment zones as initiation sources in a simple kinetic model CONEFALL, standalone software. The output model simulated several thousands of rockfalls, with various runout distance (<650
m), velocity (<46.5 m/s) and energy (<540 kJ). When overlapped with the road network, this model revealed the road exposure to rockfall. Locations with runouts that reached the road lines make about 6.7 % of the total network length. Zones of estimated energies higher than serviceable threshold (300 kJ) occupy 0.9 % of the total and require additional remediation design. Presented analysis is a promising tool for supporting planning and decision making in the road management sector.",
publisher = "Faculty of Civil Engineering, University of Rijeka, Faculty of Mining, Geology and Petroleum Engineering, University of Zagreb",
journal = "Proceedings of the 5th Regional Symposium on Landslides in the Adriatic-Balkan Region",
title = "Regional rockfall exposure assessment, experiences from Serbia",
pages = "150-145",
url = "https://hdl.handle.net/21.15107/rcub_grafar_2662"
}

Marjanović, M., Abolmasov, B., Đurić, U., Krušić, J.,& Bogdanović, S.. (2022). Regional rockfall exposure assessment, experiences from Serbia. in Proceedings of the 5th Regional Symposium on Landslides in the Adriatic-Balkan Region
Faculty of Civil Engineering, University of Rijeka., 145-150.
https://hdl.handle.net/21.15107/rcub_grafar_2662

Marjanović M, Abolmasov B, Đurić U, Krušić J, Bogdanović S. Regional rockfall exposure assessment, experiences from Serbia. in Proceedings of the 5th Regional Symposium on Landslides in the Adriatic-Balkan Region. 2022;:145-150.
https://hdl.handle.net/21.15107/rcub_grafar_2662 .

Marjanović, Miloš, Abolmasov, Biljana, Đurić, Uroš, Krušić, Jelka, Bogdanović, Snežana, "Regional rockfall exposure assessment, experiences from Serbia" in Proceedings of the 5th Regional Symposium on Landslides in the Adriatic-Balkan Region (2022):145-150,
https://hdl.handle.net/21.15107/rcub_grafar_2662 .

TY  - CONF
AU  - Đurić, Uroš
AU  - Abolmasov, Biljana
AU  - Marjanović, Miloš
AU  - Jocković, Sanja
AU  - Marjanović, Miloš
PY  - 2022
UR  - https://grafar.grf.bg.ac.rs/handle/123456789/2661
AB  - Landslides are one of the most often natural disasters that have an extensive impact on society including loss of life, destruction of infrastructure and properties, damage to land and loss of natural resources. Landslide losses can significantly vary and they depend on a variety of different criteria such as the size and type of landslide, lithological setting of terrain, the terrain slope gradient, the quality of materials used for construction, and the construction typology. Damage from landslides is usually characterized as either direct or indirect and in most questionnaires only the data referring to the direct damage is collected. In this paper, a landslide damage questionnaire that can be used for landslide damage characterization and determination of landslide hazard and risk in urban areas is proposed. The questionnaire contains 11 groups of questions that include all necessary fields for gathering the data which is essential for both landslide hazard and risk estimation. It was used as an inventory landslide damage form in suburban housings which usually occupy larger land plots, while objects built on such plots are mostly houses for an individual living or ancillary type.
PB  - Faculty of Civil Engineering, University of Rijeka
PB  - Faculty of Mining, Geology and Petroleum Engineering, University of Zagreb
C3  - Proceedings of the 5th Regional Symposium on Landslides in the Adriatic-Balkan Region
T1  - A proposal for the landslide damage questionnaire in suburban areas
EP  - 130
SP  - 125
UR  - https://hdl.handle.net/21.15107/rcub_grafar_2661
ER  - 

@conference{
author = "Đurić, Uroš and Abolmasov, Biljana and Marjanović, Miloš and Jocković, Sanja and Marjanović, Miloš",
year = "2022",
abstract = "Landslides are one of the most often natural disasters that have an extensive impact on society including loss of life, destruction of infrastructure and properties, damage to land and loss of natural resources. Landslide losses can significantly vary and they depend on a variety of different criteria such as the size and type of landslide, lithological setting of terrain, the terrain slope gradient, the quality of materials used for construction, and the construction typology. Damage from landslides is usually characterized as either direct or indirect and in most questionnaires only the data referring to the direct damage is collected. In this paper, a landslide damage questionnaire that can be used for landslide damage characterization and determination of landslide hazard and risk in urban areas is proposed. The questionnaire contains 11 groups of questions that include all necessary fields for gathering the data which is essential for both landslide hazard and risk estimation. It was used as an inventory landslide damage form in suburban housings which usually occupy larger land plots, while objects built on such plots are mostly houses for an individual living or ancillary type.",
publisher = "Faculty of Civil Engineering, University of Rijeka, Faculty of Mining, Geology and Petroleum Engineering, University of Zagreb",
journal = "Proceedings of the 5th Regional Symposium on Landslides in the Adriatic-Balkan Region",
title = "A proposal for the landslide damage questionnaire in suburban areas",
pages = "130-125",
url = "https://hdl.handle.net/21.15107/rcub_grafar_2661"
}

Đurić, U., Abolmasov, B., Marjanović, M., Jocković, S.,& Marjanović, M.. (2022). A proposal for the landslide damage questionnaire in suburban areas. in Proceedings of the 5th Regional Symposium on Landslides in the Adriatic-Balkan Region
Faculty of Civil Engineering, University of Rijeka., 125-130.
https://hdl.handle.net/21.15107/rcub_grafar_2661

Đurić U, Abolmasov B, Marjanović M, Jocković S, Marjanović M. A proposal for the landslide damage questionnaire in suburban areas. in Proceedings of the 5th Regional Symposium on Landslides in the Adriatic-Balkan Region. 2022;:125-130.
https://hdl.handle.net/21.15107/rcub_grafar_2661 .

Đurić, Uroš, Abolmasov, Biljana, Marjanović, Miloš, Jocković, Sanja, Marjanović, Miloš, "A proposal for the landslide damage questionnaire in suburban areas" in Proceedings of the 5th Regional Symposium on Landslides in the Adriatic-Balkan Region (2022):125-130,
https://hdl.handle.net/21.15107/rcub_grafar_2661 .

TY  - CONF
AU  - Đurić, Uroš
AU  - Brodić, Nenad
AU  - Radić, Zoran
AU  - Đurić, Dragana
AU  - Marjanović, Miloš
PY  - 2022
UR  - https://grafar.grf.bg.ac.rs/handle/123456789/2899
AB  - Početkom 2020. godine za potrebe rekonstrukcije i adaptacije tunela izvršena su inženjerskogeološka istraživanja koja su obuhvatila detaljno inženjerskogeološko rekognosciranje i kartiranje glavnog tunelskog hodnika i svih podzemnih prostorija kao i geofizičko profiliranje. Rad prikazuje mogućnost primene tehnike generisanja modela objekta na osnovu snimaka dobijenih kamerom pri kretanju oko objekta (engl. Structure from motion - SfM) za 3D rekonstrukciju jedne podzemne prostorije tunela „Čajkino brdo“ u Vrnjačkoj Banji za potrebe inženjerskogeološkog kartiranja i parametrizacije.
SfM predstavlja fotogrametrijsku tehniku određivanja 3D strukture objekta, pozicija i orijentacija kamere iz sekvenci dve ili više dvodimenzionalnih slika istog objekta, ali iz različitih položaja kamere (pasivnog senzora). Za razliku od klasične fotogrametrije gde je neophodno poznavanje spoljašnjih i unutrašnih parametara snimaka, SfM proces 3D rekonstrukcije okruženja je prilično automatizovan i lakši jer je najčešće samo potrebno napraviti dovoljan broj fotografija sačinjenih istim senzorom sa različitih položaja. Snimanje se odvija u vidljivom delu spektra i princip 3D rekonstrukcije okruženja je analogan ljudskom vidu, koji na sličan način formira 3D sliku. Primena SfM tehnike u podzemnim prostorijama je kompleksna usled izostanka prirodnog osvetljenja, nemogućnosti GPS pozicioniranja senzora i ograničenog prostora, koji su ključni za njihovu uspešnu primenu i kvalitetne rezultate 3D rekonstrukcije. Dodatni problem predstavljaju senke, koje mogu otežati kvalitetno automatsko povezivanje snimaka, a koje se formiraju primenom veštačkih izvora osvetljavanja da bi se formirao snimak u vidljivom delu spektra. Kod fotogrametrijske rekonstrukcije modela objekta bitno je i da površina objekta bude matirana, tj. bez sjajnih reflektujućih površina kakve su najčešće površine stena u tunelima.
Tokom istraživanja izvršeno je ogledno fotogrametrijsko snimanje odabrane prostorije i obrada dobijenih snimaka primenom SfM tehnike. Snimanje je izvršeno korišćenjem mobilnog telefona Huawei P10 Pro i Xiaomi Mija 360° sferne kamere. Snimanje mobilnim telefonom je vršeno „iz ruke“ i sa „visine očiju posmatrača“ tako da se ostvari najveći mogući preklop između snimaka. Snimanje sfernom kamerom je izvršeno uz pomoć stativa, postavljanjem sferne kamere u pravilnom mrežnom rasporedu na tri različite visine.
Na osnovu snimaka dobijenih na ovaj način, primenom SfM tehnike generisana su dva različita 3D oblaka tačaka koja su upoređena i na osnovu kojih je izvršeno inženjerskogeološko kartiranje podzemne prostorije. 3D oblak tačaka je procesiran, uključujući urazmeravanje, orijentaciju, odnosno rotiranje prostorije u realan položaj i uklanjanje suvišnih tačaka. Na ovaj način, a nakon procesiranja, izvršeno je inženjerskogeološko kartiranje zidova i svoda podzemne prostorije, odnosno određivanje indeksa hrapavosti stenske mase, definisanje strukturnog sklopa tj. utvrđivanje karakterističnih familija pukotina (manuelno i automatski), izradu karakterističnih profila svetlog otvora i analizu njihove stabilnosti uz kritički osvrt.
PB  - Srpsko geološko društvo
C3  - Zbornik apstrakata XVIII Kongres geologa Srbije, Divčibare
T1  - Primena Structure From Motion tehnike za inženjerskogeološko kartiranje podzemnih prostorija
EP  - 89
SP  - 88
UR  - https://hdl.handle.net/21.15107/rcub_grafar_2899
ER  - 

