Forecast verification for extreme value distributions with an application to probabilistic peak wind prediction

By Petra Friederichs, Thordis Linda Thorarinsdottir. 2012

132 citations recorded by the source corpus.

Predictions of the uncertainty associated with extreme events are a vital component of any prediction system for such events. Consequently, the prediction system ought to be probabilistic in nature, with the predictions taking the form of probability distributions. This paper concerns probabilistic prediction systems where the data are assumed to follow either a generalized extreme value (GEV) distribution or a generalized Pareto distribution. In this setting, the properties of proper scoring rules that facilitate the assessment of the prediction uncertainty are investigated, and closed form expressions for the continuous ranked probability score (CRPS) are provided. In an application to peak wind prediction, the predictive performance of a GEV model under maximum likelihood estimation, optimum score estimation with the CRPS, and a Bayesian framework are compared. The Bayesian inference yields the highest overall prediction skill and is shown to be a valuable tool for covariate selection, while the predictions obtained under optimum CRPS estimation are the sharpest and give the best performance for high thresholds and quantiles. Copyright © 2012 John Wiley & Sons, Ltd.

Subfields: Atmospheric Science, Electrical and Electronic Engineering, Global and Planetary Change

View Paper: https://www.semanticscholar.org/paper/842c82873844860c5287b6e369ccbcc700870141

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Atmospheric Science

In Electrical and Electronic Engineering

In Global and Planetary Change

Citations in the corpus

Comparison of non-homogeneous regression models for probabilistic wind speed forecasting (2013, methodology): “To link the parameters of the predictive GEV distribution to the ensemble, we apply the Bayesian covariate selection algorithm described in Friederichs and Thorarinsdottir (2012). We assume a constant shape parameter ξ while the location μ and the scale σ may depend on the ensemble mean and variance”
Probabilistic quantitative precipitation forecasting using Ensemble Model Output Statistics (2013, background): “However, while COSMO-DE-EPS members have been constructed such that they all have comparable skill (Gebhardt et al., 2011), overfitting may be a price worth paying if one uses an EPS where some members are distinctly less skilled than others. A completely different weighting strategy (which we plan ”
Evaluating Probabilistic Forecasts with scoringRules (2017, background): “…parameter ξ < 1, and generalizes via location parameter µ ∈ R and scale parameter σ > 0, The CDFs and otherwise required functions are given by F ξ,µ,σ ( x ) = F ξ x − and for ξ = 0: F ξ ( x ) = exp ( − exp( − x )) for ξ > 0: Friederichs and Thorarinsdottir (2012) give an equivalent expression.”