Citation

Phelps N, Woolford DG, Phelps N, Woolford DG. Int. J. Wildland Fire 2021; 30(11): 850-870.

Copyright

(Copyright © 2021, International Association of Wildland Fire, Fire Research Institute, Publisher CSIRO Publishing)

DOI

10.1071/WF20139

PMID

unavailable

Abstract

Wildland fire occurrence prediction (FOP) modelling supports fire management decisions, such as suppression resource pre-positioning and the routeing of detection patrols. Common empirical modelling methods for FOP include both model-based (statistical modelling) and algorithmic-based (machine learning) approaches. However, it was recently shown that many machine learning models in FOP literature are not suitable for fire management operations because of overprediction if not properly calibrated to output true probabilities. We present methods for properly calibrating statistical and machine learning models for fine-scale, spatially explicit daily FOP followed by a case-study comparison of human-caused FOP modelling in the Lac La Biche region of Alberta, Canada, using data from 1996 to 2016. Calibrated bagged classification trees, random forests, neural networks, logistic regression models and logistic generalised additive models (GAMs) are compared in order to assess the pros and cons of these approaches when properly calibrated.

RESULTS suggest that logistic GAMs can have similar performance to machine learning models for FOP. Hence, we advocate that the pros and cons of different modelling approaches should be discussed with fire management practitioners when determining which models to use operationally because statistical methods are commonly viewed as more interpretable than machine learning methods.

Language: en