@conference{
author = "Đurić, Uroš and Brodić, Nenad and Radić, Zoran and Đurić, Dragana and Marjanović, Miloš",
year = "2022",
abstract = "Početkom 2020. godine za potrebe rekonstrukcije i adaptacije tunela izvršena su inženjerskogeološka istraživanja koja su obuhvatila detaljno inženjerskogeološko rekognosciranje i kartiranje glavnog tunelskog hodnika i svih podzemnih prostorija kao i geofizičko profiliranje. Rad prikazuje mogućnost primene tehnike generisanja modela objekta na osnovu snimaka dobijenih kamerom pri kretanju oko objekta (engl. Structure from motion - SfM) za 3D rekonstrukciju jedne podzemne prostorije tunela „Čajkino brdo“ u Vrnjačkoj Banji za potrebe inženjerskogeološkog kartiranja i parametrizacije.
SfM predstavlja fotogrametrijsku tehniku određivanja 3D strukture objekta, pozicija i orijentacija kamere iz sekvenci dve ili više dvodimenzionalnih slika istog objekta, ali iz različitih položaja kamere (pasivnog senzora). Za razliku od klasične fotogrametrije gde je neophodno poznavanje spoljašnjih i unutrašnih parametara snimaka, SfM proces 3D rekonstrukcije okruženja je prilično automatizovan i lakši jer je najčešće samo potrebno napraviti dovoljan broj fotografija sačinjenih istim senzorom sa različitih položaja. Snimanje se odvija u vidljivom delu spektra i princip 3D rekonstrukcije okruženja je analogan ljudskom vidu, koji na sličan način formira 3D sliku. Primena SfM tehnike u podzemnim prostorijama je kompleksna usled izostanka prirodnog osvetljenja, nemogućnosti GPS pozicioniranja senzora i ograničenog prostora, koji su ključni za njihovu uspešnu primenu i kvalitetne rezultate 3D rekonstrukcije. Dodatni problem predstavljaju senke, koje mogu otežati kvalitetno automatsko povezivanje snimaka, a koje se formiraju primenom veštačkih izvora osvetljavanja da bi se formirao snimak u vidljivom delu spektra. Kod fotogrametrijske rekonstrukcije modela objekta bitno je i da površina objekta bude matirana, tj. bez sjajnih reflektujućih površina kakve su najčešće površine stena u tunelima.
Tokom istraživanja izvršeno je ogledno fotogrametrijsko snimanje odabrane prostorije i obrada dobijenih snimaka primenom SfM tehnike. Snimanje je izvršeno korišćenjem mobilnog telefona Huawei P10 Pro i Xiaomi Mija 360° sferne kamere. Snimanje mobilnim telefonom je vršeno „iz ruke“ i sa „visine očiju posmatrača“ tako da se ostvari najveći mogući preklop između snimaka. Snimanje sfernom kamerom je izvršeno uz pomoć stativa, postavljanjem sferne kamere u pravilnom mrežnom rasporedu na tri različite visine.
Na osnovu snimaka dobijenih na ovaj način, primenom SfM tehnike generisana su dva različita 3D oblaka tačaka koja su upoređena i na osnovu kojih je izvršeno inženjerskogeološko kartiranje podzemne prostorije. 3D oblak tačaka je procesiran, uključujući urazmeravanje, orijentaciju, odnosno rotiranje prostorije u realan položaj i uklanjanje suvišnih tačaka. Na ovaj način, a nakon procesiranja, izvršeno je inženjerskogeološko kartiranje zidova i svoda podzemne prostorije, odnosno određivanje indeksa hrapavosti stenske mase, definisanje strukturnog sklopa tj. utvrđivanje karakterističnih familija pukotina (manuelno i automatski), izradu karakterističnih profila svetlog otvora i analizu njihove stabilnosti uz kritički osvrt.",
publisher = "Srpsko geološko društvo",
journal = "Zbornik apstrakata XVIII Kongres geologa Srbije, Divčibare",
title = "Primena Structure From Motion tehnike za inženjerskogeološko kartiranje podzemnih prostorija",
pages = "89-88",
url = "https://hdl.handle.net/21.15107/rcub_grafar_2899"
}

Đurić, U., Brodić, N., Radić, Z., Đurić, D.,& Marjanović, M.. (2022). Primena Structure From Motion tehnike za inženjerskogeološko kartiranje podzemnih prostorija. in Zbornik apstrakata XVIII Kongres geologa Srbije, Divčibare
Srpsko geološko društvo., 88-89.
https://hdl.handle.net/21.15107/rcub_grafar_2899

Đurić U, Brodić N, Radić Z, Đurić D, Marjanović M. Primena Structure From Motion tehnike za inženjerskogeološko kartiranje podzemnih prostorija. in Zbornik apstrakata XVIII Kongres geologa Srbije, Divčibare. 2022;:88-89.
https://hdl.handle.net/21.15107/rcub_grafar_2899 .

Đurić, Uroš, Brodić, Nenad, Radić, Zoran, Đurić, Dragana, Marjanović, Miloš, "Primena Structure From Motion tehnike za inženjerskogeološko kartiranje podzemnih prostorija" in Zbornik apstrakata XVIII Kongres geologa Srbije, Divčibare (2022):88-89,
https://hdl.handle.net/21.15107/rcub_grafar_2899 .

TY  - CONF
AU  - Marjanović, Miloš
AU  - Abolmasov, Biljana
AU  - Berisavljević, Zoran
AU  - Pejić, Marko
AU  - Vranić, Petko
PY  - 2021
UR  - https://grafar.grf.bg.ac.rs/handle/123456789/3030
AB  - In this article, we are elaborating an example of predictive rockfall assessment by
using Terrestrial Laser Scanning (TLS) in monitoring a road cut, hosted in flysch rock formation,
near Ljig in Serbia. A sequence of rockfall events from 2013-2019 is presented, while the cut
has been more broadly investigated in our earlier work. Beside occasional rockfalls which are
routinely detected by annual TLS monitoring, it was possible to track the pre-failure
deformations preceding a series of rockfalls, reaching 0.3 m3 in volume with 0.5 annual
reoccurrence probability. Monitoring enabled identification of subtle displacements of about 1
cm after the first event in 2014 and keeping track of its progression. After a series of events in
the following years, we were able to define the pre-failure threshold which can be applied to the
adjacent rock blocks, assuming a similar block volume. It also enabled us to anticipate and
simulate the event before it happens. This approach allows planning, prevention and protection,
and there is a great deal of interest to standardize it for high-risk slopes and cuts in rock masses.
PB  - IOP Publishing
C3  - IOP Conference Series: Earth and Environmental Science
T1  - Pre-failure deformation monitoring as rockfall prediction tool
DO  - 10.1088/1755-1315/833/1/012197
ER  - 

@conference{
author = "Marjanović, Miloš and Abolmasov, Biljana and Berisavljević, Zoran and Pejić, Marko and Vranić, Petko",
year = "2021",
abstract = "In this article, we are elaborating an example of predictive rockfall assessment by
using Terrestrial Laser Scanning (TLS) in monitoring a road cut, hosted in flysch rock formation,
near Ljig in Serbia. A sequence of rockfall events from 2013-2019 is presented, while the cut
has been more broadly investigated in our earlier work. Beside occasional rockfalls which are
routinely detected by annual TLS monitoring, it was possible to track the pre-failure
deformations preceding a series of rockfalls, reaching 0.3 m3 in volume with 0.5 annual
reoccurrence probability. Monitoring enabled identification of subtle displacements of about 1
cm after the first event in 2014 and keeping track of its progression. After a series of events in
the following years, we were able to define the pre-failure threshold which can be applied to the
adjacent rock blocks, assuming a similar block volume. It also enabled us to anticipate and
simulate the event before it happens. This approach allows planning, prevention and protection,
and there is a great deal of interest to standardize it for high-risk slopes and cuts in rock masses.",
publisher = "IOP Publishing",
journal = "IOP Conference Series: Earth and Environmental Science",
title = "Pre-failure deformation monitoring as rockfall prediction tool",
doi = "10.1088/1755-1315/833/1/012197"
}

Marjanović, M., Abolmasov, B., Berisavljević, Z., Pejić, M.,& Vranić, P.. (2021). Pre-failure deformation monitoring as rockfall prediction tool. in IOP Conference Series: Earth and Environmental Science
IOP Publishing..
https://doi.org/10.1088/1755-1315/833/1/012197

Marjanović M, Abolmasov B, Berisavljević Z, Pejić M, Vranić P. Pre-failure deformation monitoring as rockfall prediction tool. in IOP Conference Series: Earth and Environmental Science. 2021;.
doi:10.1088/1755-1315/833/1/012197 .

Marjanović, Miloš, Abolmasov, Biljana, Berisavljević, Zoran, Pejić, Marko, Vranić, Petko, "Pre-failure deformation monitoring as rockfall prediction tool" in IOP Conference Series: Earth and Environmental Science (2021),
https://doi.org/10.1088/1755-1315/833/1/012197 . .

TY  - CONF
AU  - Marjanović, Miloš
AU  - Abolmasov, Biljana
AU  - Pejić, Marko
AU  - Jelka, Krušić
PY  - 2021
UR  - https://grafar.grf.bg.ac.rs/handle/123456789/3032
PB  - International Association for Engineering Geology and the Environment
C3  - Proceedings of 3rd European Regional Conference of IAEG/ Athens/ Greece/ 6-10 October 2021
T1  - Long-term rockslope monitoring and rockfall prediction
UR  - https://hdl.handle.net/21.15107/rcub_grafar_3032
ER  - 

@conference{
author = "Marjanović, Miloš and Abolmasov, Biljana and Pejić, Marko and Jelka, Krušić",
year = "2021",
publisher = "International Association for Engineering Geology and the Environment",
journal = "Proceedings of 3rd European Regional Conference of IAEG/ Athens/ Greece/ 6-10 October 2021",
title = "Long-term rockslope monitoring and rockfall prediction",
url = "https://hdl.handle.net/21.15107/rcub_grafar_3032"
}

Marjanović, M., Abolmasov, B., Pejić, M.,& Jelka, K.. (2021). Long-term rockslope monitoring and rockfall prediction. in Proceedings of 3rd European Regional Conference of IAEG/ Athens/ Greece/ 6-10 October 2021
International Association for Engineering Geology and the Environment..
https://hdl.handle.net/21.15107/rcub_grafar_3032

Marjanović M, Abolmasov B, Pejić M, Jelka K. Long-term rockslope monitoring and rockfall prediction. in Proceedings of 3rd European Regional Conference of IAEG/ Athens/ Greece/ 6-10 October 2021. 2021;.
https://hdl.handle.net/21.15107/rcub_grafar_3032 .

