Machine learning–based extreme event attribution
Science Advances · 23.08.2024 · 10 (34)
DOI: 10.1126/sciadv.adl3242 ↗Kurz gefasst
Fachartikel in der Zeitschrift Science Advances, erschienen am 23.08.2024. Verfasst von Jared T Trok und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Earth System Science, Stanford University, Stanford, CA, USA. Die Arbeit wurde bisher 58-mal zitiert (Crossref) und nennt 73 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.
Abstract (Originalsprache)
The observed increase in extreme weather has prompted recent methodological advances in extreme event attribution. We propose a machine learning–based approach that uses convolutional neural networks to create dynamically consistent counterfactual versions of historical extreme events under different levels of global mean temperature (GMT). We apply this technique to one recent extreme heat event (southcentral North America 2023) and several historical events that have been previously analyzed using established attribution methods. We estimate that temperatures during the southcentral North America event were 1.18° to 1.42°C warmer because of global warming and that similar events will occur 0.14 to 0.60 times per year at 2.0°C above preindustrial levels of GMT. Additionally, we find that the learned relationships between daily temperature and GMT are influenced by the seasonality of the forced temperature response and the daily meteorological conditions. Our results broadly agree with other attribution techniques, suggesting that machine learning can be used to perform rapid, low-cost attribution of extreme events.
Autor:innen und Institutionen
- Department of Earth System Science, Stanford University, Stanford, CA, USA.
- Department of Atmospheric Science, Colorado State University, Fort Collins, CO, USA.
- Department of Civil and Environmental Engineering, Colorado State University, Fort Collins, CO, USA.
- Doerr School of Sustainability, Stanford University, Stanford, CA, USA.
ORCID-Profile: Jared T Trok, Elizabeth A Barnes, Frances V Davenport, Noah S Diffenbaugh
Zitieren
APA
Trok, J. T., Barnes, E. A., Davenport, F. V., & Diffenbaugh, N. S. (2024). Machine learning–based extreme event attribution. Science Advances, 10(34). https://doi.org/10.1126/sciadv.adl3242
Vancouver
Trok JT, Barnes EA, Davenport FV, Diffenbaugh NS. Machine learning–based extreme event attribution. Science Advances. 2024;10(34). doi:10.1126/sciadv.adl3242
BibTeX
@article{Trok2024,
author = {Trok, Jared T and Barnes, Elizabeth A and Davenport, Frances V and Diffenbaugh, Noah S},
title = {Machine learning–based extreme event attribution},
journal = {Science Advances},
year = {2024},
volume = {10},
number = {34},
doi = {10.1126/sciadv.adl3242}
}
EUVIMED