A marginal modelling approach for predicting wildfire extremes across the contiguous United States

DOI10.1007/S10687-023-00469-7MaRDI QIDQ6100565zbMATH OpenOpenAlexFDO

Authors Eleanor D'Arcy, Callum J. R. Murphy-Barltrop, Rob Shooter, Emma S. Simpson

Publication date 12 May 2023

Published in Extremes (Search for Journal in Brave)

Copyright license Creative Commons Attribution 4.0 International

Full work available at URL https://arxiv.org/abs/2112.15372

zbMATH Keywords

extreme value theorysemi-parametric modellingwildfire prediction

Mathematics Subject Classification ID

Statistics (62-XX)

Abstract: This paper details a methodology proposed for the EVA 2021 conference data challenge. The aim of this challenge was to predict the number and size of wildfires over the contiguous US between 1993 and 2015, with more importance placed on extreme events. In the data set provided, over 14% of both wildfire count and burnt area observations are missing; the objective of the data challenge was to estimate a range of marginal probabilities from the distribution functions of these missing observations. To enable this prediction, we make the assumption that the marginal distribution of a missing observation can be informed using non-missing data from neighbouring locations. In our method, we select spatial neighbourhoods for each missing observation and fit marginal models to non-missing observations in these regions. For the wildfire counts, we assume the compiled data sets follow a zero-inflated negative binomial distribution, while for burnt area values, we model the bulk and tail of each compiled data set using non-parametric and parametric techniques, respectively. Cross validation is used to select tuning parameters, and the resulting predictions are shown to significantly outperform the benchmark method proposed in the challenge outline. We conclude with a discussion of our modelling framework, and evaluate ways in which it could be extended.

Cites work

• scientific article; zbMATH DE number 6734253 (Why is no real title available?)
• A combined statistical and machine learning approach for spatial prediction of extreme wildfire frequencies and sizes
• An introduction to statistical modeling of extreme values
• Data Mining and Knowledge Discovery Handbook
• Dependence measures for extreme value analyses
• Generalized Additive Models for Exceedances of High Thresholds With an Application to Return Level Estimation for U.S. Wind Gusts
• Gradient boosting with extreme-value theory for wildfire prediction
• Modelling extremes of spatial aggregates of precipitation using conditional methods
• Reconstruction of incomplete wildfire data using deep generative models
• Residual life time at great age
• Spatiotemporal wildfire modeling through point processes with moderate and extreme marks
• Statistical inference using extreme order statistics
• The MELBS team winning entry for the EVA2017 competition for spatiotemporal prediction of extreme rainfall using generalized extreme value quantiles

Cited in

(2)

• A maximal covering location-based model for analyzing the vulnerability of landscapes to wildfires: assessing the worst-case scenario
• Gradient boosting with extreme-value theory for wildfire prediction

This page was built for publication: A marginal modelling approach for predicting wildfire extremes across the contiguous United States

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6100565)