Marjanović, Miloš, Abolmasov, Biljana, Pejić, Marko, Jelka, Krušić, "Long-term rockslope monitoring and rockfall prediction" in Proceedings of 3rd European Regional Conference of IAEG/ Athens/ Greece/ 6-10 October 2021 (2021),
https://hdl.handle.net/21.15107/rcub_grafar_3032 .

TY  - CONF
AU  - Samardžić-Petrović, Mileva
AU  - Popović, Jovan
AU  - Đurić, Uroš
AU  - Abolmasov, Biljana
AU  - Pejić, Marko
AU  - Marjanović, Miloš
PY  - 2020
UR  - https://grafar.grf.bg.ac.rs/handle/123456789/2214
AB  - The Umka landslide is one of the biggest inhabited active landslides in Serbia. The Umka landslide activity has been monitored for a period longer than 85 years, by various geotechnical and geodetic techniques. Since 2010, landslide activity has been continuously monitored by automated permanent Global Navigation Satellite System (GNSS) based monitoring system in real time. Furthermore, since 2018 landslide activity has been monitored by GNSS kinematic positioning of a set of characteristic points as well as by UAV (Unmanned Aerial Vehicle) photogrammetry. The main issue of this paper is the presentation of the results gained with GNSS kinematic positioning of characteristic points of Umka landslide within three observation epochs.
PB  - University of Banja Luka Faculty of Architecture, Civil Engineering and Geode
C3  - XIV International Conference On Contemporary Theory And Practice In Construction XIV Stepgrad XIV Proceedings, 2020
T1  - Permanent GNSS monitoring of landslide Umka
DO  - 10.7251/STP2014091S
ER  - 

@conference{
author = "Samardžić-Petrović, Mileva and Popović, Jovan and Đurić, Uroš and Abolmasov, Biljana and Pejić, Marko and Marjanović, Miloš",
year = "2020",
abstract = "The Umka landslide is one of the biggest inhabited active landslides in Serbia. The Umka landslide activity has been monitored for a period longer than 85 years, by various geotechnical and geodetic techniques. Since 2010, landslide activity has been continuously monitored by automated permanent Global Navigation Satellite System (GNSS) based monitoring system in real time. Furthermore, since 2018 landslide activity has been monitored by GNSS kinematic positioning of a set of characteristic points as well as by UAV (Unmanned Aerial Vehicle) photogrammetry. The main issue of this paper is the presentation of the results gained with GNSS kinematic positioning of characteristic points of Umka landslide within three observation epochs.",
publisher = "University of Banja Luka Faculty of Architecture, Civil Engineering and Geode",
journal = "XIV International Conference On Contemporary Theory And Practice In Construction XIV Stepgrad XIV Proceedings, 2020",
title = "Permanent GNSS monitoring of landslide Umka",
doi = "10.7251/STP2014091S"
}

Samardžić-Petrović, M., Popović, J., Đurić, U., Abolmasov, B., Pejić, M.,& Marjanović, M.. (2020). Permanent GNSS monitoring of landslide Umka. in XIV International Conference On Contemporary Theory And Practice In Construction XIV Stepgrad XIV Proceedings, 2020
University of Banja Luka Faculty of Architecture, Civil Engineering and Geode..
https://doi.org/10.7251/STP2014091S

Samardžić-Petrović M, Popović J, Đurić U, Abolmasov B, Pejić M, Marjanović M. Permanent GNSS monitoring of landslide Umka. in XIV International Conference On Contemporary Theory And Practice In Construction XIV Stepgrad XIV Proceedings, 2020. 2020;.
doi:10.7251/STP2014091S .

Samardžić-Petrović, Mileva, Popović, Jovan, Đurić, Uroš, Abolmasov, Biljana, Pejić, Marko, Marjanović, Miloš, "Permanent GNSS monitoring of landslide Umka" in XIV International Conference On Contemporary Theory And Practice In Construction XIV Stepgrad XIV Proceedings, 2020 (2020),
https://doi.org/10.7251/STP2014091S . .

TY  - JOUR
AU  - Đurić, Uroš
AU  - Marjanović, Miloš
AU  - Radić, Zoran
AU  - Abolmasov, Biljana
PY  - 2019
UR  - https://grafar.grf.bg.ac.rs/handle/123456789/1729
AB  - Improvements of Machine Learning-based landslide prediction models can be made by optimizing scale, customizing training samples to provide sets with the best examples, feature selection, etc. Herein, a novel approach, named Cross-Scaling, is proposed that includes the mixing of training and testing set resolutions. Hypothetically, training on a coarser resolution dataset and testing the model on a finer resolution should help the algorithm to better generalize ambiguous examples of landslide classes and yield fewer over/underestimations in the model. This case study considers the City of Belgrade area for training and its south-eastern suburb for testing. The dataset is exceptionally rich with detailed geological, morphological and environmental data, so 24 landslide predictors were used for multi-class mapping: Class 0 – stable ground, Class 1 - dormant landslides, and Class 2 – active landslides. Two state-of-the-art algorithms were implemented: Support Vector Machines and Random Forest. Additionally, our modelling included variants with an implemented feature selection by using the Information Gain and Correlation Feature Selection. All these variants were modelled across four resolutions - 25, 50, 100 and 200 m, whereby Cross-Scaling was implemented as follows: training on 50 and testing on 25, training on 100 and testing on 25, training on 100 and testing on 50, training on 200 and testing on 25, training on 200 and testing on 50, and finally, training on 200 and testing on 100 m resolution datasets. The results clearly show that Cross-Scaling improves the performance of the model, especially for Class 2, when compared to the performance of their non-Cross-Scaled counterparts; this thereby proves the initial hypothesis. Random Forest models tend to be less sensitive to scale and feature selection effects than the SVM. Class 1 remains the most difficult to discern, leaving some room for even further customization and adjustments. In conclusion, the Cross-Scaling technique is proposed as a method that could become a promising tool for training/testing protocols in landslide assessment.
PB  - Elsevier
T2  - Engineering Geology
T1  - Machine learning based landslide assessment of the Belgrade metropolitan area: Pixel resolution effects and a cross-scaling concept
EP  - 38
SP  - 23
VL  - 256
DO  - 10.1016/j.enggeo.2019.05.007
ER  - 

@article{
author = "Đurić, Uroš and Marjanović, Miloš and Radić, Zoran and Abolmasov, Biljana",
year = "2019",
abstract = "Improvements of Machine Learning-based landslide prediction models can be made by optimizing scale, customizing training samples to provide sets with the best examples, feature selection, etc. Herein, a novel approach, named Cross-Scaling, is proposed that includes the mixing of training and testing set resolutions. Hypothetically, training on a coarser resolution dataset and testing the model on a finer resolution should help the algorithm to better generalize ambiguous examples of landslide classes and yield fewer over/underestimations in the model. This case study considers the City of Belgrade area for training and its south-eastern suburb for testing. The dataset is exceptionally rich with detailed geological, morphological and environmental data, so 24 landslide predictors were used for multi-class mapping: Class 0 – stable ground, Class 1 - dormant landslides, and Class 2 – active landslides. Two state-of-the-art algorithms were implemented: Support Vector Machines and Random Forest. Additionally, our modelling included variants with an implemented feature selection by using the Information Gain and Correlation Feature Selection. All these variants were modelled across four resolutions - 25, 50, 100 and 200 m, whereby Cross-Scaling was implemented as follows: training on 50 and testing on 25, training on 100 and testing on 25, training on 100 and testing on 50, training on 200 and testing on 25, training on 200 and testing on 50, and finally, training on 200 and testing on 100 m resolution datasets. The results clearly show that Cross-Scaling improves the performance of the model, especially for Class 2, when compared to the performance of their non-Cross-Scaled counterparts; this thereby proves the initial hypothesis. Random Forest models tend to be less sensitive to scale and feature selection effects than the SVM. Class 1 remains the most difficult to discern, leaving some room for even further customization and adjustments. In conclusion, the Cross-Scaling technique is proposed as a method that could become a promising tool for training/testing protocols in landslide assessment.",
publisher = "Elsevier",
journal = "Engineering Geology",
title = "Machine learning based landslide assessment of the Belgrade metropolitan area: Pixel resolution effects and a cross-scaling concept",
pages = "38-23",
volume = "256",
doi = "10.1016/j.enggeo.2019.05.007"
}

Đurić, U., Marjanović, M., Radić, Z.,& Abolmasov, B.. (2019). Machine learning based landslide assessment of the Belgrade metropolitan area: Pixel resolution effects and a cross-scaling concept. in Engineering Geology
Elsevier., 256, 23-38.
https://doi.org/10.1016/j.enggeo.2019.05.007

Đurić U, Marjanović M, Radić Z, Abolmasov B. Machine learning based landslide assessment of the Belgrade metropolitan area: Pixel resolution effects and a cross-scaling concept. in Engineering Geology. 2019;256:23-38.
doi:10.1016/j.enggeo.2019.05.007 .

Đurić, Uroš, Marjanović, Miloš, Radić, Zoran, Abolmasov, Biljana, "Machine learning based landslide assessment of the Belgrade metropolitan area: Pixel resolution effects and a cross-scaling concept" in Engineering Geology, 256 (2019):23-38,
https://doi.org/10.1016/j.enggeo.2019.05.007 . .

