Abstract
In order to formulate effective fire-mitigation policies, it is important to understand the spatial and temporal distribution of different types of wildfires and to be able to predict their occurrence taking the main influencing factors into account. The objective of this short communication is to assess the capability of a fast and easy-to-implement random forest algorithm to estimate cumulative probabilities fire frequency and burned area using a large dataset collected in the USA. The input variables of the algorithm are voluntary restricted to climate and land use factors, which are easy to obtain in practice. No input related to fire frequency, burned area, or to any other fire characteristic is used. After model selection and training, the performance of random forest is assessed using an independent dataset including 80,000 observations of fire occurrence and burned area. Results show that the score of our simple random forest algorithm is 9% higher than the score of the winner of the data challenge of Opitz (Extreme, 2022) revealing that, although this model has a good performance, it is not the best. However, the approach proposed here can be implemented using standard packages, does not require any fire monitoring system after training, and requires little specialized knowledge in machine learning, which makes it usable by a large diversity of stakeholders. The results of this study suggest that random forest should be part of the toolbox of engineers and scientists involved in wildfire prediction.
Similar content being viewed by others
Data availability
All data analysed in this study are those made available by Opitz (2022) for the EVA Data Challenge 2021. They are available from the corresponding author on reasonable request.
References
Abatzogloua, J.T., Williams, A.P.: Impact of anthropogenic climate change on wildfire across western US forests. Proc. Nat. Acad. Sci. 113, 11770–11775 (2016)
Biau, G., Devroye, L., Lugosi, G.: Consistency of random forests and other averaging classifiers. J. Mach. Learn. Res. 9, 2015–2033 (2008)
Breiman, L.: Random forests. Maching Learn. 45, 5–32 (2001). https://doi.org/10.1023/A:1010933404324
CRS.: (2011). https://sgp.fas.org/crs/misc/IF10244.pdf
Gnecco, N., Terefe, E.M., Engelke, S. Extremal random forests. arXiv:2201.12865 (2022)
Jain, P., Coogan, S.C.P., Subramarian, S.G., Crowley, M., Taylor, S.: Flannigan M.D. A review of machine learning applications in wildfire science and management. Environ. Reviews. (2020). https://doi.org/10.1139/er-2020-0019
Joseph, M.B., Rossi, M.W., Mietkiewicz, N.P., Mahood, A.L., Cattau, M.E., St, L.A., Denis, R.C., Nagy, V., Iglesias, J.T., Abatzoglou: Balch. Spatiotemporal prediction of wildfire size extremes with bayesian finite sample maxima. Ecol. Appl. 29, e01898 (2019). https://doi.org/10.1002/eap.1898
Keeley, J.E., Syphard, A.D.: Historical patterns of wildfire ignition sources in California ecosystems. Int. J. Wildland Fire. 27, 781–799 (2018)
Li, S., Banerjee, T. Spatial and temporal pattern of wildfires in California from 2000 to 2019. Scie. Rep. s11, 8779 (2021). https://doi.org/10.1038/s41598-021-88131-9
Li, S., Sparrow, S.N., Otto, F.E.L., Rifai, S.W., Oliveras, I., Krikken, F., Anderson, L.O., Malhi, Y., Wallom, D.: Anthropogenic climate change contribution to wildfire-prone weather conditions in the Cerrado and Arc of deforestation. Environ. Res. Lett. 16, 16 094051 (2021)
Malley, J.D., Kruppa, J., Malley, K.G., Ziegler, A.: Probablity machines: consistent probability estimation using nonparametric learning machines. Methods Inf. Med. 51, 274–281 (2012). https://doi.org/10.3414/ME00-01-0052
Opitz, T., Editorial: EVA 2021 Data Competition on spatio-temporal prediction of wildfire activity in the United States. Extremes (2022)
Taylor, S.W., Woolford, D.G., Dean, C.B., Martell, D.L.: Wildfire prediction to inform fire management: statistical science challenges. Stat. Sci. 28, 586–615 (2013)
Wright, M.N., Ziegler, A.: A fast implementation of Random forests for high Dimensional Data in C + + and R. J. Stat. Softw. 77, 1–17 (2017). https://doi.org/10.18637/jss.v077.i01
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that they have no conflict of interest.
Additional information
Publisher’s Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Makowski, D. Simple random forest classification algorithms for predicting occurrences and sizes of wildfires. Extremes 26, 331–338 (2023). https://doi.org/10.1007/s10687-022-00458-2
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10687-022-00458-2