Forest fires have become a major problem in many regions of the world, including parts of Central Europe. The modelling study addresses the different factors for Forest Fire Susceptibility (FFS), making use of high spatial resolution of input data for the state of Brandenburg, Germany. An increasing susceptibility is found under rising greenhouse gas forcing scenarios when other changes are not taken into account. Extreme weather periods are of particular relevance in this respect. However, the importance of anthropogenic and vegetation parameters for modelling FFS on a regional level can outweigh the pure climatic effects. The paper also suggests some recommendations for forest management and environmental planning for a reduction of fire risk.
Forest fires have become a major problem in many regions of the world, including parts of...
In this study we applied a random forest machine learning algorithm to model current and future forest fire susceptibility (FFS) in north-eastern Germany using anthropogenic, climatic, topographic, soil, and vegetation variables. Model accuracy ranged between 69 % and 71 %, showing moderately high model reliability for predicting FFS. The model results underline the importance of anthropogenic and vegetation parameters. This study will support regional forest fire prevention and management.
In this study we applied a random forest machine learning algorithm to model current and future...