TY  - JOUR
AU  - Peshevski, I.
AU  - Jovanovski, M.
AU  - Abolmasov, Biljana
AU  - Papić, J.
AU  - Đurić, Uroš
AU  - Marjanović, Miloš
AU  - Haque, U.
AU  - Nedelkovska, N.
PY  - 2019
UR  - https://grafar.grf.bg.ac.rs/handle/123456789/994
AB  - In this paper a heuristic approach for preliminary regional landslide susceptibility assessment using limited amount of data is presented. It is called arbitrary polynomial method and takes into account 5 landslide conditioning parameters: lithology, slope inclination, average annual rainfall, land use and maximum expected seismic intensity. According to the method, in the first stage, a gradation is performed for each of the carefully selected conditioning parameters by assigning so called rating points to the grid cells on which the region is divided. Values of the rating points vary from 0 to 3 and depend on the parameter’s character and importance for landslide development within the region of interest. A so called Total Landslide Susceptibility Rating (TLSR) model is obtained by summing the individual rating points of each parameter and dividing the region into five susceptibility zones according to Jenks natural breaks classification. Verification of the TLSR model is then performed by overlaying the landslide inventory map of the selected region over the prepared susceptibility map. The sensitivity of the model can be additionally tested by multiplying the conditioning parameter’s rating points by sensitivity coefficients. In this way, additional landslide susceptibility models are obtained, named Weighted Total Landslide Susceptibility Rating (WTLSR) models. As a practical example of the method, two TLSR models are presented here for the Polog region in Republic of Macedonia, for return periods of maximum expected seismic intensity for 100 and 500 years. With over 74% of mapped landslides falling in zones of high and very high susceptibility, the results are considered satisfactory for regional scale landslide modelling and are comparable with more advanced quantitative methods. Additional WTLSR models were prepared, and their correlation identified the best model. The presented approach is considered to be very convenient for conducting preliminary regional landslide susceptibility assessments with the ability to fine-tune the results. Due to its simplicity, it can be applied to additional landslide conditioning parameters other than the one presented in the paper, depending on the region of interest and available data sources. It is especially practical for use in developing countries, where various organizational, technical and economic constraints prevent application of more advanced data driven methods. Limitations and restrictions of the approach are also discussed.
PB  - Croatian Geological Survey
T2  - Geologia Croatica
T1  - Preliminary regional landslide susceptibility assessment using limited data
EP  - 92
IS  - 1
SP  - 81
VL  - 72
DO  - 10.4154/gc.2019.03
ER  - 

@article{
author = "Peshevski, I. and Jovanovski, M. and Abolmasov, Biljana and Papić, J. and Đurić, Uroš and Marjanović, Miloš and Haque, U. and Nedelkovska, N.",
year = "2019",
abstract = "In this paper a heuristic approach for preliminary regional landslide susceptibility assessment using limited amount of data is presented. It is called arbitrary polynomial method and takes into account 5 landslide conditioning parameters: lithology, slope inclination, average annual rainfall, land use and maximum expected seismic intensity. According to the method, in the first stage, a gradation is performed for each of the carefully selected conditioning parameters by assigning so called rating points to the grid cells on which the region is divided. Values of the rating points vary from 0 to 3 and depend on the parameter’s character and importance for landslide development within the region of interest. A so called Total Landslide Susceptibility Rating (TLSR) model is obtained by summing the individual rating points of each parameter and dividing the region into five susceptibility zones according to Jenks natural breaks classification. Verification of the TLSR model is then performed by overlaying the landslide inventory map of the selected region over the prepared susceptibility map. The sensitivity of the model can be additionally tested by multiplying the conditioning parameter’s rating points by sensitivity coefficients. In this way, additional landslide susceptibility models are obtained, named Weighted Total Landslide Susceptibility Rating (WTLSR) models. As a practical example of the method, two TLSR models are presented here for the Polog region in Republic of Macedonia, for return periods of maximum expected seismic intensity for 100 and 500 years. With over 74% of mapped landslides falling in zones of high and very high susceptibility, the results are considered satisfactory for regional scale landslide modelling and are comparable with more advanced quantitative methods. Additional WTLSR models were prepared, and their correlation identified the best model. The presented approach is considered to be very convenient for conducting preliminary regional landslide susceptibility assessments with the ability to fine-tune the results. Due to its simplicity, it can be applied to additional landslide conditioning parameters other than the one presented in the paper, depending on the region of interest and available data sources. It is especially practical for use in developing countries, where various organizational, technical and economic constraints prevent application of more advanced data driven methods. Limitations and restrictions of the approach are also discussed.",
publisher = "Croatian Geological Survey",
journal = "Geologia Croatica",
title = "Preliminary regional landslide susceptibility assessment using limited data",
pages = "92-81",
number = "1",
volume = "72",
doi = "10.4154/gc.2019.03"
}

Peshevski, I., Jovanovski, M., Abolmasov, B., Papić, J., Đurić, U., Marjanović, M., Haque, U.,& Nedelkovska, N.. (2019). Preliminary regional landslide susceptibility assessment using limited data. in Geologia Croatica
Croatian Geological Survey., 72(1), 81-92.
https://doi.org/10.4154/gc.2019.03

Peshevski I, Jovanovski M, Abolmasov B, Papić J, Đurić U, Marjanović M, Haque U, Nedelkovska N. Preliminary regional landslide susceptibility assessment using limited data. in Geologia Croatica. 2019;72(1):81-92.
doi:10.4154/gc.2019.03 .

Peshevski, I., Jovanovski, M., Abolmasov, Biljana, Papić, J., Đurić, Uroš, Marjanović, Miloš, Haque, U., Nedelkovska, N., "Preliminary regional landslide susceptibility assessment using limited data" in Geologia Croatica, 72, no. 1 (2019):81-92,
https://doi.org/10.4154/gc.2019.03 . .

TY  - CHAP
AU  - Marjanović, Miloš
AU  - Samardžić-Petrović, Mileva
AU  - Abolmasov, Biljana
AU  - Đurić, Uroš
PY  - 2019
UR  - https://grafar.grf.bg.ac.rs/handle/123456789/989
AB  - 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, and Halenkovice area in Czech Republic, eight key issues were identified, and appropriate options, solutions, and some new concepts for overcoming them were introduced. The following issues were addressed: Landslide inventory enhancements (overcoming small number of landslide instances), Choice of attributes (which attributes are appropriate and pros and cons on attribute selection/extraction), Classification versus regression (which type of task is more appropriate in particular cases), Choice of ML technique (discussion of most popular ML techniques), Sampling strategy (overcoming the overfit by choosing training instances wisely), Cross-scaling (a new concept for improving the algorithm’s learning capacity), Quasi-hazard concept (introducing artificial temporal base for upgrading from susceptibility to hazard assessment), and Objective model evaluation (the best practice for validating resulting models against the existing inventory). All of them are followed by appropriate practical examples from one of abovementioned case studies. The ultimate objective is to provide guidance and inspire LAM community for a more innovative approach in modeling.
PB  - Springer Netherlands
T2  - Advances in Natural and Technological Hazards Research
T1  - Concepts for improving machine learning based landslide assessment
EP  - 58
SP  - 27
VL  - 48
DO  - 10.1007/978-3-319-73383-8_2
ER  - 

@inbook{
author = "Marjanović, Miloš and Samardžić-Petrović, Mileva and Abolmasov, Biljana and Đurić, Uroš",
year = "2019",
abstract = "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, and Halenkovice area in Czech Republic, eight key issues were identified, and appropriate options, solutions, and some new concepts for overcoming them were introduced. The following issues were addressed: Landslide inventory enhancements (overcoming small number of landslide instances), Choice of attributes (which attributes are appropriate and pros and cons on attribute selection/extraction), Classification versus regression (which type of task is more appropriate in particular cases), Choice of ML technique (discussion of most popular ML techniques), Sampling strategy (overcoming the overfit by choosing training instances wisely), Cross-scaling (a new concept for improving the algorithm’s learning capacity), Quasi-hazard concept (introducing artificial temporal base for upgrading from susceptibility to hazard assessment), and Objective model evaluation (the best practice for validating resulting models against the existing inventory). All of them are followed by appropriate practical examples from one of abovementioned case studies. The ultimate objective is to provide guidance and inspire LAM community for a more innovative approach in modeling.",
publisher = "Springer Netherlands",
journal = "Advances in Natural and Technological Hazards Research",
booktitle = "Concepts for improving machine learning based landslide assessment",
pages = "58-27",
volume = "48",
doi = "10.1007/978-3-319-73383-8_2"
}

Marjanović, M., Samardžić-Petrović, M., Abolmasov, B.,& Đurić, U.. (2019). Concepts for improving machine learning based landslide assessment. in Advances in Natural and Technological Hazards Research
Springer Netherlands., 48, 27-58.
https://doi.org/10.1007/978-3-319-73383-8_2

Marjanović M, Samardžić-Petrović M, Abolmasov B, Đurić U. Concepts for improving machine learning based landslide assessment. in Advances in Natural and Technological Hazards Research. 2019;48:27-58.
doi:10.1007/978-3-319-73383-8_2 .

Marjanović, Miloš, Samardžić-Petrović, Mileva, Abolmasov, Biljana, Đurić, Uroš, "Concepts for improving machine learning based landslide assessment" in Advances in Natural and Technological Hazards Research, 48 (2019):27-58,
https://doi.org/10.1007/978-3-319-73383-8_2 . .

TY  - CHAP
AU  - Marjanović, Miloš
AU  - Abolmasov, Biljana
AU  - Milenković, Svetozar
AU  - Đurić, Uroš
AU  - Samardžić-Petrović, Mileva
PY  - 2019
UR  - https://grafar.grf.bg.ac.rs/handle/123456789/1892
PB  - Elsevier
T2  - Spatial Modeling in GIS and R for Earth and Environmental Sciences
T1  - Multihazard Exposure Assessment on the Valjevo City Road Network
EP  - 688
SP  - 671
DO  - https://doi.org/10.1016/B978-0-12-815226-3.00031-4
ER  - 

@inbook{
author = "Marjanović, Miloš and Abolmasov, Biljana and Milenković, Svetozar and Đurić, Uroš and Samardžić-Petrović, Mileva",
year = "2019",
publisher = "Elsevier",
journal = "Spatial Modeling in GIS and R for Earth and Environmental Sciences",
booktitle = "Multihazard Exposure Assessment on the Valjevo City Road Network",
pages = "688-671",
doi = "https://doi.org/10.1016/B978-0-12-815226-3.00031-4"
}

Marjanović, M., Abolmasov, B., Milenković, S., Đurić, U.,& Samardžić-Petrović, M.. (2019). Multihazard Exposure Assessment on the Valjevo City Road Network. in Spatial Modeling in GIS and R for Earth and Environmental Sciences
Elsevier., 671-688.
https://doi.org/https://doi.org/10.1016/B978-0-12-815226-3.00031-4

Marjanović M, Abolmasov B, Milenković S, Đurić U, Samardžić-Petrović M. Multihazard Exposure Assessment on the Valjevo City Road Network. in Spatial Modeling in GIS and R for Earth and Environmental Sciences. 2019;:671-688.
doi:https://doi.org/10.1016/B978-0-12-815226-3.00031-4 .

