TY  - JOUR
AU  - Milanović, Slobodan
AU  - Marković, Nenad
AU  - Pamučar, Dragan
AU  - Gigović, Ljubomir
AU  - Kostić, Pavle
AU  - Milanović, Slađan D.
PY  - 2021
UR  - https://omorika.sfb.bg.ac.rs/handle/123456789/1211
AB  - Forest fire risk has increased globally during the previous decades. The Mediterranean region is traditionally the most at risk in Europe, but continental countries like Serbia have experienced significant economic and ecological losses due to forest fires. To prevent damage to forests and infrastructure, alongside other societal losses, it is necessary to create an effective protection system against fire, which minimizes the harmful effects. Forest fire probability mapping, as one of the basic tools in risk management, allows the allocation of resources for fire suppression, within a fire season, from zones with a lower risk to those under higher threat. Logistic regression (LR) has been used as a standard procedure in forest fire probability mapping, but in the last decade, machine learning methods such as fandom forest (RF) have become more frequent. The main goals in this study were to (i) determine the main explanatory variables for forest fire occurrence for both models, LR and RF, and (ii) map the probability of forest fire occurrence in Eastern Serbia based on LR and RF. The most important variable was drought code, followed by different anthropogenic features depending on the type of the model. The RF models demonstrated better overall predictive ability than LR models. The map produced may increase firefighting efficiency due to the early detection of forest fire and enable resources to be allocated in the eastern part of Serbia, which covers more than one-third of the country's area.
T2  - Forests
T1  - Forest Fire Probability Mapping in Eastern Serbia: Logistic Regression versus Random Forest Method
IS  - 1
VL  - 12
DO  - 10.3390/f12010005
UR  - conv_1525
ER  - 

@article{
author = "Milanović, Slobodan and Marković, Nenad and Pamučar, Dragan and Gigović, Ljubomir and Kostić, Pavle and Milanović, Slađan D.",
year = "2021",
abstract = "Forest fire risk has increased globally during the previous decades. The Mediterranean region is traditionally the most at risk in Europe, but continental countries like Serbia have experienced significant economic and ecological losses due to forest fires. To prevent damage to forests and infrastructure, alongside other societal losses, it is necessary to create an effective protection system against fire, which minimizes the harmful effects. Forest fire probability mapping, as one of the basic tools in risk management, allows the allocation of resources for fire suppression, within a fire season, from zones with a lower risk to those under higher threat. Logistic regression (LR) has been used as a standard procedure in forest fire probability mapping, but in the last decade, machine learning methods such as fandom forest (RF) have become more frequent. The main goals in this study were to (i) determine the main explanatory variables for forest fire occurrence for both models, LR and RF, and (ii) map the probability of forest fire occurrence in Eastern Serbia based on LR and RF. The most important variable was drought code, followed by different anthropogenic features depending on the type of the model. The RF models demonstrated better overall predictive ability than LR models. The map produced may increase firefighting efficiency due to the early detection of forest fire and enable resources to be allocated in the eastern part of Serbia, which covers more than one-third of the country's area.",
journal = "Forests",
title = "Forest Fire Probability Mapping in Eastern Serbia: Logistic Regression versus Random Forest Method",
number = "1",
volume = "12",
doi = "10.3390/f12010005",
url = "conv_1525"
}

Milanović, S., Marković, N., Pamučar, D., Gigović, L., Kostić, P.,& Milanović, S. D.. (2021). Forest Fire Probability Mapping in Eastern Serbia: Logistic Regression versus Random Forest Method. in Forests, 12(1).
https://doi.org/10.3390/f12010005
conv_1525

Milanović S, Marković N, Pamučar D, Gigović L, Kostić P, Milanović SD. Forest Fire Probability Mapping in Eastern Serbia: Logistic Regression versus Random Forest Method. in Forests. 2021;12(1).
doi:10.3390/f12010005
conv_1525 .

Milanović, Slobodan, Marković, Nenad, Pamučar, Dragan, Gigović, Ljubomir, Kostić, Pavle, Milanović, Slađan D., "Forest Fire Probability Mapping in Eastern Serbia: Logistic Regression versus Random Forest Method" in Forests, 12, no. 1 (2021),
https://doi.org/10.3390/f12010005 .,
conv_1525 .

