Modeling and Mapping of Forest Fire Occurrence in the Lower Silesian Voivodeship of Poland Based on Machine Learning Methods

Milanović, Slobodan; Kaczmarowski, Jan; Ciesielski, Mariusz; Trailović, Zoran; Mielcarek, Miłosz; Szczygieł, Ryszard; Kwiatkowski, Mirosław; Bałazy, Radomir; Zasada, M.; Milanović, Svetlana

doi:10.3390/f14010046

Cited by 8 publications

(2 citation statements)

References 99 publications

(115 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In Poland, the causes of fires are almost entirely of anthropogenic origin [4]. The most important anthropogenic factors that may affect the occurrence of fires are considered to be population density, the density of local roads in forest areas, the density of contact lines between residential complexes and forests, and the distance of forests from buildings and communication lines [40][41][42].…”

Section: Discussionmentioning

confidence: 99%

Spatio-Temporal Dynamics of Forest Fires in Poland and Consequences for Fire Protection Systems: Seeking a Balance between Efficiency and Costs

Kolanek,

Szymanowski,

Małysz

2023

Sustainability

View full text Add to dashboard Cite

An important issue from the forest fire protection system perspective is forecasting fires and maintaining a high readiness of firefighting units at a low cost. In Poland, the level of fire protection is defined by the degree of forest fire risk, based on forecasts made for 1 March to 30 September, i.e., the risk period (the so-called fire season). In this paper, based on classical statistical and spatial analysis, we positively verify the research hypothesis that the fire season in Poland changes in terms of start and end dates depending on the region. We therefore propose a modification to the forecasting period, adapted to local conditions and calculated annually on the basis of the previous period. Then, using network analysis, we negatively verify the hypothesis that the size of the burned area is related to the distance from fire brigades, which proves that the reasons for such a differentiation in the number of fires should be sought elsewhere than in the system used for allocating fire units. On the basis of cluster analysis, attention is drawn to areas where large fires break out more often.

show abstract

Section: Discussionmentioning

confidence: 99%

Spatio-Temporal Dynamics of Forest Fires in Poland and Consequences for Fire Protection Systems: Seeking a Balance between Efficiency and Costs

Kolanek,

Szymanowski,

Małysz

2023

Sustainability

View full text Add to dashboard Cite

show abstract

“…[6] found that the density of the roads and the length of the boundary between a forest and residential areas were the most effective factors for predicting forest fires among 28 identified factors. Milanović et al [25] identified coniferous forests, proximity to agricultural land, and the amount of leaf litter as the main factors affecting forests using the gradient boosted machine algorithm.…”

Section: Introductionmentioning

confidence: 99%

Identifying Influential Spatial Drivers of Forest Fires through Geographically and Temporally Weighted Regression Coupled with a Continuous Invasive Weed Optimization Algorithm

Pahlavani,

Raei,

Bigdeli

et al. 2024

Fire

View full text Add to dashboard Cite

Identifying the underlying factors derived from geospatial and remote sensing data that contribute to forest fires is of paramount importance. It aids experts in pinpointing areas and periods most susceptible to these incidents. In this study, we employ the geographically and temporally weighted regression (GTWR) method in conjunction with a refined continuous invasive weed optimization (CIWO) algorithm to assess certain spatially relevant drivers of forest fires, encompassing both biophysical and anthropogenic influences. Our proposed approach demonstrates theoretical utility in addressing the spatial regression problem by meticulously accounting for the autocorrelation and non-stationarity inherent in spatial data. We leverage tricube and Gaussian kernels to weight the GTWR for two distinct temporal datasets, yielding coefficients of determination (R2) amounting to 0.99 and 0.97, respectively. In contrast, traditional geographically weighted regression (GWR) using the tricube kernel achieved R2 values of 0.87 and 0.88, while the Gaussian kernel yielded R2 values of 0.8138 and 0.82 for the same datasets. This investigation underscores the substantial impact of both biophysical and anthropogenic factors on forest fires within the study areas.

show abstract

Forest wildfire risk mapping, performance comparison of machine learning algorithms

Jalilian

Shataee

2023

Preprint

View full text Add to dashboard Cite

Mapping wildfire risk using proper models and algorithms is one of the top execution priorities for forest managers to prevent wildfires before fires occur. This study evaluates the abilities of the Artificial Neural Network (ANN), Support Vector Machines (SVM), Random Forest (RF), Multivariate Adaptive Regression Splines (MARS) machine learning methods for the prediction and mapping of fire risk across the forests of Golestan Province, Iran. For modeling, the area was first gridded into 1 ha grids, and then pixel values of influential factors were extracted and standardized based on the point shape file of grid centers. The nonparametric algorithms were implemented using 70% of fire points as training samples. The obtained forest fire risk maps were classified into three zones, including low-risk, medium-risk, and high-risk classes. The classification accuracy of the obtained risk maps was evaluated using 30% of the remained fire points. The results showed that the RF algorithm, with an overall accuracy of 75%, had the best performance in fire risk predictions compared to other algorithms. Forest managers can use this methodology to predict areas of most significant fire risk to prevent future fires through land use management, strategic decision-making, and planning. The results enable forest managers to find the best way to monitor, manage, and control fire outbreaks based on fire risk maps of forests in northeastern Iran or other regions with similar conditions.

show abstract

Modeling and Mapping of Forest Fire Occurrence in the Lower Silesian Voivodeship of Poland Based on Machine Learning Methods

Cited by 8 publications

References 99 publications

Spatio-Temporal Dynamics of Forest Fires in Poland and Consequences for Fire Protection Systems: Seeking a Balance between Efficiency and Costs

Spatio-Temporal Dynamics of Forest Fires in Poland and Consequences for Fire Protection Systems: Seeking a Balance between Efficiency and Costs

Identifying Influential Spatial Drivers of Forest Fires through Geographically and Temporally Weighted Regression Coupled with a Continuous Invasive Weed Optimization Algorithm

Forest wildfire risk mapping, performance comparison of machine learning algorithms

Contact Info

Product

Resources

About