Predicting hazards of climate extremes: a statistical perspective
- 18 December 2025
- journal article
- Published by Oxford University Press (OUP) in Journal of the Royal Statistical Society Series C: Applied Statistics
Abstract
Climate extremes such as floods, storms, and heatwaves have caused severe economic and human losses across Europe in recent decades. To support the European Union (EU)’s climate resilience efforts, we propose a statistical framework for short-to-medium-term prediction of tail risks related to extreme economic losses and fatalities. Our approach builds on Extreme Value Theory and employs the predictive distribution of future tail events to quantify both estimation and aleatoric uncertainty. Using data on losses and fatalities in Europe from 1980 to 2023, we model extreme events through Peaks Over Threshold methodology and fit Generalised Pareto (GP) and discrete-GP models using an empirical Bayes procedure. Our predictive approach enables a ‘What-if’ analysis to evaluate hypothetical scenarios beyond observed levels, including potential worst-case outcomes, for a precautionary risk assessment of future extreme episodes. To account for a time-varying behaviour of extreme losses and fatalities we extend our predictive method using a proportional tail model that allows to handle heteroscedastic extremes over time. Results of our analysis under stationarity and non-stationary settings raise concerns, reinforcing the urgency of integrating predictive tail risk assessment into EU adaptation strategies.Keywords
All Related Versions
Funding Information
- MUR-PRIN Bando 2022-prot (20229PFAX5)
- Next Generation EU (J53D23004260001)
This publication has 29 references indexed in Scilit:
- Gradient boosting with extreme-value theory for wildfire predictionExtremes, 2023
- Estimation and uncertainty quantification for extreme quantile regionsExtremes, 2019
- A comparison of dependence function estimators in multivariate extremesStatistics and Computing, 2017
- Multivariate nonparametric estimation of the Pickands dependence function using Bernstein polynomialsJournal of Statistical Planning and Inference, 2017
- Statistics of Extremes: Challenges and Opportunities2016
- A limiting distribution for maxima of discrete stationary triangular arrays with an application to risk due to avalanchesExtremes, 2015
- Likelihood estimators for multivariate extremesExtremes, 2015
- Discretization of distributions in the maximum domain of attractionExtremes, 2011
- Extreme Value Theory2006
- An Introduction to Statistical Modeling of Extreme Values2001