Statistical Modeling of Spatial Extremes

Abstract

The areal modeling of the extremes of a natural process such as rainfall or temperature is important in environmental statistics; for example, understanding extreme areal rainfall is crucial in flood protection. This article reviews recent progress in the statistical modeling of spatial extremes, starting with sketches of the necessary elements of extreme value statistics and geostatistics. The main types of statistical models thus far proposed, based on latent variables, on copulas and on spatial max-stable processes, are described and then are compared by application to a data set on rainfall in Switzerland. Whereas latent variable modeling allows a better fit to marginal distributions, it fits the joint distributions of extremes poorly, so appropriately-chosen copula or max-stable models seem essential for successful spatial modeling of extremes.

Published in at http://dx.doi.org/10.1214/11-STS376 the Statistical Science (http://www.imstat.org/sts/) by the Institute of Mathematical Statistics (http://www.imstat.org)

References in corpus (6)

• Stationary max-stable fields associated to negative definite functions
• Spatial modeling of extreme snow depth
• On spatial extremes: with application to a rainfall problem
• Spatial extremes: Models for the stationary case
• Bayesian Inference from Composite Likelihoods, with an Application to Spatial Extremes
• Maximum empirical likelihood estimation of the spectral measure of an extreme-value distribution

Cited by in corpus (86)

• Uncertainty Quantification in Complex Simulation Models Using Ensemble Copula Coupling
• Space-time modelling of extreme events
• Extremes and Recurrence in Dynamical Systems
• Extremal t processes: Elliptical domain of attraction and a spectral representation
• Extended Generalised Pareto Models for Tail Estimation
• Efficient inference and simulation for elliptical Pareto processes
• Multivariate peaks over thresholds models
• Spatial Bayesian hierarchical modeling of precipitation extremes over a large domain
• Bayesian inference for the Brown-Resnick process, with an application to extreme low temperatures
• Modeling asymptotically independent spatial extremes based on Laplace random fields
• A probabilistic gridded product for daily precipitation extremes over the United States
• Conditional Modelling of Spatio-Temporal Extremes for Red Sea Surface Temperatures
• Bayesian regional flood frequency analysis for large catchments
• Anisotropic Brown-Resnick space-time processes: estimation and model assessment
• Spatial hierarchical modeling of threshold exceedances using rate mixtures
• Approximate Bayesian Computation with composite score functions
• A modeler's guide to extreme value software
• Spatio-temporal modelling of extreme storms
• Computationally efficient spatial modeling of annual maximum 24 hour precipitation. An application to data from Iceland
• Modelling sub-daily precipitation extremes with the blended generalised extreme value distribution
• Model-based inference of conditional extreme value distributions with hydrological applications
• Integration of max-stable processes and Bayesian model averaging to predict extreme climatic events in multi-model ensembles
• Aspects of likelihood inference
• A two-step approach to model precipitation extremes in California based on max-stable and marginal point processes
• Estimating space-time trend and dependence of heavy rainfall
• Explaining the unexplainable: leveraging extremal dependence to characterize the 2021 Pacific Northwest heatwave
• Optimal Bayesian design for model discrimination via classification
• Simulating flood event sets using extremal principal components
• ABC model selection for spatial extremes models applied to South Australian maximum temperature data
• Likelihood based inference for high-dimensional extreme value distributions
• Discussion of "Statistical Modeling of Spatial Extremes" by A. C. Davison, S. A. Padoan and M. Ribatet
• Discussion of "Statistical Modeling of Spatial Extremes" by A. C. Davison, S. A. Padoan and M. Ribatet
• Spatial deformation for non-stationary extremal dependence
• Extreme Dependence Models
• Estimation of Huesler-Reiss distributions and Brown-Resnick processes
• Exact simulation of max-stable processes
• Rank-based Estimation under Asymptotic Dependence and Independence, with Applications to Spatial Extremes
• On the Tail Behaviour of Aggregated Random Variables
• Conditional simulations of Brown-Resnick processes
• The MCMC split sampler: A block Gibbs sampling scheme for latent Gaussian models
• Estimating the limiting shape of bivariate scaled sample clouds: with additional benefits of self-consistent inference for existing extremal dependence properties
• Flexible space-time models for extreme data
• Hierarchical space-time modeling of exceedances with an application to rainfall data
• A semiparametric spatiotemporal Bayesian model for the bulk and extremes of the Fosberg Fire Weather Index
• Trend detection in GEV models
• Non-stationary max-stable models with an application to heavy rainfall data
• Probabilities of concurrent extremes
• Latent Gaussian Models for High-Dimensional Spatial Extremes
• High-order Composite Likelihood Inference for Max-Stable Distributions and Processes
• A Regionalisation Approach for Rainfall based on Extremal Dependence
• Automated, Efficient, and Practical Extreme Value Analysis with Environmental Applications
• Estimation of spatial max-stable models using threshold exceedances
• The Goldie Equation: III. Homomorphisms from Functional Equations
• Modelling multivariate extreme value distributions via Markov trees
• Censored pairwise likelihood-based tests for mixing coefficient of spatial max-mixture models
• $k$-means clustering of extremes
• Flexible models for nonstationary dependence: Methodology and examples
• Bayesian non-asymptotic extreme value models for environmental data
• Whittle estimation based on the extremal spectral density of a heavy-tailed random field
• Using spatial extreme-value theory with machine learning to model and understand spatially compounding weather extremes
• Fast and Scalable Inference for Spatial Extreme Value Models
• High-dimensional inference using the extremal skew-$t$ process
• Exploration and inference in spatial extremes using empirical basis functions
• Extremal dependence and spatial risk measures for insured losses due to extreme winds
• Factor Copula Models for Replicated Spatial Data
• Discussion of "Estimating the historical and future probabilities of large terrorist event" by Aaron Clauset and Ryan Woodard
• Conditional simulation of extremal Gaussian processes
• Modeling spatial extremes using normal mean-variance mixtures
• Modelling and simulating spatial extremes by combining extreme value theory with generative adversarial networks
• Inference for extreme spatial temperature events in a changing climate with application to Ireland
• Reliable inference for complex models by discriminative composite likelihood estimation
• An adaptive mixture-population Monte Carlo method for likelihood-free inference
• Max-stable processes and stationary systems of Lévy particles
• Section on the special year for mathematics of planet earth (MPE 2013)
• Extremal behavior of squared Bessel processes attracted by the Brown-Resnick process
• A Dimension-Reduced Multivariate Spatial Model for Extreme Events: Balancing Flexibility and Scalability
• Post-processing of wind gusts from COSMO-REA6 with a spatial Bayesian hierarchical extreme value model
• Bayesian hierarchical modeling of extreme hourly precipitation in Norway
• CRPS M-estimation for max-stable models
• Design loads for wave impacts -- introducing the Probabilistic Adaptive Screening (PAS) method for predicting extreme non-linear loads on maritime structures
• On Computationally-Scalable Spatio-Temporal Regression Clustering of Precipitation Threshold Excesses
• Event-controlled constructions of random fields of maxima with non-max-stable dependence
• Semiparametric estimation for space-time max-stable processes: F -madogram-based estimation approach
• Improved return level estimation via a weighted likelihood, latent spatial extremes model
• Exploiting Multi-Core Architectures for Reduced-Variance Estimation with Intractable Likelihoods
• Spatiotemporal analysis of urban heatwaves using Tukey g-and-h random field models