Preprints
https://doi.org/10.5194/nhess-2021-384
https://doi.org/10.5194/nhess-2021-384
 
23 Dec 2021
23 Dec 2021
Status: a revised version of this preprint is currently under review for the journal NHESS.

A data-driven prediction model for Fennoscandian wildfires

Sigrid Jørgensen Bakke1, Niko Wanders2, Karin van der Wiel3, and Lena Merete Tallaksen1 Sigrid Jørgensen Bakke et al.
  • 1Department of Geosciences, University of Oslo
  • 2Department of Physical Geography, Utrecht University
  • 3Royal Netherlands Meteorological Institute

Abstract. Wildfires are recurrent natural hazards that affect terrestrial ecosystems, the carbon cycle, climate and society. They are typically hard to predict, as their exact location and occurrence are driven by a variety of factors. Identifying a selection of dominant controls can ultimately improve predictions and projections of wildfires in both the current and a future climate. In this study, we applied a data-driven machine learning approach to identify dominant hydrometeorological factors determining fire occurrence over Fennoscandia, and produced spatiotemporally resolved fire danger probability maps. A random forest learner was applied to predict fire danger probabilities over space and time, using a monthly 2001–2019 satellite-based fire occurrence dataset at a 0.25° spatial grid as the target variable. The final data-driven model slightly outperformed the established Canadian fire weather index (FWI) used for comparison. Half of the 30 potential predictors included in the study were automatically selected for the model. Shallow volumetric soil water anomaly stood out as the dominant predictor, followed by predictors related to temperature and deep volumetric soil water. Using a local fire occurrence record for Norway as target data in a separate analysis, the test set performance increased considerably. This improvement shows the potential of developing reliable data-driven prediction models for regions with a high quality fire occurrence record, and the limitation of using satellite-based fire occurrence data in regions subject to small fires not picked up by satellites. We conclude that data-driven fire prediction models are promising, both as a tool to identify the dominant predictors and for fire danger probability mapping. The derived relationships between wildfires and its compound predictors can further be used to assess potential changes in fire danger probability under future climate scenarios.

Sigrid Jørgensen Bakke et al.

Status: final response (author comments only)

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse
  • RC1: 'Comment on nhess-2021-384', Anonymous Referee #1, 21 Feb 2022
    • AC1: 'Reply on RC1', Sigrid Joergensen Bakke, 16 May 2022
  • RC2: 'Comment on nhess-2021-384', Anonymous Referee #2, 17 Mar 2022
    • AC2: 'Reply on RC2', Sigrid Joergensen Bakke, 16 May 2022

Sigrid Jørgensen Bakke et al.

Sigrid Jørgensen Bakke et al.

Viewed

Total article views: 657 (including HTML, PDF, and XML)
HTML PDF XML Total Supplement BibTeX EndNote
451 185 21 657 39 19 13
  • HTML: 451
  • PDF: 185
  • XML: 21
  • Total: 657
  • Supplement: 39
  • BibTeX: 19
  • EndNote: 13
Views and downloads (calculated since 23 Dec 2021)
Cumulative views and downloads (calculated since 23 Dec 2021)

Viewed (geographical distribution)

Total article views: 603 (including HTML, PDF, and XML) Thereof 603 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Latest update: 06 Oct 2022
Download
Short summary
In this study, we developed a machine learning model to identify dominant controls of wildfire in Fennoscandia, and produce monthly fire danger probability maps. The dominant control was shallow soil water anomaly, followed by air temperature and deep soil water. The model proved skilful with a similar performance as the existing Canadian Fire Weather Index. We highlight the benefit of using data-driven models jointly with other fire models to improve fire monitoring and prediction.
Altmetrics