Home > Research > Publications & Outputs > MODELLING EXTREMES OF SPATIAL AGGREGATES OF PRE...

Electronic data

  • SCEdraft_AOAS_v2_2

    Accepted author manuscript, 3.32 MB, PDF document

    Available under license: CC BY-NC: Creative Commons Attribution-NonCommercial 4.0 International License

Links

Text available via DOI:

View graph of relations

MODELLING EXTREMES OF SPATIAL AGGREGATES OF PRECIPITATION USING CONDITIONAL METHODS

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Published

Standard

MODELLING EXTREMES OF SPATIAL AGGREGATES OF PRECIPITATION USING CONDITIONAL METHODS. / Richards, Jordan; Tawn, Jonathan; Brown, Simon.
In: Annals of Applied Statistics, Vol. 16, No. 4, 31.12.2022, p. 2693-2713.

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Harvard

APA

Vancouver

Richards J, Tawn J, Brown S. MODELLING EXTREMES OF SPATIAL AGGREGATES OF PRECIPITATION USING CONDITIONAL METHODS. Annals of Applied Statistics. 2022 Dec 31;16(4):2693-2713. doi: 10.1214/22-AOAS1609

Author

Richards, Jordan ; Tawn, Jonathan ; Brown, Simon. / MODELLING EXTREMES OF SPATIAL AGGREGATES OF PRECIPITATION USING CONDITIONAL METHODS. In: Annals of Applied Statistics. 2022 ; Vol. 16, No. 4. pp. 2693-2713.

Bibtex

@article{e683ea92dd8e41e08e45d5cdddb8e0c0,
title = "MODELLING EXTREMES OF SPATIAL AGGREGATES OF PRECIPITATION USING CONDITIONAL METHODS",
abstract = "Inference on the extremal behaviour of spatial aggregates of precipitationis important for quantifying river flood risk. There are two classes of previousapproach, with one failing to ensure self-consistency in inference acrossdifferent regions of aggregation and the other imposing highly restrictive assumptions. To overcome these issues, we propose a model for high-resolutionprecipitation data, from which we can simulate realistic fields and explorethe behaviour of spatial aggregates. Recent developments have seen spatialextensions of the Heffernan and Tawn (2004) model for conditional multivariateextremes, which can handle a wide range of dependence structures.Our contribution is twofold: extensions and improvements of this approachand its model inference for high-dimensional data; and a novel framework forderiving aggregates addressing edge effects and sub-regions without rain.Weapply our modelling approach to gridded East-Anglia, UK precipitation data.Return-level curves for spatial aggregates over different regions of varioussizes are estimated and shown to fit very well to the data.",
author = "Jordan Richards and Jonathan Tawn and Simon Brown",
year = "2022",
month = dec,
day = "31",
doi = "10.1214/22-AOAS1609",
language = "English",
volume = "16",
pages = "2693--2713",
journal = "Annals of Applied Statistics",
issn = "1932-6157",
publisher = "Institute of Mathematical Statistics",
number = "4",

}

RIS

TY - JOUR

T1 - MODELLING EXTREMES OF SPATIAL AGGREGATES OF PRECIPITATION USING CONDITIONAL METHODS

AU - Richards, Jordan

AU - Tawn, Jonathan

AU - Brown, Simon

PY - 2022/12/31

Y1 - 2022/12/31

N2 - Inference on the extremal behaviour of spatial aggregates of precipitationis important for quantifying river flood risk. There are two classes of previousapproach, with one failing to ensure self-consistency in inference acrossdifferent regions of aggregation and the other imposing highly restrictive assumptions. To overcome these issues, we propose a model for high-resolutionprecipitation data, from which we can simulate realistic fields and explorethe behaviour of spatial aggregates. Recent developments have seen spatialextensions of the Heffernan and Tawn (2004) model for conditional multivariateextremes, which can handle a wide range of dependence structures.Our contribution is twofold: extensions and improvements of this approachand its model inference for high-dimensional data; and a novel framework forderiving aggregates addressing edge effects and sub-regions without rain.Weapply our modelling approach to gridded East-Anglia, UK precipitation data.Return-level curves for spatial aggregates over different regions of varioussizes are estimated and shown to fit very well to the data.

AB - Inference on the extremal behaviour of spatial aggregates of precipitationis important for quantifying river flood risk. There are two classes of previousapproach, with one failing to ensure self-consistency in inference acrossdifferent regions of aggregation and the other imposing highly restrictive assumptions. To overcome these issues, we propose a model for high-resolutionprecipitation data, from which we can simulate realistic fields and explorethe behaviour of spatial aggregates. Recent developments have seen spatialextensions of the Heffernan and Tawn (2004) model for conditional multivariateextremes, which can handle a wide range of dependence structures.Our contribution is twofold: extensions and improvements of this approachand its model inference for high-dimensional data; and a novel framework forderiving aggregates addressing edge effects and sub-regions without rain.Weapply our modelling approach to gridded East-Anglia, UK precipitation data.Return-level curves for spatial aggregates over different regions of varioussizes are estimated and shown to fit very well to the data.

U2 - 10.1214/22-AOAS1609

DO - 10.1214/22-AOAS1609

M3 - Journal article

VL - 16

SP - 2693

EP - 2713

JO - Annals of Applied Statistics

JF - Annals of Applied Statistics

SN - 1932-6157

IS - 4

ER -