Abstract
Fires can have an anthropogenic or natural origin. The most frequent natural fire cause is lightning. Since anthropogenic and lightning fires have different climatic and socio-economic drivers, it is important to distinguish between these different fire causes. We developed random forest models that predict the fraction of anthropogenic and lightning fire incidences, and their burned area, at the level of the Nomenclature des Unités Territoriales Statistiques level 3 (NUTS3) for Europe. The models were calibrated using the centered log-ratio of fire incidence and burned area reference data from the European Forest Fire Information System. After a correlation analysis, the population density, fractional human land impact, elevation and burned area coefficient of variation—a measure of interannual variability in burned area—were selected as predictor variables in the models. After parameter tuning and running the models with several train-validate compositions, we found that the vast majority of fires and burned area in Europe has an anthropogenic cause, while lightning plays a significant role in the remote northern regions of Scandinavia. Combining our results with burned area data from the Moderate Resolution Imaging Spectroradiometer, we estimated that 96.5 ± 0.9% of the burned area in Europe has an anthropogenic cause. Our spatially explicit fire cause attribution model demonstrates the spatial variability between anthropogenic and lightning fires and their burned area over Europe and could be used to improve predictive fire models by accounting for fire cause.
Original language | English |
---|---|
Article number | 651 |
Pages (from-to) | 1-19 |
Number of pages | 19 |
Journal | Land |
Volume | 11 |
Issue number | 5 |
Early online date | 28 Apr 2022 |
DOIs | |
Publication status | Published - May 2022 |
Bibliographical note
Special Issue: Feature Papers for Land–Climate Interactions Section.Funding Information:
Funding: S.V. acknowledges the support from the Dutch Research Council through Vidi grant 016.Vidi.189.070 and from the European Research Council under the European Union’s Horizon 2020 research and innovation program (grant agreement No 101000987).
Publisher Copyright:
© 2022 by the authors. Licensee MDPI, Basel, Switzerland.
Keywords
- burned area
- Europe
- fire cause
- ignition
- random forest model