Marjanović, Miloš, Abolmasov, Biljana, Milenković, Svetozar, Đurić, Uroš, Samardžić-Petrović, Mileva, "Multihazard Exposure Assessment on the Valjevo City Road Network" in Spatial Modeling in GIS and R for Earth and Environmental Sciences (2019):671-688,
https://doi.org/https://doi.org/10.1016/B978-0-12-815226-3.00031-4 . .

TY  - CONF
AU  - Đurić, Uroš
AU  - Pejić, Marko
AU  - Marjanović, Miloš
AU  - Đurić, D.
AU  - Krušić, Jelka
PY  - 2018
UR  - https://grafar.grf.bg.ac.rs/handle/123456789/1644
AB  - Project "Мonitoring оf Erosion on the Đavolja Varoš site ‐ MEĐA: sustainability of natural phenomena in climate change conditions ", was created by a team of young scientists and PhD students from the Faculty of Mining and Geology and Faculty of Civil Engineering, University of Belgrade. The area of interest is Đavolja Varoš, near Kuršumlija, where all field research will be carried out, while the analysis of the collected data will be done at the Faculty of Mining and Geology and Faculty of Civil Engineering in Belgrade. MEĐA aims to popularize the natural values of the protected area of Đavolja Varoš, but also to raise awareness about the problems of sustainability of this natural phenomenon in the climate change conditions (Naydenova 2012), among the wider and local public, as well as among the scientific circles in the country and abroad. Indirectly, the project encourages local activism through local involvement in the development of this research and its results, responsible planning, interdisciplinary approach to solving problems and approaching the problem of the local population through education, which should be stimulative for the preservation and promotion of the natural heritage. The desired long‐term effect that would result from this research should have a significant part in the overall socioeconomic development of the municipality of Kuršumlija, and the entire Toplica district.
PB  - Srpsko geološko društvo, Beograd
C3  - Knjiga apstrakata / 17. Kongres geologa Srbije, Vrnjačka Banja, 17-20. maj 2018. = Book of abstracts / 17th Serbian Geological Congress, Vrnjačka banja, Maz 17-20, 2018. Vol. 2
T1  - Monitoring of erosion in the area of Đabolja Varoš: Project "Međa"
T1  - Monitoring erozije na području Đavolje Varoši: Projekat „Međa“
EP  - 785
SP  - 780
UR  - https://hdl.handle.net/21.15107/rcub_grafar_1644
ER  - 

@conference{
author = "Đurić, Uroš and Pejić, Marko and Marjanović, Miloš and Đurić, D. and Krušić, Jelka",
year = "2018",
abstract = "Project "Мonitoring оf Erosion on the Đavolja Varoš site ‐ MEĐA: sustainability of natural phenomena in climate change conditions ", was created by a team of young scientists and PhD students from the Faculty of Mining and Geology and Faculty of Civil Engineering, University of Belgrade. The area of interest is Đavolja Varoš, near Kuršumlija, where all field research will be carried out, while the analysis of the collected data will be done at the Faculty of Mining and Geology and Faculty of Civil Engineering in Belgrade. MEĐA aims to popularize the natural values of the protected area of Đavolja Varoš, but also to raise awareness about the problems of sustainability of this natural phenomenon in the climate change conditions (Naydenova 2012), among the wider and local public, as well as among the scientific circles in the country and abroad. Indirectly, the project encourages local activism through local involvement in the development of this research and its results, responsible planning, interdisciplinary approach to solving problems and approaching the problem of the local population through education, which should be stimulative for the preservation and promotion of the natural heritage. The desired long‐term effect that would result from this research should have a significant part in the overall socioeconomic development of the municipality of Kuršumlija, and the entire Toplica district.",
publisher = "Srpsko geološko društvo, Beograd",
journal = "Knjiga apstrakata / 17. Kongres geologa Srbije, Vrnjačka Banja, 17-20. maj 2018. = Book of abstracts / 17th Serbian Geological Congress, Vrnjačka banja, Maz 17-20, 2018. Vol. 2",
title = "Monitoring of erosion in the area of Đabolja Varoš: Project "Međa", Monitoring erozije na području Đavolje Varoši: Projekat „Međa“",
pages = "785-780",
url = "https://hdl.handle.net/21.15107/rcub_grafar_1644"
}

Đurić, U., Pejić, M., Marjanović, M., Đurić, D.,& Krušić, J.. (2018). Monitoring of erosion in the area of Đabolja Varoš: Project "Međa". in Knjiga apstrakata / 17. Kongres geologa Srbije, Vrnjačka Banja, 17-20. maj 2018. = Book of abstracts / 17th Serbian Geological Congress, Vrnjačka banja, Maz 17-20, 2018. Vol. 2
Srpsko geološko društvo, Beograd., 780-785.
https://hdl.handle.net/21.15107/rcub_grafar_1644

Đurić U, Pejić M, Marjanović M, Đurić D, Krušić J. Monitoring of erosion in the area of Đabolja Varoš: Project "Međa". in Knjiga apstrakata / 17. Kongres geologa Srbije, Vrnjačka Banja, 17-20. maj 2018. = Book of abstracts / 17th Serbian Geological Congress, Vrnjačka banja, Maz 17-20, 2018. Vol. 2. 2018;:780-785.
https://hdl.handle.net/21.15107/rcub_grafar_1644 .

Đurić, Uroš, Pejić, Marko, Marjanović, Miloš, Đurić, D., Krušić, Jelka, "Monitoring of erosion in the area of Đabolja Varoš: Project "Međa"" in Knjiga apstrakata / 17. Kongres geologa Srbije, Vrnjačka Banja, 17-20. maj 2018. = Book of abstracts / 17th Serbian Geological Congress, Vrnjačka banja, Maz 17-20, 2018. Vol. 2 (2018):780-785,
https://hdl.handle.net/21.15107/rcub_grafar_1644 .

TY  - JOUR
AU  - Marjanović, Miloš
AU  - Krautblatter, Michael
AU  - Abolmasov, Biljana
AU  - Đurić, Uroš
AU  - Sandić, Cvjetko
AU  - Nikolić, Velizar
PY  - 2018
UR  - https://grafar.grf.bg.ac.rs/handle/123456789/951
AB  - This paper focuses on modeling rainfall-induced massive landsliding in the Western Serbia in the 2001-2014 period. The motivation for conducting the study was the rainfall-induced flooding and landsliding that took place across most of the Serbia and Bosnia and Herzegovina in May 2014, and had devastating effects, including human casualties, and destruction of natural and urban environment. In the first part of the study, the general analysis was conducted. It includes a wide area (70,000 km(2)), wherein spatial rainfall patterns were identified using the monthly rainfall data from the 2001-2014. Areas that have higher monthly precipitation than the baseline monthly rainfall (1961-90) were outlined. One location within these zones was chosen as critical Loznica in Western Serbia. The area of Loznica was further examined: comparison between local daily rainfall and local landslide events recorded in 2001-2014; correlation between specific rainfall conditions, i.e. cumulative rainfall for different time windows, and the landsliding events in the specified period; identification of additional non-reported rainfall events that were potentially responsible for landsliding; analyses of the rainfall thresholds and temporal rainfall distribution. The Decision Tree algorithm was used to identify rainfall conditions that triggered landslides in the specified period. It was hypothesized that short-term rainfall has less influence on massive landsliding than the mid/long-term rainfall. Unlike other black-box techniques, Decision Tree-based modeling gives a good insight into the thresholding process. Namely, it was possible to follow the Decision Tree structure and reconstruct the critical cumulative rainfall distribution and thresholds that have led to landsliding. The main findings suggest that a high-yield mid-term rainfall (2 and 3-day rainfall) are the most important for massive landsliding, while long-term cumulative rainfall (30-day) has some additional influence in the case of Loznica. The upper threshold values extracted from the original, and appended synthetic rainfall events were about 30 mm for 2- and 3-day rainfall, and 140 mm for 30-day rainfall, which is in agreement with the evidence of the May 2014 event. It is thereby shown how proposed approach can be used preliminarily in the case of rainfall/landslide data scarcity for rough threshold estimation and extrapolation. However, limitations regarding utilization of such data must be accounted for.
PB  - Elsevier B.V.
T2  - Engineering Geology
T1  - The rainfall-induced landsliding in Western Serbia: A temporal prediction approach using Decision Tree technique
EP  - 159
SP  - 147
VL  - 232
DO  - 10.1016/j.enggeo.2017.11.021
ER  - 