TY  - JOUR
AU  - Brovkina, Olga
AU  - Stojanović, Marko
AU  - Milanović, Slobodan
AU  - Latypov, Iscander
AU  - Marković, Nenad
AU  - Cienciala, Emil
PY  - 2020
UR  - https://omorika.sfb.bg.ac.rs/handle/123456789/1150
AB  - This study aims to improving long-term post-fire environment assessment. It proposes a method for monitoring fire impact using Sentinel-2 satellite data by combining spectral and textural features of land cover types inside a post-fire study sites. Specific objectives were to 1) test stability of the burnt area index for Sentinel-2 (BAIS2) for identification of burn in study sites, 2) investigate the optimal feature combination for mapping land covers inside study sites, and 3) assess and analyse dynamic in land covers of study sites. BAIS2 was shown independent on date acquisition of satellite images to distinguish forest burn from other land covers over the analysed May-September vegetation period. Texture of study site improved the classification results. The most accurate classification method for identification of study sites land covers (with 0.84 Kappa coefficient and 0.86 overall accuracy) was based on combination of Sentinel-2 bands, BAIS2, and texture by Fourier transform. Analysis of vegetation recovery within the study sites demonstrated different recovery rates. Natural regeneration of pine was not observed, during three to six years of observations following fire events. The proposed method and findings can support planning of forest management measures needed to effectively restore forest cover.
T2  - Geomatics Natural Hazards & Risk
T1  - Monitoring of post-fire forest scars in Serbia based on satellite Sentinel-2 data
EP  - 2339
IS  - 1
SP  - 2315
VL  - 11
DO  - 10.1080/19475705.2020.1836037
UR  - conv_1511
ER  - 

@article{
author = "Brovkina, Olga and Stojanović, Marko and Milanović, Slobodan and Latypov, Iscander and Marković, Nenad and Cienciala, Emil",
year = "2020",
abstract = "This study aims to improving long-term post-fire environment assessment. It proposes a method for monitoring fire impact using Sentinel-2 satellite data by combining spectral and textural features of land cover types inside a post-fire study sites. Specific objectives were to 1) test stability of the burnt area index for Sentinel-2 (BAIS2) for identification of burn in study sites, 2) investigate the optimal feature combination for mapping land covers inside study sites, and 3) assess and analyse dynamic in land covers of study sites. BAIS2 was shown independent on date acquisition of satellite images to distinguish forest burn from other land covers over the analysed May-September vegetation period. Texture of study site improved the classification results. The most accurate classification method for identification of study sites land covers (with 0.84 Kappa coefficient and 0.86 overall accuracy) was based on combination of Sentinel-2 bands, BAIS2, and texture by Fourier transform. Analysis of vegetation recovery within the study sites demonstrated different recovery rates. Natural regeneration of pine was not observed, during three to six years of observations following fire events. The proposed method and findings can support planning of forest management measures needed to effectively restore forest cover.",
journal = "Geomatics Natural Hazards & Risk",
title = "Monitoring of post-fire forest scars in Serbia based on satellite Sentinel-2 data",
pages = "2339-2315",
number = "1",
volume = "11",
doi = "10.1080/19475705.2020.1836037",
url = "conv_1511"
}

Brovkina, O., Stojanović, M., Milanović, S., Latypov, I., Marković, N.,& Cienciala, E.. (2020). Monitoring of post-fire forest scars in Serbia based on satellite Sentinel-2 data. in Geomatics Natural Hazards & Risk, 11(1), 2315-2339.
https://doi.org/10.1080/19475705.2020.1836037
conv_1511

Brovkina O, Stojanović M, Milanović S, Latypov I, Marković N, Cienciala E. Monitoring of post-fire forest scars in Serbia based on satellite Sentinel-2 data. in Geomatics Natural Hazards & Risk. 2020;11(1):2315-2339.
doi:10.1080/19475705.2020.1836037
conv_1511 .

Brovkina, Olga, Stojanović, Marko, Milanović, Slobodan, Latypov, Iscander, Marković, Nenad, Cienciala, Emil, "Monitoring of post-fire forest scars in Serbia based on satellite Sentinel-2 data" in Geomatics Natural Hazards & Risk, 11, no. 1 (2020):2315-2339,
https://doi.org/10.1080/19475705.2020.1836037 .,
conv_1511 .

