Preprints
https://doi.org/10.5194/egusphere-2025-143
https://doi.org/10.5194/egusphere-2025-143
24 Jan 2025
 | 24 Jan 2025
Status: this preprint is open for discussion and under review for Natural Hazards and Earth System Sciences (NHESS).

Assessing human-caused wildfire ignition likelihood across Europe

Pere Joan Gelabert, Adrián Jiménez-Ruano, Clara Ochoa, Fermín Alcasena, Johan Sjöström, Christopher Marrs, Luís Mário Ribeiro, Palaiologos Palaiologou, Carmen Bentué Martínez, Emilio Chuvieco, Cristina Vega-Garcia, and Marcos Rodrigues

Abstract. This study features a cohesive modelling approach of human-caused wildfire ignitions applied to a set of representative regions in terms of fire activity across Europe (pilot sites, PS). Our main goal was to develop a common approach to model human-caused ignition probability at a fine-grained spatial resolution (100 m) and identify the main drivers of their emerge. Specifically, we (i) ascertain which factors influence ignitions in each PS; (ii) deliver a spatial-explicit representation of ignition probability, and (iii) provide a framework for comparison with regional-scale models among PS. To do so, we calibrated Random Forest models from historical fire records compiled by local fire agencies, and geospatial layers of land cover, accessibility, population density and dead fine-fuel moisture content (DFMC). Models were built individually for each PS, comparing them with a full model constructed from all PS. Furthermore, special attention was given to the effect of spatial autocorrelation in model performance. All models achieved sufficient predictive performance (AUCs from 0.70 to 0.89). For all PS models, the yearly anomaly in DFMC was the most influential variable. Among human-related factors, distance to the Wildland Urban Interface emerged as the most relevant variable, followed by proximity to roads, population density, and the fraction of wildland coverage. The performance of the full model achieved an AUC value of 0.81, with mean DFMC and anomaly being the main ignition factors, modulated by distance to roads and population density. The local performance of the full model dropped by 0.10 for AUC in both Southern Sweden and Attica (Greece) regions. The wildfire occurrence models developed in this study are essential for understanding wildfire ignition hazard and may help implement integrated wildfire risk management strategies and mitigation policies in fire-prone EU landscapes.

Publisher's note: Copernicus Publications remains neutral with regard to jurisdictional claims made in the text, published maps, institutional affiliations, or any other geographical representation in this preprint. The responsibility to include appropriate place names lies with the authors.
Share
Pere Joan Gelabert, Adrián Jiménez-Ruano, Clara Ochoa, Fermín Alcasena, Johan Sjöström, Christopher Marrs, Luís Mário Ribeiro, Palaiologos Palaiologou, Carmen Bentué Martínez, Emilio Chuvieco, Cristina Vega-Garcia, and Marcos Rodrigues

Status: open (until 07 Mar 2025)

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse
Pere Joan Gelabert, Adrián Jiménez-Ruano, Clara Ochoa, Fermín Alcasena, Johan Sjöström, Christopher Marrs, Luís Mário Ribeiro, Palaiologos Palaiologou, Carmen Bentué Martínez, Emilio Chuvieco, Cristina Vega-Garcia, and Marcos Rodrigues
Pere Joan Gelabert, Adrián Jiménez-Ruano, Clara Ochoa, Fermín Alcasena, Johan Sjöström, Christopher Marrs, Luís Mário Ribeiro, Palaiologos Palaiologou, Carmen Bentué Martínez, Emilio Chuvieco, Cristina Vega-Garcia, and Marcos Rodrigues

Viewed

Total article views: 101 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
68 28 5 101 1 0
  • HTML: 68
  • PDF: 28
  • XML: 5
  • Total: 101
  • BibTeX: 1
  • EndNote: 0
Views and downloads (calculated since 24 Jan 2025)
Cumulative views and downloads (calculated since 24 Jan 2025)

Viewed (geographical distribution)

Total article views: 104 (including HTML, PDF, and XML) Thereof 104 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Latest update: 06 Feb 2025
Download
Short summary
Wildfires threaten ecosystems and communities across Europe. Our study developed models to predict where and why these ignitions occur in different European environments. We found that weather anomalies and human factors, like proximity to urban areas and roads, are key drivers. Using Machine Learning our models achieved strong predictive accuracy. These insights help design better wildfire prevention strategies, ensuring safer landscapes and communities as fire risks grow with climate change.
Share