@article{
author = "Marjanović, Miloš and Krautblatter, Michael and Abolmasov, Biljana and Đurić, Uroš and Sandić, Cvjetko and Nikolić, Velizar",
year = "2018",
abstract = "This paper focuses on modeling rainfall-induced massive landsliding in the Western Serbia in the 2001-2014 period. The motivation for conducting the study was the rainfall-induced flooding and landsliding that took place across most of the Serbia and Bosnia and Herzegovina in May 2014, and had devastating effects, including human casualties, and destruction of natural and urban environment. In the first part of the study, the general analysis was conducted. It includes a wide area (70,000 km(2)), wherein spatial rainfall patterns were identified using the monthly rainfall data from the 2001-2014. Areas that have higher monthly precipitation than the baseline monthly rainfall (1961-90) were outlined. One location within these zones was chosen as critical Loznica in Western Serbia. The area of Loznica was further examined: comparison between local daily rainfall and local landslide events recorded in 2001-2014; correlation between specific rainfall conditions, i.e. cumulative rainfall for different time windows, and the landsliding events in the specified period; identification of additional non-reported rainfall events that were potentially responsible for landsliding; analyses of the rainfall thresholds and temporal rainfall distribution. The Decision Tree algorithm was used to identify rainfall conditions that triggered landslides in the specified period. It was hypothesized that short-term rainfall has less influence on massive landsliding than the mid/long-term rainfall. Unlike other black-box techniques, Decision Tree-based modeling gives a good insight into the thresholding process. Namely, it was possible to follow the Decision Tree structure and reconstruct the critical cumulative rainfall distribution and thresholds that have led to landsliding. The main findings suggest that a high-yield mid-term rainfall (2 and 3-day rainfall) are the most important for massive landsliding, while long-term cumulative rainfall (30-day) has some additional influence in the case of Loznica. The upper threshold values extracted from the original, and appended synthetic rainfall events were about 30 mm for 2- and 3-day rainfall, and 140 mm for 30-day rainfall, which is in agreement with the evidence of the May 2014 event. It is thereby shown how proposed approach can be used preliminarily in the case of rainfall/landslide data scarcity for rough threshold estimation and extrapolation. However, limitations regarding utilization of such data must be accounted for.",
publisher = "Elsevier B.V.",
journal = "Engineering Geology",
title = "The rainfall-induced landsliding in Western Serbia: A temporal prediction approach using Decision Tree technique",
pages = "159-147",
volume = "232",
doi = "10.1016/j.enggeo.2017.11.021"
}

Marjanović, M., Krautblatter, M., Abolmasov, B., Đurić, U., Sandić, C.,& Nikolić, V.. (2018). The rainfall-induced landsliding in Western Serbia: A temporal prediction approach using Decision Tree technique. in Engineering Geology
Elsevier B.V.., 232, 147-159.
https://doi.org/10.1016/j.enggeo.2017.11.021

Marjanović M, Krautblatter M, Abolmasov B, Đurić U, Sandić C, Nikolić V. The rainfall-induced landsliding in Western Serbia: A temporal prediction approach using Decision Tree technique. in Engineering Geology. 2018;232:147-159.
doi:10.1016/j.enggeo.2017.11.021 .

Marjanović, Miloš, Krautblatter, Michael, Abolmasov, Biljana, Đurić, Uroš, Sandić, Cvjetko, Nikolić, Velizar, "The rainfall-induced landsliding in Western Serbia: A temporal prediction approach using Decision Tree technique" in Engineering Geology, 232 (2018):147-159,
https://doi.org/10.1016/j.enggeo.2017.11.021 . .

TY  - CONF
AU  - Abolmasov, Biljana
AU  - Marjanović, Miloš
AU  - Milenković, Svetozar
AU  - Pejić, Marko
AU  - Berisavljević, Zoran
PY  - 2018
UR  - https://grafar.grf.bg.ac.rs/handle/123456789/3031
AB  - The section of E75 motorway under construction was subjected to simulation of potential rockfall hazard. 3D point-cloud surface model of the rock slope, obtained by a combination of LiDAR and UAV techniques, was used for mapping of discontinuities, their orientation and spacing. These were inputs for appropriate slope stability analyses, which were further used do delineate potential depletion zones or rockfall block sources. Once delineated, source zones were used to simulate 3D rock trajectories over 3D surface slope model, for various block sizes. All trajectories were compared and evaluated for their potential impact on the viaduct setting, based on their spatial propagation, kinetic energies and forces, bouncing heights etc. Finally, according preventive measures for rockfall hazard mitigation were proposed.
PB  - Willey Ernst and Sons
C3  - Proceedings of the 16th Danube-European Conference on Geotechnical Engineering-Geotechnical hazards and risks: Experiences and practices, Skopje, Republic of Macedonia
T1  - Rockfall simulation on a rock slope along E75 road at km 890+725 to 891+093
VL  - 1
DO  - https://doi.org/10.1002/cepa.682
ER  - 

@conference{
author = "Abolmasov, Biljana and Marjanović, Miloš and Milenković, Svetozar and Pejić, Marko and Berisavljević, Zoran",
year = "2018",
abstract = "The section of E75 motorway under construction was subjected to simulation of potential rockfall hazard. 3D point-cloud surface model of the rock slope, obtained by a combination of LiDAR and UAV techniques, was used for mapping of discontinuities, their orientation and spacing. These were inputs for appropriate slope stability analyses, which were further used do delineate potential depletion zones or rockfall block sources. Once delineated, source zones were used to simulate 3D rock trajectories over 3D surface slope model, for various block sizes. All trajectories were compared and evaluated for their potential impact on the viaduct setting, based on their spatial propagation, kinetic energies and forces, bouncing heights etc. Finally, according preventive measures for rockfall hazard mitigation were proposed.",
publisher = "Willey Ernst and Sons",
journal = "Proceedings of the 16th Danube-European Conference on Geotechnical Engineering-Geotechnical hazards and risks: Experiences and practices, Skopje, Republic of Macedonia",
title = "Rockfall simulation on a rock slope along E75 road at km 890+725 to 891+093",
volume = "1",
doi = "https://doi.org/10.1002/cepa.682"
}

Abolmasov, B., Marjanović, M., Milenković, S., Pejić, M.,& Berisavljević, Z.. (2018). Rockfall simulation on a rock slope along E75 road at km 890+725 to 891+093. in Proceedings of the 16th Danube-European Conference on Geotechnical Engineering-Geotechnical hazards and risks: Experiences and practices, Skopje, Republic of Macedonia
Willey Ernst and Sons., 1.
https://doi.org/https://doi.org/10.1002/cepa.682

Abolmasov B, Marjanović M, Milenković S, Pejić M, Berisavljević Z. Rockfall simulation on a rock slope along E75 road at km 890+725 to 891+093. in Proceedings of the 16th Danube-European Conference on Geotechnical Engineering-Geotechnical hazards and risks: Experiences and practices, Skopje, Republic of Macedonia. 2018;1.
doi:https://doi.org/10.1002/cepa.682 .

Abolmasov, Biljana, Marjanović, Miloš, Milenković, Svetozar, Pejić, Marko, Berisavljević, Zoran, "Rockfall simulation on a rock slope along E75 road at km 890+725 to 891+093" in Proceedings of the 16th Danube-European Conference on Geotechnical Engineering-Geotechnical hazards and risks: Experiences and practices, Skopje, Republic of Macedonia, 1 (2018),
https://doi.org/https://doi.org/10.1002/cepa.682 . .

TY  - CONF
AU  - Đurić, Uroš
AU  - Marjanović, Miloš
AU  - Abolmasov, Biljana
AU  - Radić, Zoran
AU  - Jelisavac, Branko
PY  - 2018
UR  - https://grafar.grf.bg.ac.rs/handle/123456789/1593
AB  - The Umka landslide is systematically investigated and one of the biggest inhabited landslides in Serbia. Landslide is active, with known sliding intensity (more or less) for last 50 years, while landslide is old couple of hundred years, and its genesis is related with evolution of Sava meanders. Although the landslide is known and occasionally mentioned in mass media, certain migration of population is evident, so besides permanent displacement from the landslide – some new housing objects are notices with permanent residents, even within the most active and most affected part of the landslide. According to previous research, a landslide is divided into three zones (blocks) that are different by sliding depth, dynamics and by slope morphology. The last object inventorying was performed during 1989–1990 by the Highway Institute from Belgrade when the map of the damaged objects (with the type of foundation, walls, and category of object) was created, local water system was mapped, while evaluation of population was performed by last known census data. Since the last inventorying was performed 25 years ago, and a landslide is still not stabilized although project documentation for stabilization exists from that period, the vulnerability of population is still actual while in some parts it is even more intensive which is a consequence of unplanned and illegal construction works during ’60 and ’70 of XIX century, when most of objecst were built (over 250 of them).Considering above, there was a need for inventtorying of all present building objects which are within the landslide cadaster border, so such that data can be easily compared with previous research. The base for the creating new inventorying sheet was surveying sheet from 1989. New sheet contains 11 groups of question: 1) Basic data about building object 2) Data about object construction 3) Data about object deformations 4) Data about object foundation 5) Data about household 6) Damage estimation 7) Emergency and temporary interventions 8) Recovery measures 9) Data about household water, surface and groundwaters 10) Sketch of object damage 11) Other comments. Previous inventorying didn’t include the question about householdand population working and life habits which is necessary data for the risk estimation. Inventorying was carried out from September to November 2017. and more than 360 objects were evidenced with more than 500 residents. Each object was photographed and located by the coordinate of the object central point with previously written or oral permission of the resident or object owner. More than 95% of object owners and residents gave the permission for the collecting the data, while there was a lot of objects that were abandoned and which was only evidenced from the outside by construction condition. Detailed results with following statistics will be presented after the data processing that will be done by the end of the 2018 year. Inventorying was performed within the project grant no. TR36009 that is financed by Ministry of education, science and technological development of the Republic of Serbia.
PB  - Srpsko geološko društvo, Beograd
C3  - Knjiga apstrakata / 17. Kongres geologa Srbije, Vrnjačka Banja, 17-20. maj 2018. = Book of abstracts / 17th Serbian Geological Congress, Vrnjačka banja, Maz 17-20, 2018. Vol. 2
T1  - Building objects and huseholds inventorying for the purpose of risk estimation on the Umka landslide near Belgrade
T1  - Evidentiranje građevinskih objekata i stanovništva za potrebe procene rizika od klizišta Umka kod Beograda
EP  - 669
SP  - 668
VL  - 2
UR  - https://hdl.handle.net/21.15107/rcub_grafar_1593
ER  - 

