Home > Research > Publications & Outputs > Modeling of spatial extremes in environmental d...

Electronic data

  • EDS_opinion_final

    Accepted author manuscript, 5.05 MB, PDF document

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

Links

Text available via DOI:

View graph of relations

Modeling of spatial extremes in environmental data science: Time to move away from max-stable processes

Research output: Contribution to Journal/MagazineComment/debatepeer-review

E-pub ahead of print

Standard

Modeling of spatial extremes in environmental data science: Time to move away from max-stable processes. / Huser, Raphael; Opitz, Thomas; Wadsworth, Jennifer.
In: Environmental Data Science, Vol. 4, No. 1, e3, 31.12.2025.

Research output: Contribution to Journal/MagazineComment/debatepeer-review

Harvard

APA

Huser, R., Opitz, T., & Wadsworth, J. (2025). Modeling of spatial extremes in environmental data science: Time to move away from max-stable processes. Environmental Data Science, 4(1), Article e3. Advance online publication. https://doi.org/10.1017/eds.2024.54

Vancouver

Huser R, Opitz T, Wadsworth J. Modeling of spatial extremes in environmental data science: Time to move away from max-stable processes. Environmental Data Science. 2025 Dec 31;4(1):e3. Epub 2025 Jan 15. doi: 10.1017/eds.2024.54

Author

Huser, Raphael ; Opitz, Thomas ; Wadsworth, Jennifer. / Modeling of spatial extremes in environmental data science : Time to move away from max-stable processes. In: Environmental Data Science. 2025 ; Vol. 4, No. 1.

Bibtex

@article{89ca4ba071144b609ddd5f3b6938eccf,
title = "Modeling of spatial extremes in environmental data science: Time to move away from max-stable processes",
abstract = "Environmental data science for spatial extremes has traditionally relied heavily on max-stable processes. Even though the popularity of these models has perhaps peaked with statisticians, they are still perceived and considered as the “state of the art” in many applied fields. However, while the asymptotic theory supporting the use of max-stable processes is mathematically rigorous and comprehensive, we think that it has also been overused, if not misused, in environmental applications, to the detriment of more purposeful and meticulously validated models. In this article, we review the main limitations of max-stable process models, and strongly argue against their systematic use in environmental studies. Alternative solutions based on more flexible frameworks using the exceedances of variables above appropriately chosen high thresholds are discussed, and an outlook on future research is given. We consider the opportunities offered by hybridizing machine learning with extreme-value statistics, highlighting seven key recommendations moving forward.",
author = "Raphael Huser and Thomas Opitz and Jennifer Wadsworth",
year = "2025",
month = jan,
day = "15",
doi = "10.1017/eds.2024.54",
language = "English",
volume = "4",
journal = "Environmental Data Science",
publisher = "Cambridge: Cambridge University Press.",
number = "1",

}

RIS

TY - JOUR

T1 - Modeling of spatial extremes in environmental data science

T2 - Time to move away from max-stable processes

AU - Huser, Raphael

AU - Opitz, Thomas

AU - Wadsworth, Jennifer

PY - 2025/1/15

Y1 - 2025/1/15

N2 - Environmental data science for spatial extremes has traditionally relied heavily on max-stable processes. Even though the popularity of these models has perhaps peaked with statisticians, they are still perceived and considered as the “state of the art” in many applied fields. However, while the asymptotic theory supporting the use of max-stable processes is mathematically rigorous and comprehensive, we think that it has also been overused, if not misused, in environmental applications, to the detriment of more purposeful and meticulously validated models. In this article, we review the main limitations of max-stable process models, and strongly argue against their systematic use in environmental studies. Alternative solutions based on more flexible frameworks using the exceedances of variables above appropriately chosen high thresholds are discussed, and an outlook on future research is given. We consider the opportunities offered by hybridizing machine learning with extreme-value statistics, highlighting seven key recommendations moving forward.

AB - Environmental data science for spatial extremes has traditionally relied heavily on max-stable processes. Even though the popularity of these models has perhaps peaked with statisticians, they are still perceived and considered as the “state of the art” in many applied fields. However, while the asymptotic theory supporting the use of max-stable processes is mathematically rigorous and comprehensive, we think that it has also been overused, if not misused, in environmental applications, to the detriment of more purposeful and meticulously validated models. In this article, we review the main limitations of max-stable process models, and strongly argue against their systematic use in environmental studies. Alternative solutions based on more flexible frameworks using the exceedances of variables above appropriately chosen high thresholds are discussed, and an outlook on future research is given. We consider the opportunities offered by hybridizing machine learning with extreme-value statistics, highlighting seven key recommendations moving forward.

U2 - 10.1017/eds.2024.54

DO - 10.1017/eds.2024.54

M3 - Comment/debate

VL - 4

JO - Environmental Data Science

JF - Environmental Data Science

IS - 1

M1 - e3

ER -