A data-driven model for Fennoscandian wildfire danger

Bakke, Sigrid Jørgensen; Wanders, Niko; van der Wiel, Karin; Tallaksen, Lena Merete

doi:https://doi.org/10.5194/nhess-23-65-2023

Articles | Volume 23, issue 1

https://doi.org/10.5194/nhess-23-65-2023

© Author(s) 2023. This work is distributed under
the Creative Commons Attribution 4.0 License.

https://doi.org/10.5194/nhess-23-65-2023

© Author(s) 2023. This work is distributed under
the Creative Commons Attribution 4.0 License.

Articles | Volume 23, issue 1

Research article

|

12 Jan 2023

Research article |

| 12 Jan 2023

A data-driven model for Fennoscandian wildfire danger

Sigrid Jørgensen Bakke, Niko Wanders, Karin van der Wiel, and Lena Merete Tallaksen

Supplement

https://doi.org/10.5194/nhess-23-65-2023-supplement

Data sets

Fire burned area from 2001 to present derived from satellite observations from the European Space Agency Climate Change Initiative (ESA-CCI) ESA-CCI https://doi.org/10.24381/cds.f333cf85

ERA5-Land monthly averaged data from 1981 to present J. Muñoz Sabater https://doi.org/10.24381/cds.68d2bb30

ERA5-Land hourly data from 1981 to present J. Muñoz Sabater https://doi.org/10.24381/cds.e2161bac

E-OBS daily gridded meteorological data for Europe from 1950 to present derived from in-situ observations: v23.1e EU-FP6 project UERRA, Copernicus Climate Change Service and data providers in the EC&D project https://doi.org/10.24381/cds.151d3ec6

MOD13C2 MODIS/Terra Vegetation Indices Monthly L3 Global 0.05Deg CMG V006 K. Didan https://doi.org/10.5067/MODIS/MOD13C2.006

Model code and software

Climate Data Operator (CDO) (1.9.6) U. Schulzweida, R. Mueller, O. Heidmann, C. Ansorge, L. Kornblueh, F. Wachsmann, M. Kameswarrao, and R. Quast https://doi.org/10.5281/zenodo.3991595

Pandas: v1.3.2 J. Reback, jbrockmendel, W. McKinney, J. Van den Bossche, T. Augspurger, P. Cloud, S. Hawkins, gfyoung, Sinhrks, M. Roeschke, A. Klein, T. Petersen, J. Tratner, C. She, W. Ayd, P. Hoefler, S. Naveh, M. Garcia, J. Schendel, A. Hayden, D. Saxton, R. Shadrach, M. E. Gorelli, F. Li, V. Jancauskas, attack68, A. McMaster, P. Battiston, S. Seabold, and K. Dong https://doi.org/10.5281/zenodo.5203279

xskillscore: v0.0.23 R. Bell, A. Spring, R. Brady, Andrew, D. Squire, Z. Blackwood, M. C. Sitter, and T. Chegini https://doi.org/10.5281/zenodo.5173153

cartopy: v0.17.0 P. Elson, E. Sales de Andrade, R. Hattersley, E. Campbell, A. Dawson, R. May, scmc72, B. Little, C. Pelley, B. Blay, K. Donkers, P. Killick, marqh, lbdreyer, P. Peglar, N. Wilson, D. Kirkham, C. Bosley, J. Signell, Filipe, L. Krischer, D. Eriksson, A. Smith, Carlos, D. McDougall, A. Crosby, D. Herzmann, scaine1, Greg, and munslowa https://doi.org/10.5281/zenodo.1490296

xarray: v0.20.1 S. Hoyer, C. Fitzgerald, J. Hamman, keewis, D. Cherian, C. Fitzgerald, M. Hauser, K. Fujii, F. Maussion, crusaderky, S. Clark, A. Kleeman, T. Nicholas, T. K. Illviljan, J. Munroe, A. Amici, A. Barghini, A. Banihirwe, R. Bell, gimperiale, Z. Hatfield-Dodds, R. Abernathey, B. Bovy, johnomotani, K. Mühlbauer, M. Roszko, and P. J. Wolfram https://doi.org/10.5281/zenodo.5648431

SCI: Standardized Climate Indices such as SPI, SRI or SPEI L. Gudmundsson and J. H. Stagge https://cran.r-project.org/package=SCI

NumPy: v1.20.3 NumPy project https://github.com/numpy/numpy

scikit-learn: v0.24.2 O. Grisel, A. Mueller, Lars, A. Gramfort, G. Louppe, P. Prettenhofer, M. Blondel, V. Niculae, J. Nothman, A. Joly, T. J. Fan, J. Vanderplas, M. Kumar, H. Qin, N. Hug, N. Varoquaux, L. Estève, R. Layton, G. Lemaitre, J. H. Metzen, A. Jalali, V. R. Rajagopalan, J. Schönberger, R. Yurchak, J. du Boisberranger, W. Li, C. Woolam, T. Dupré la Tour, K. Eren, and Eustache https://doi.org/10.5281/zenodo.4725836

SciPy: v1.6.2 P. Virtanen, R. Gommers, E. Burovski, T. E. Oliphant, W. Weckesser, D. Cournapeau, alexbrc, T. Reddy, P. Peterson, M. Haberland, J. Wilson, A. Nelson, endolith, N. Mayorov, S. van der Walt, I. Polat, D. Laxalde, M. Brett, E. Larson, J. Millman, Lars, P. van Mulbregt, eric-jones, C. J. Carey, E. Moore, R. Kern, peterbell10, T. Leslie, J. Perktold, and K. Striega https://doi.org/10.5281/zenodo.4635380

matplotlib: v3.4.3 T. A. Caswell, M. Droettboom, A. Lee, E. Sales de Andrade, T. Hoffmann, J. Hunter, J. Klymak, E. Firing, D. Stansby, N. Varoquaux, J. H. Nielsen, B. Root, R. May, P. Elson, J. K. Seppänen, D. Dale, J.-J. Lee, D. McDougall, A. Straw, P. Hobson, hannah, C. Gohlke, T. S. Yu, E. Ma, A. F. Vincent, S. Silvester, C. Moad, N. Kniazev, E. Ernest, and P. Ivanov https://doi.org/10.5281/zenodo.5194481

seaborn: v0.11.2 M. Waskom, M. Gelbart, O. Botvinnik, J. Ostblom, P. Hobson, S. Lukauskas, D. C. Gemperline, T. Augspurger, Y. Halchenko, J. Warmenhoven, J. B. Cole, J. de Ruiter, J. Vanderplas, S. Hoyer, C. Pye, A. Miles, C. Swain, K. Meyer, M. Martin, P. Bachant, E. Quintero, G. Kunter, S. Villalba, Brian, C. Fitzgerald, C. Evans, M. L. Williams, D. O'Kane, T. Yarkoni, and T. Brunner https://doi.org/10.5281/zenodo.5205191

Download

Article (4236 KB)
Full-text XML

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 Forest Fire Weather Index (FWI). We highlight the benefit of using data-driven models jointly with other fire models to improve fire monitoring and prediction.