TY  - JOUR
AU  - Milanović, Slobodan
AU  - Kaczmarowski, Jan
AU  - Ciesielski, Mariusz
AU  - Trailović, Zoran
AU  - Mielcarek, Milosz
AU  - Szczygiel, Ryszard
AU  - Kwiatkowski, Miroslaw
AU  - Balazy, Radomir
AU  - Zasada, Michal
AU  - Milanović, Slađan D.
PY  - 2023
UR  - https://omorika.sfb.bg.ac.rs/handle/123456789/1429
AB  - In recent years, forest fires have become an important issue in Central Europe. To model the probability of the occurrence of forest fires in the Lower Silesian Voivodeship of Poland, historical fire data and several types of predictors were collected or generated, including topographic, vegetation, climatic, and anthropogenic features. The main objectives of this study were to determine the importance of the predictors of forest fire occurrence and to map the probability of forest fire occurrence. The H2O driverless artificial intelligence (DAI) cloud platform was used to model forest fire probability. The gradient boosted machine (GBM) and random forest (RF) methods were applied to assess the probability of forest fire occurrence. Evaluation the importance of the variables was performed using the H2O platform permutation method. The most important variables were the presence of coniferous forest and the distance to agricultural land according to the GBM and RF methods, respectively. Model validation was conducted using receiver operating characteristic (ROC) analysis. The areas under the curve (AUCs) of the ROC plots from the GBM and RF models were 83.3% and 81.3%, respectively. Based on the results obtained, the GBM model can be recommended for the mapping of forest fire occurrence in the study area.
T2  - Forests
T1  - Modeling and Mapping of Forest Fire Occurrence in the Lower Silesian Voivodeship of Poland Based on Machine Learning Methods
IS  - 1
VL  - 14
DO  - 10.3390/f14010046
UR  - conv_1680
ER  - 

@article{
author = "Milanović, Slobodan and Kaczmarowski, Jan and Ciesielski, Mariusz and Trailović, Zoran and Mielcarek, Milosz and Szczygiel, Ryszard and Kwiatkowski, Miroslaw and Balazy, Radomir and Zasada, Michal and Milanović, Slađan D.",
year = "2023",
abstract = "In recent years, forest fires have become an important issue in Central Europe. To model the probability of the occurrence of forest fires in the Lower Silesian Voivodeship of Poland, historical fire data and several types of predictors were collected or generated, including topographic, vegetation, climatic, and anthropogenic features. The main objectives of this study were to determine the importance of the predictors of forest fire occurrence and to map the probability of forest fire occurrence. The H2O driverless artificial intelligence (DAI) cloud platform was used to model forest fire probability. The gradient boosted machine (GBM) and random forest (RF) methods were applied to assess the probability of forest fire occurrence. Evaluation the importance of the variables was performed using the H2O platform permutation method. The most important variables were the presence of coniferous forest and the distance to agricultural land according to the GBM and RF methods, respectively. Model validation was conducted using receiver operating characteristic (ROC) analysis. The areas under the curve (AUCs) of the ROC plots from the GBM and RF models were 83.3% and 81.3%, respectively. Based on the results obtained, the GBM model can be recommended for the mapping of forest fire occurrence in the study area.",
journal = "Forests",
title = "Modeling and Mapping of Forest Fire Occurrence in the Lower Silesian Voivodeship of Poland Based on Machine Learning Methods",
number = "1",
volume = "14",
doi = "10.3390/f14010046",
url = "conv_1680"
}

Milanović, S., Kaczmarowski, J., Ciesielski, M., Trailović, Z., Mielcarek, M., Szczygiel, R., Kwiatkowski, M., Balazy, R., Zasada, M.,& Milanović, S. D.. (2023). Modeling and Mapping of Forest Fire Occurrence in the Lower Silesian Voivodeship of Poland Based on Machine Learning Methods. in Forests, 14(1).
https://doi.org/10.3390/f14010046
conv_1680

Milanović S, Kaczmarowski J, Ciesielski M, Trailović Z, Mielcarek M, Szczygiel R, Kwiatkowski M, Balazy R, Zasada M, Milanović SD. Modeling and Mapping of Forest Fire Occurrence in the Lower Silesian Voivodeship of Poland Based on Machine Learning Methods. in Forests. 2023;14(1).
doi:10.3390/f14010046
conv_1680 .

Milanović, Slobodan, Kaczmarowski, Jan, Ciesielski, Mariusz, Trailović, Zoran, Mielcarek, Milosz, Szczygiel, Ryszard, Kwiatkowski, Miroslaw, Balazy, Radomir, Zasada, Michal, Milanović, Slađan D., "Modeling and Mapping of Forest Fire Occurrence in the Lower Silesian Voivodeship of Poland Based on Machine Learning Methods" in Forests, 14, no. 1 (2023),
https://doi.org/10.3390/f14010046 .,
conv_1680 .