TY  - JOUR
AU  - Mihajlović, Ljubodrag
AU  - Marković, Nenad
AU  - Milanović, Slobodan
PY  - 2005
UR  - https://omorika.sfb.bg.ac.rs/handle/123456789/165
AB  - Geografski informacioni sistem (GIS) predstavlja celinu, koju čine baza podataka i grafički objekti. Ova dva segmenta su međusobno povezana, tako da svakom pojedinačnom grafičkom objektu odgovara zapis u bazi podataka. Upravljanje i manipulacija velikim brojem raznolikih podataka, vezanih za prostor i vreme, kao i prostorna podela u šumarstvu, učinili su da je GIS odavno postao sastavni deo prakse i nauke u razvijenim zemljama. Aktuelna gradacija gubara, koja je zahvatila vise stotina hiljada hektara šuma Srbije sa različitim stepenom defolijacije tokom 2004. i 2005. godine, potvrđuje neophodnost uvođenja GIS-a u oblasti zaštite šuma. Primena ovog sistema u prvoj fazi bi se ograničila na praćenje gradacije i olakšavanje poslova na saniranju njenih posledica.
AB  - Geographic Information System (GIS) is a combination of a database and graphical objects organized together so that every object has its record in a database. Management and manipulation with large number of different data related to the space and time made GIS the standard in forestry science and practice in the developed countries. Actual gradation of gypsy moth in Serbia that has spread over hundred thousands of hectares of forests, manifested in different degree of defoliation throughout 2004 and 2005, proves the necessities of GIS introduction in forest protection. In its first phase GIS application will be limited to tracking and pursuing gypsy moth gradation and facilitation of reclamation efforts.
PB  - Univerzitet u Novom Sadu - Poljoprivredni fakultet - Departman za zaštitu bilja i životne sredine "dr Pavla Vukasovića", Novi Sad
T2  - Biljni lekar
T1  - Potrebe i mogućnosti primene geografskog informacionog sistema u zaštiti šuma od gubara
T1  - Need for and application of geographic information system in forest protection against gypsy moth
EP  - 631
IS  - 6
SP  - 626
VL  - 33
UR  - conv_597
ER  - 

@article{
author = "Mihajlović, Ljubodrag and Marković, Nenad and Milanović, Slobodan",
year = "2005",
abstract = "Geografski informacioni sistem (GIS) predstavlja celinu, koju čine baza podataka i grafički objekti. Ova dva segmenta su međusobno povezana, tako da svakom pojedinačnom grafičkom objektu odgovara zapis u bazi podataka. Upravljanje i manipulacija velikim brojem raznolikih podataka, vezanih za prostor i vreme, kao i prostorna podela u šumarstvu, učinili su da je GIS odavno postao sastavni deo prakse i nauke u razvijenim zemljama. Aktuelna gradacija gubara, koja je zahvatila vise stotina hiljada hektara šuma Srbije sa različitim stepenom defolijacije tokom 2004. i 2005. godine, potvrđuje neophodnost uvođenja GIS-a u oblasti zaštite šuma. Primena ovog sistema u prvoj fazi bi se ograničila na praćenje gradacije i olakšavanje poslova na saniranju njenih posledica., Geographic Information System (GIS) is a combination of a database and graphical objects organized together so that every object has its record in a database. Management and manipulation with large number of different data related to the space and time made GIS the standard in forestry science and practice in the developed countries. Actual gradation of gypsy moth in Serbia that has spread over hundred thousands of hectares of forests, manifested in different degree of defoliation throughout 2004 and 2005, proves the necessities of GIS introduction in forest protection. In its first phase GIS application will be limited to tracking and pursuing gypsy moth gradation and facilitation of reclamation efforts.",
publisher = "Univerzitet u Novom Sadu - Poljoprivredni fakultet - Departman za zaštitu bilja i životne sredine "dr Pavla Vukasovića", Novi Sad",
journal = "Biljni lekar",
title = "Potrebe i mogućnosti primene geografskog informacionog sistema u zaštiti šuma od gubara, Need for and application of geographic information system in forest protection against gypsy moth",
pages = "631-626",
number = "6",
volume = "33",
url = "conv_597"
}

Mihajlović, L., Marković, N.,& Milanović, S.. (2005). Potrebe i mogućnosti primene geografskog informacionog sistema u zaštiti šuma od gubara. in Biljni lekar
Univerzitet u Novom Sadu - Poljoprivredni fakultet - Departman za zaštitu bilja i životne sredine "dr Pavla Vukasovića", Novi Sad., 33(6), 626-631.
conv_597

Mihajlović L, Marković N, Milanović S. Potrebe i mogućnosti primene geografskog informacionog sistema u zaštiti šuma od gubara. in Biljni lekar. 2005;33(6):626-631.
conv_597 .

Mihajlović, Ljubodrag, Marković, Nenad, Milanović, Slobodan, "Potrebe i mogućnosti primene geografskog informacionog sistema u zaštiti šuma od gubara" in Biljni lekar, 33, no. 6 (2005):626-631,
conv_597 .