@conference{
author = "Đurić, Uroš and Marjanović, Miloš and Abolmasov, Biljana and Radić, Zoran and Jelisavac, Branko",
year = "2018",
abstract = "The Umka landslide is systematically investigated and one of the biggest inhabited landslides in Serbia. Landslide is active, with known sliding intensity (more or less) for last 50 years, while landslide is old couple of hundred years, and its genesis is related with evolution of Sava meanders. Although the landslide is known and occasionally mentioned in mass media, certain migration of population is evident, so besides permanent displacement from the landslide – some new housing objects are notices with permanent residents, even within the most active and most affected part of the landslide. According to previous research, a landslide is divided into three zones (blocks) that are different by sliding depth, dynamics and by slope morphology. The last object inventorying was performed during 1989–1990 by the Highway Institute from Belgrade when the map of the damaged objects (with the type of foundation, walls, and category of object) was created, local water system was mapped, while evaluation of population was performed by last known census data. Since the last inventorying was performed 25 years ago, and a landslide is still not stabilized although project documentation for stabilization exists from that period, the vulnerability of population is still actual while in some parts it is even more intensive which is a consequence of unplanned and illegal construction works during ’60 and ’70 of XIX century, when most of objecst were built (over 250 of them).Considering above, there was a need for inventtorying of all present building objects which are within the landslide cadaster border, so such that data can be easily compared with previous research. The base for the creating new inventorying sheet was surveying sheet from 1989. New sheet contains 11 groups of question: 1) Basic data about building object 2) Data about object construction 3) Data about object deformations 4) Data about object foundation 5) Data about household 6) Damage estimation 7) Emergency and temporary interventions 8) Recovery measures 9) Data about household water, surface and groundwaters 10) Sketch of object damage 11) Other comments. Previous inventorying didn’t include the question about householdand population working and life habits which is necessary data for the risk estimation. Inventorying was carried out from September to November 2017. and more than 360 objects were evidenced with more than 500 residents. Each object was photographed and located by the coordinate of the object central point with previously written or oral permission of the resident or object owner. More than 95% of object owners and residents gave the permission for the collecting the data, while there was a lot of objects that were abandoned and which was only evidenced from the outside by construction condition. Detailed results with following statistics will be presented after the data processing that will be done by the end of the 2018 year. Inventorying was performed within the project grant no. TR36009 that is financed by Ministry of education, science and technological development of the Republic of Serbia.",
publisher = "Srpsko geološko društvo, Beograd",
journal = "Knjiga apstrakata / 17. Kongres geologa Srbije, Vrnjačka Banja, 17-20. maj 2018. = Book of abstracts / 17th Serbian Geological Congress, Vrnjačka banja, Maz 17-20, 2018. Vol. 2",
title = "Building objects and huseholds inventorying for the purpose of risk estimation on the Umka landslide near Belgrade, Evidentiranje građevinskih objekata i stanovništva za potrebe procene rizika od klizišta Umka kod Beograda",
pages = "669-668",
volume = "2",
url = "https://hdl.handle.net/21.15107/rcub_grafar_1593"
}

Đurić, U., Marjanović, M., Abolmasov, B., Radić, Z.,& Jelisavac, B.. (2018). Building objects and huseholds inventorying for the purpose of risk estimation on the Umka landslide near Belgrade. in Knjiga apstrakata / 17. Kongres geologa Srbije, Vrnjačka Banja, 17-20. maj 2018. = Book of abstracts / 17th Serbian Geological Congress, Vrnjačka banja, Maz 17-20, 2018. Vol. 2
Srpsko geološko društvo, Beograd., 2, 668-669.
https://hdl.handle.net/21.15107/rcub_grafar_1593

Đurić U, Marjanović M, Abolmasov B, Radić Z, Jelisavac B. Building objects and huseholds inventorying for the purpose of risk estimation on the Umka landslide near Belgrade. in Knjiga apstrakata / 17. Kongres geologa Srbije, Vrnjačka Banja, 17-20. maj 2018. = Book of abstracts / 17th Serbian Geological Congress, Vrnjačka banja, Maz 17-20, 2018. Vol. 2. 2018;2:668-669.
https://hdl.handle.net/21.15107/rcub_grafar_1593 .

Đurić, Uroš, Marjanović, Miloš, Abolmasov, Biljana, Radić, Zoran, Jelisavac, Branko, "Building objects and huseholds inventorying for the purpose of risk estimation on the Umka landslide near Belgrade" in Knjiga apstrakata / 17. Kongres geologa Srbije, Vrnjačka Banja, 17-20. maj 2018. = Book of abstracts / 17th Serbian Geological Congress, Vrnjačka banja, Maz 17-20, 2018. Vol. 2, 2 (2018):668-669,
https://hdl.handle.net/21.15107/rcub_grafar_1593 .

TY  - JOUR
AU  - Krušić, Jelka
AU  - Marjanović, Miloš
AU  - Samardžić-Petrović, Mileva
AU  - Abolmasov, Biljana
AU  - Andrejev, Katarina
AU  - Miladinović, Aleksandar
PY  - 2017
UR  - https://grafar.grf.bg.ac.rs/handle/123456789/1084
T2  - Geofizika
T1  - Comparison of expert, deterministic and Machine Learning approach for landslide susceptibility assessment in Ljubovija Municipality, Serbia
EP  - 273
IS  - 2
SP  - 251
VL  - 34
DO  - 10.15233/gfz.2017.34.15
ER  - 

@article{
author = "Krušić, Jelka and Marjanović, Miloš and Samardžić-Petrović, Mileva and Abolmasov, Biljana and Andrejev, Katarina and Miladinović, Aleksandar",
year = "2017",
journal = "Geofizika",
title = "Comparison of expert, deterministic and Machine Learning approach for landslide susceptibility assessment in Ljubovija Municipality, Serbia",
pages = "273-251",
number = "2",
volume = "34",
doi = "10.15233/gfz.2017.34.15"
}

Krušić, J., Marjanović, M., Samardžić-Petrović, M., Abolmasov, B., Andrejev, K.,& Miladinović, A.. (2017). Comparison of expert, deterministic and Machine Learning approach for landslide susceptibility assessment in Ljubovija Municipality, Serbia. in Geofizika, 34(2), 251-273.
https://doi.org/10.15233/gfz.2017.34.15

Krušić J, Marjanović M, Samardžić-Petrović M, Abolmasov B, Andrejev K, Miladinović A. Comparison of expert, deterministic and Machine Learning approach for landslide susceptibility assessment in Ljubovija Municipality, Serbia. in Geofizika. 2017;34(2):251-273.
doi:10.15233/gfz.2017.34.15 .

Krušić, Jelka, Marjanović, Miloš, Samardžić-Petrović, Mileva, Abolmasov, Biljana, Andrejev, Katarina, Miladinović, Aleksandar, "Comparison of expert, deterministic and Machine Learning approach for landslide susceptibility assessment in Ljubovija Municipality, Serbia" in Geofizika, 34, no. 2 (2017):251-273,
https://doi.org/10.15233/gfz.2017.34.15 . .

TY  - CONF
AU  - Andrejev, Katarina
AU  - Krušić, Jelka
AU  - Đurić, Uroš
AU  - Marjanović, Miloš
AU  - Abolmasov, Biljana
PY  - 2017
UR  - https://grafar.grf.bg.ac.rs/handle/123456789/896
AB  - This paper represents a relative landslide risk assessment of the City of Valjevo in Western Serbia. After the extreme rainfall during the May 2014, many new landslides were triggered, and Valjevo was one of the most affected areas in Serbia. The modeling was preceded by the data selection, and included ranging and preprocessing of the conditioning factors. The following eight factors were chosen as representative: stream distance, slope, lithology, elevation, distance from hydrogeological borders, land use, erodibility and aspect. Landslide susceptibility analysis was completed using the Analytical Hierarchy Process (AHP) multi-criteria method. Validation was performed by cross-referencing with an existing landslide inventory, which was made by field mapping and interpretation of satellite images. Finally, the relative risk was determined for the City of Valjevo by using a realistic population distribution model as a source for elements at risk. The results show the distribution of risk and suggest that 20% of the inhabited area falls into the high risk class, but this encompasses less than 5% of the total population.
C3  - Advancing Culture of Living With Landslides, Vol 5: Landslides in Different Environments
T1  - Relative Landslide Risk Assessment for the City of Valjevo
EP  - 533
SP  - 525
DO  - 10.1007/978-3-319-53483-1_62
ER  - 

@conference{
author = "Andrejev, Katarina and Krušić, Jelka and Đurić, Uroš and Marjanović, Miloš and Abolmasov, Biljana",
year = "2017",
abstract = "This paper represents a relative landslide risk assessment of the City of Valjevo in Western Serbia. After the extreme rainfall during the May 2014, many new landslides were triggered, and Valjevo was one of the most affected areas in Serbia. The modeling was preceded by the data selection, and included ranging and preprocessing of the conditioning factors. The following eight factors were chosen as representative: stream distance, slope, lithology, elevation, distance from hydrogeological borders, land use, erodibility and aspect. Landslide susceptibility analysis was completed using the Analytical Hierarchy Process (AHP) multi-criteria method. Validation was performed by cross-referencing with an existing landslide inventory, which was made by field mapping and interpretation of satellite images. Finally, the relative risk was determined for the City of Valjevo by using a realistic population distribution model as a source for elements at risk. The results show the distribution of risk and suggest that 20% of the inhabited area falls into the high risk class, but this encompasses less than 5% of the total population.",
journal = "Advancing Culture of Living With Landslides, Vol 5: Landslides in Different Environments",
title = "Relative Landslide Risk Assessment for the City of Valjevo",
pages = "533-525",
doi = "10.1007/978-3-319-53483-1_62"
}

Andrejev, K., Krušić, J., Đurić, U., Marjanović, M.,& Abolmasov, B.. (2017). Relative Landslide Risk Assessment for the City of Valjevo. in Advancing Culture of Living With Landslides, Vol 5: Landslides in Different Environments, 525-533.
https://doi.org/10.1007/978-3-319-53483-1_62

Andrejev K, Krušić J, Đurić U, Marjanović M, Abolmasov B. Relative Landslide Risk Assessment for the City of Valjevo. in Advancing Culture of Living With Landslides, Vol 5: Landslides in Different Environments. 2017;:525-533.
doi:10.1007/978-3-319-53483-1_62 .

Andrejev, Katarina, Krušić, Jelka, Đurić, Uroš, Marjanović, Miloš, Abolmasov, Biljana, "Relative Landslide Risk Assessment for the City of Valjevo" in Advancing Culture of Living With Landslides, Vol 5: Landslides in Different Environments (2017):525-533,
https://doi.org/10.1007/978-3-319-53483-1_62 . .