TY  - JOUR
AU  - Ciesielski, Mariusz
AU  - Balazy, Radomir
AU  - Borkowski, Boleslaw
AU  - Szczesny, Wieslaw
AU  - Zasada, Michal
AU  - Kaczmarowski, Jan
AU  - Kwiatkowski, Miroslaw
AU  - Szczygiel, Ryszard
AU  - Milanović, Slobodan
PY  - 2022
UR  - https://omorika.sfb.bg.ac.rs/handle/123456789/1285
AB  - Climate is one of the main causes of forest fires in Europe. In addition, forest fires are influenced by other factors, such as the reconstruction of tree stands with a uniform species composition and increasing human pressure. At the same time, the increasing number of fires is accompanied by a steady increase in the number and quality of spatial information collected, which affects the ability to conduct more accurate studies of forest fires. The appropriate use of spatial information systems (GIS) together with all the collected information on fires could provide new insights into their causes and, in further steps, allow the development of new, more accurate predictive models. The objectives of the study were: (i) to estimate the probability of fire occurrence in the period 2007-2016; (ii) to evaluate the performance of the developed model; (iii) to identify and quantify anthropogenic, topographic and stand factors affecting the probability of fire occurrence in forest areas in Poland. To achieve these objectives, a statistical model based on a logistic regression approach was built using the nationwide forest fire database for the period from 2007 to 2016. The information in the database was obtained from the Polish State For-est Information System (SILP). Then it was supplemented with spatial, topo-graphic and socio-economic information from various spatial and statistical databases. The results showed that fire probability is significantly positively affected by population density and distance from buildings. In addition, the further the distance from roads and railways, watercourses and water objects or the edge of the forest, height above sea level, and steep slopes, the lower is the fire probability. Analysis of spatial, ecological and socio-economic fac-tors provides new insights that contribute to a better understanding of fire oc-currence in Poland.
T2  - Iforest-Biogeosciences and Forestry
T1  - Contribution of anthropogenic, vegetation, and topographic features to forest fire occurrence in Poland
EP  - 314
SP  - 307
VL  - 15
DO  - 10.3832/ifor4052-015
UR  - conv_1654
ER  - 

@article{
author = "Ciesielski, Mariusz and Balazy, Radomir and Borkowski, Boleslaw and Szczesny, Wieslaw and Zasada, Michal and Kaczmarowski, Jan and Kwiatkowski, Miroslaw and Szczygiel, Ryszard and Milanović, Slobodan",
year = "2022",
abstract = "Climate is one of the main causes of forest fires in Europe. In addition, forest fires are influenced by other factors, such as the reconstruction of tree stands with a uniform species composition and increasing human pressure. At the same time, the increasing number of fires is accompanied by a steady increase in the number and quality of spatial information collected, which affects the ability to conduct more accurate studies of forest fires. The appropriate use of spatial information systems (GIS) together with all the collected information on fires could provide new insights into their causes and, in further steps, allow the development of new, more accurate predictive models. The objectives of the study were: (i) to estimate the probability of fire occurrence in the period 2007-2016; (ii) to evaluate the performance of the developed model; (iii) to identify and quantify anthropogenic, topographic and stand factors affecting the probability of fire occurrence in forest areas in Poland. To achieve these objectives, a statistical model based on a logistic regression approach was built using the nationwide forest fire database for the period from 2007 to 2016. The information in the database was obtained from the Polish State For-est Information System (SILP). Then it was supplemented with spatial, topo-graphic and socio-economic information from various spatial and statistical databases. The results showed that fire probability is significantly positively affected by population density and distance from buildings. In addition, the further the distance from roads and railways, watercourses and water objects or the edge of the forest, height above sea level, and steep slopes, the lower is the fire probability. Analysis of spatial, ecological and socio-economic fac-tors provides new insights that contribute to a better understanding of fire oc-currence in Poland.",
journal = "Iforest-Biogeosciences and Forestry",
title = "Contribution of anthropogenic, vegetation, and topographic features to forest fire occurrence in Poland",
pages = "314-307",
volume = "15",
doi = "10.3832/ifor4052-015",
url = "conv_1654"
}

Ciesielski, M., Balazy, R., Borkowski, B., Szczesny, W., Zasada, M., Kaczmarowski, J., Kwiatkowski, M., Szczygiel, R.,& Milanović, S.. (2022). Contribution of anthropogenic, vegetation, and topographic features to forest fire occurrence in Poland. in Iforest-Biogeosciences and Forestry, 15, 307-314.
https://doi.org/10.3832/ifor4052-015
conv_1654

Ciesielski M, Balazy R, Borkowski B, Szczesny W, Zasada M, Kaczmarowski J, Kwiatkowski M, Szczygiel R, Milanović S. Contribution of anthropogenic, vegetation, and topographic features to forest fire occurrence in Poland. in Iforest-Biogeosciences and Forestry. 2022;15:307-314.
doi:10.3832/ifor4052-015
conv_1654 .

Ciesielski, Mariusz, Balazy, Radomir, Borkowski, Boleslaw, Szczesny, Wieslaw, Zasada, Michal, Kaczmarowski, Jan, Kwiatkowski, Miroslaw, Szczygiel, Ryszard, Milanović, Slobodan, "Contribution of anthropogenic, vegetation, and topographic features to forest fire occurrence in Poland" in Iforest-Biogeosciences and Forestry, 15 (2022):307-314,
https://doi.org/10.3832/ifor4052-015 .,
conv_1654 .