TY  - JOUR
AU  - Pantić, Damjan
AU  - Krstić, Milun
AU  - Danilović, Milorad
AU  - Matović, Bratislav
AU  - Marković, Nenad
PY  - 2003
UR  - https://omorika.sfb.bg.ac.rs/handle/123456789/116
AB  - U radu su prikazani rezultati proučavanja tokova razvoja i prirasta pojedinačnih stabala, kao i proizvodnosti izdanačkih sastojina bukve na području Crnog Vrha. Analizirana su stabla iz kategorije 20% najdebljih stabala u sastojini, standardnom dendrometrijskom analizom, a proizvodnost je utvrđena na osnovu vrednosti osnovnih taksacionih elemenata dobijenih sa oglednih površina. Rezultati ovih analiza, u kombinaciji sa rezultatima istraživanja drugih autora, koji su sa različitih aspekata proučavali izdanačke bukove šume na istom lokalitetu, omogućili su realno i sveobuhvatno sagledavanje stanja ovih sastojina. Na osnovu toga definisan je dugoročni gazdinski cilj (konverzija u visoki uzgojni oblik) i aktuelna uzgojna mera (visoka selektivna proreda).
AB  - The trends of development and increment of individual trees, as well as the productivity of beech coppice stands in the region of Crni Vrh were studied. The trees in the category of 20% of the largest-diameter trees in the stand were analyzed by the standard dendrometric analysis, the productivity was assessed based on the values of the major taxation elements measured at the sample plots. The results of these analyses, combined with the results reported by other authors, who studied beech coppice forests at the same locality but from different aspects, enable the real and comprehensive assessment of the state of these stands. On this basis, the aim of long-term management (conversion into a high silvicultural form) and the actual silvicultural measure (high selection thinning) were defined.
PB  - Univerzitet u Beogradu - Šumarski fakultet, Beograd
T2  - Glasnik Šumarskog fakulteta
T1  - Razvoj stabala i proizvodnost izdanačkih sastojina bukve na području Crnog Vrha
T1  - Tree development and productivity of beech coppice stands in the Crni Vrh region
EP  - 186
IS  - 87
SP  - 175
DO  - 10.2298/GSF0387175P
UR  - conv_149
ER  - 

@article{
author = "Pantić, Damjan and Krstić, Milun and Danilović, Milorad and Matović, Bratislav and Marković, Nenad",
year = "2003",
abstract = "U radu su prikazani rezultati proučavanja tokova razvoja i prirasta pojedinačnih stabala, kao i proizvodnosti izdanačkih sastojina bukve na području Crnog Vrha. Analizirana su stabla iz kategorije 20% najdebljih stabala u sastojini, standardnom dendrometrijskom analizom, a proizvodnost je utvrđena na osnovu vrednosti osnovnih taksacionih elemenata dobijenih sa oglednih površina. Rezultati ovih analiza, u kombinaciji sa rezultatima istraživanja drugih autora, koji su sa različitih aspekata proučavali izdanačke bukove šume na istom lokalitetu, omogućili su realno i sveobuhvatno sagledavanje stanja ovih sastojina. Na osnovu toga definisan je dugoročni gazdinski cilj (konverzija u visoki uzgojni oblik) i aktuelna uzgojna mera (visoka selektivna proreda)., The trends of development and increment of individual trees, as well as the productivity of beech coppice stands in the region of Crni Vrh were studied. The trees in the category of 20% of the largest-diameter trees in the stand were analyzed by the standard dendrometric analysis, the productivity was assessed based on the values of the major taxation elements measured at the sample plots. The results of these analyses, combined with the results reported by other authors, who studied beech coppice forests at the same locality but from different aspects, enable the real and comprehensive assessment of the state of these stands. On this basis, the aim of long-term management (conversion into a high silvicultural form) and the actual silvicultural measure (high selection thinning) were defined.",
publisher = "Univerzitet u Beogradu - Šumarski fakultet, Beograd",
journal = "Glasnik Šumarskog fakulteta",
title = "Razvoj stabala i proizvodnost izdanačkih sastojina bukve na području Crnog Vrha, Tree development and productivity of beech coppice stands in the Crni Vrh region",
pages = "186-175",
number = "87",
doi = "10.2298/GSF0387175P",
url = "conv_149"
}

Pantić, D., Krstić, M., Danilović, M., Matović, B.,& Marković, N.. (2003). Razvoj stabala i proizvodnost izdanačkih sastojina bukve na području Crnog Vrha. in Glasnik Šumarskog fakulteta
Univerzitet u Beogradu - Šumarski fakultet, Beograd.(87), 175-186.
https://doi.org/10.2298/GSF0387175P
conv_149

Pantić D, Krstić M, Danilović M, Matović B, Marković N. Razvoj stabala i proizvodnost izdanačkih sastojina bukve na području Crnog Vrha. in Glasnik Šumarskog fakulteta. 2003;(87):175-186.
doi:10.2298/GSF0387175P
conv_149 .

Pantić, Damjan, Krstić, Milun, Danilović, Milorad, Matović, Bratislav, Marković, Nenad, "Razvoj stabala i proizvodnost izdanačkih sastojina bukve na području Crnog Vrha" in Glasnik Šumarskog fakulteta, no. 87 (2003):175-186,
https://doi.org/10.2298/GSF0387175P .,
conv_149 .