TY  - CONF
AU  - Abolmasov, Biljana
AU  - Marjanović, Miloš
AU  - Milenković, Svetozar
AU  - Đurić, Uroš
AU  - Jelisavac, Branko
AU  - Pejić, Marko
PY  - 2017
UR  - https://grafar.grf.bg.ac.rs/handle/123456789/884
AB  - The IPL project No 181 titled "Study of slow moving landslide Umka near Belgrade" started in November 2012. The study area is located on the right bank of Sava River, 25 km south west of Belgrade, Serbia. The basic objective of the Project was to enable the analysis, correlation and synthesis of data obtained from various phases of investigation of Umka landslide after 35 years of research. Apart from this, the analysis of data from monitoring conducted during certain phases of research was compared with data from automated GNSS monitoring over the last six years, although during numerous investigations various research methods were used for research and monitoring. The project was focused on: analysis of previous detail site investigations and field instrumentation from 1990-2005, analysis of aerial photos and orthophoto images from 1957-2010, analysis of automated GNSS monitoring results from 2010 to end of the Project and analysis of precipitation and levels of the Sava River. Project beneficiaries are local community and local and regional authorities. In this paper we will present results of the proposed project targets performed by Project participants.
C3  - Advancing Culture of Living With Landslides, Vol 1: Isdr-Icl Sendai Partnerships 2015-2025
T1  - Study of Slow Moving Landslide Umka Near Belgrade, Serbia (IPL-181)
EP  - 427
SP  - 419
DO  - 10.1007/978-3-319-59469-9_37
ER  - 

@conference{
author = "Abolmasov, Biljana and Marjanović, Miloš and Milenković, Svetozar and Đurić, Uroš and Jelisavac, Branko and Pejić, Marko",
year = "2017",
abstract = "The IPL project No 181 titled "Study of slow moving landslide Umka near Belgrade" started in November 2012. The study area is located on the right bank of Sava River, 25 km south west of Belgrade, Serbia. The basic objective of the Project was to enable the analysis, correlation and synthesis of data obtained from various phases of investigation of Umka landslide after 35 years of research. Apart from this, the analysis of data from monitoring conducted during certain phases of research was compared with data from automated GNSS monitoring over the last six years, although during numerous investigations various research methods were used for research and monitoring. The project was focused on: analysis of previous detail site investigations and field instrumentation from 1990-2005, analysis of aerial photos and orthophoto images from 1957-2010, analysis of automated GNSS monitoring results from 2010 to end of the Project and analysis of precipitation and levels of the Sava River. Project beneficiaries are local community and local and regional authorities. In this paper we will present results of the proposed project targets performed by Project participants.",
journal = "Advancing Culture of Living With Landslides, Vol 1: Isdr-Icl Sendai Partnerships 2015-2025",
title = "Study of Slow Moving Landslide Umka Near Belgrade, Serbia (IPL-181)",
pages = "427-419",
doi = "10.1007/978-3-319-59469-9_37"
}

Abolmasov, B., Marjanović, M., Milenković, S., Đurić, U., Jelisavac, B.,& Pejić, M.. (2017). Study of Slow Moving Landslide Umka Near Belgrade, Serbia (IPL-181). in Advancing Culture of Living With Landslides, Vol 1: Isdr-Icl Sendai Partnerships 2015-2025, 419-427.
https://doi.org/10.1007/978-3-319-59469-9_37

Abolmasov B, Marjanović M, Milenković S, Đurić U, Jelisavac B, Pejić M. Study of Slow Moving Landslide Umka Near Belgrade, Serbia (IPL-181). in Advancing Culture of Living With Landslides, Vol 1: Isdr-Icl Sendai Partnerships 2015-2025. 2017;:419-427.
doi:10.1007/978-3-319-59469-9_37 .

Abolmasov, Biljana, Marjanović, Miloš, Milenković, Svetozar, Đurić, Uroš, Jelisavac, Branko, Pejić, Marko, "Study of Slow Moving Landslide Umka Near Belgrade, Serbia (IPL-181)" in Advancing Culture of Living With Landslides, Vol 1: Isdr-Icl Sendai Partnerships 2015-2025 (2017):419-427,
https://doi.org/10.1007/978-3-319-59469-9_37 . .

TY  - JOUR
AU  - Abolmasov, Biljana
AU  - Krušić, Jelka
AU  - Andrejev, Katarina
AU  - Marjanović, Miloš
AU  - Stanković, Ranka
AU  - Đurić, Uroš
PY  - 2017
UR  - https://grafar.grf.bg.ac.rs/handle/123456789/830
AB  - This paper is an example of landslide susceptibility assessment in Krupanj municipality in western Serbia, using two different multicriteria methods: Analytical Hierarchy Process (AHP) and Weight of Evidence (WoE). AHP is based on quantified expert judgement on the individual importance of conditioning factors, as geological, morphological and environmental proxies for landsliding. WoE is data-driven, i.e. it uses conditional probability of landslide occurrence to grade conditioning factors by their importance. Validation was performed by cross-referencing with an existing landslide inventory, which was made by field mapping and interpretation of satellite images. Both models have relatively good performance, but WoE has slightly better validation parameters. These results are a solid background for general overview of the landslide susceptibility distribution at municipality scale, and can be successfully used for further landslide risk assessment or large scale planning.
AB  - U radu su prikazani rezultati dve metode procene podložnosti terena na kliženje: višekriterijumske AHP (Analytical Hierarchy Process) metode i metode uslovne verovatnoće, odnosno metode težine dokaza WoE (Weight of Evidence) primenjene na područje opštine Krupanj u zapadnoj Srbiji. Validacija dobijenih rezultata procene izvršena je za svaki dobijeni model poređenjem sa realnim podacima evidentiranih pojava nestabilnosti dobijenih terenskim kartiranjem i analizom satelitskih snimaka visoke rezolucije. Nakon toga izvršena je uporedna analiza dobijenih rezultata.Oba modela pokazuju zadovoljavajuću tačnost, gde je statistička metoda dala nešto preciznije rezultate. Rezultati procene podložnosti predstavljaju dobru osnovu za procenu relativnog rizika od procesa kliženja i podlogu za izradu planskih dokumenata opštine Krupanj.
PB  - Udruženje inženjera građevinarstva, geotehnike, arhitekture i urbanista "Izgradnja", Beograd
T2  - Izgradnja
T1  - Application of AHP and WoE methods for landslide susceptibility assessment on Krupanj municipality
T1  - Primena AHP i WoE metode u proceni podložnosti terena na kliženje za područje opštine Krupanj
EP  - 246
IS  - 7-10
SP  - 239
UR  - https://hdl.handle.net/21.15107/rcub_grafar_830
ER  - 

@article{
author = "Abolmasov, Biljana and Krušić, Jelka and Andrejev, Katarina and Marjanović, Miloš and Stanković, Ranka and Đurić, Uroš",
year = "2017",
abstract = "This paper is an example of landslide susceptibility assessment in Krupanj municipality in western Serbia, using two different multicriteria methods: Analytical Hierarchy Process (AHP) and Weight of Evidence (WoE). AHP is based on quantified expert judgement on the individual importance of conditioning factors, as geological, morphological and environmental proxies for landsliding. WoE is data-driven, i.e. it uses conditional probability of landslide occurrence to grade conditioning factors by their importance. Validation was performed by cross-referencing with an existing landslide inventory, which was made by field mapping and interpretation of satellite images. Both models have relatively good performance, but WoE has slightly better validation parameters. These results are a solid background for general overview of the landslide susceptibility distribution at municipality scale, and can be successfully used for further landslide risk assessment or large scale planning., U radu su prikazani rezultati dve metode procene podložnosti terena na kliženje: višekriterijumske AHP (Analytical Hierarchy Process) metode i metode uslovne verovatnoće, odnosno metode težine dokaza WoE (Weight of Evidence) primenjene na područje opštine Krupanj u zapadnoj Srbiji. Validacija dobijenih rezultata procene izvršena je za svaki dobijeni model poređenjem sa realnim podacima evidentiranih pojava nestabilnosti dobijenih terenskim kartiranjem i analizom satelitskih snimaka visoke rezolucije. Nakon toga izvršena je uporedna analiza dobijenih rezultata.Oba modela pokazuju zadovoljavajuću tačnost, gde je statistička metoda dala nešto preciznije rezultate. Rezultati procene podložnosti predstavljaju dobru osnovu za procenu relativnog rizika od procesa kliženja i podlogu za izradu planskih dokumenata opštine Krupanj.",
publisher = "Udruženje inženjera građevinarstva, geotehnike, arhitekture i urbanista "Izgradnja", Beograd",
journal = "Izgradnja",
title = "Application of AHP and WoE methods for landslide susceptibility assessment on Krupanj municipality, Primena AHP i WoE metode u proceni podložnosti terena na kliženje za područje opštine Krupanj",
pages = "246-239",
number = "7-10",
url = "https://hdl.handle.net/21.15107/rcub_grafar_830"
}

Abolmasov, B., Krušić, J., Andrejev, K., Marjanović, M., Stanković, R.,& Đurić, U.. (2017). Application of AHP and WoE methods for landslide susceptibility assessment on Krupanj municipality. in Izgradnja
Udruženje inženjera građevinarstva, geotehnike, arhitekture i urbanista "Izgradnja", Beograd.(7-10), 239-246.
https://hdl.handle.net/21.15107/rcub_grafar_830

Abolmasov B, Krušić J, Andrejev K, Marjanović M, Stanković R, Đurić U. Application of AHP and WoE methods for landslide susceptibility assessment on Krupanj municipality. in Izgradnja. 2017;(7-10):239-246.
https://hdl.handle.net/21.15107/rcub_grafar_830 .

Abolmasov, Biljana, Krušić, Jelka, Andrejev, Katarina, Marjanović, Miloš, Stanković, Ranka, Đurić, Uroš, "Application of AHP and WoE methods for landslide susceptibility assessment on Krupanj municipality" in Izgradnja, no. 7-10 (2017):239-246,
https://hdl.handle.net/21.15107/rcub_grafar_830 .