Structural analysis of spatio-temporal threshold exceedances

被引:9
作者
Angulo, J. M. [1 ]
Madrid, A. E. [1 ]
机构
[1] Univ Granada, Fac Sci, Dept Stat & Operat Res, E-18071 Granada, Spain
关键词
blurring; deformation; extremes; spatio-temporal processes; threshold exceedances; ESTIMATING DEFORMATIONS; SAMPLING DESIGN; RANDOM-FIELDS; COVARIANCE; MODELS; MULTIVARIATE; DIMENSION;
D O I
10.1002/env.1018
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
Due to both the complexity of real systems and the technical difficulties inherent to extremal analysis, the statistics of extremes in spatio-temporal processes has become one of the most challenging research areas in relation to the increasingly demanding interest on risk assessment tools in many fields of application. Recent advances in spatio-temporal statistical analysis are focused, in particular, on the formulation and study of new model families, flexible to represent such real complexities and, at the same time, suitable for technical treatment and interpretation, as well as on related system dynamics problems. In this paper, significant characteristics of threshold exceedances with reference to structural properties of the processes generating such events, particularly in the context of input/output systems, are analyzed. Specifically, the effect of spatial deformation and blurring transformations on the second order structure and the geometrical properties of excursion sets is studied and illustrated through some simulated cases. A spatio-temporal model based on spatial deformation and blurring, which provides a suitable representation for a variety of environmental applications, is formulated, and further aspects regarding the temporal structure of threshold exceedances are explored and discussed. Copyright (C) 2009 John Wiley & Sons, Ltd.
引用
收藏
页码:415 / 438
页数:24
相关论文
共 58 条
[1]  
Adler R.J, 2007, Springer Monographs in Mathematics
[2]   Some new random field tools for spatial analysis [J].
Adler, Robert J. .
STOCHASTIC ENVIRONMENTAL RESEARCH AND RISK ASSESSMENT, 2008, 22 (06) :809-822
[3]  
Albeverio S, 2006, Extreme events in nature and society
[4]  
Aldous D., 1989, Probability approximations via the Poisson clumping heuristic, V77
[5]   STRUCTURAL IMAGE-RESTORATION THROUGH DEFORMABLE TEMPLATES [J].
AMIT, Y ;
GRENANDER, U ;
PICCIONI, M .
JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION, 1991, 86 (414) :376-387
[6]   Estimating deformations of isotropic Gaussian random fields on the plane [J].
Anderes, Ethan B. ;
Stein, Michael L. .
ANNALS OF STATISTICS, 2008, 36 (02) :719-741
[7]  
Angulo JM, 2000, STOCH ENV RES RISK A, V14, P412
[8]   Generalized approaches to spatial sampling design [J].
Angulo, JM ;
Ruiz-Medina, MD ;
Alonso, FJ ;
Bueso, MC .
ENVIRONMETRICS, 2005, 16 (05) :523-534
[9]   Random perturbation methods applied to multivariate spatial sampling design [J].
Angulo, JM ;
Bueso, MC .
ENVIRONMETRICS, 2001, 12 (07) :631-646
[10]  
[Anonymous], 2004, Statistics of extremes: theory and applications