利用人工智能数据驱动的全球天气模型进行气候归因:2017 年奥罗维尔大坝极端大气河流分析

Jorge Baño-Medina, Agniv Sengupta, Allison Michaelis, Luca Delle Monache, Julie Kalansky, Duncan Watson-Parris
{"title":"利用人工智能数据驱动的全球天气模型进行气候归因:2017 年奥罗维尔大坝极端大气河流分析","authors":"Jorge Baño-Medina, Agniv Sengupta, Allison Michaelis, Luca Delle Monache, Julie Kalansky, Duncan Watson-Parris","doi":"arxiv-2409.11605","DOIUrl":null,"url":null,"abstract":"AI data-driven models (Graphcast, Pangu Weather, Fourcastnet, and SFNO) are\nexplored for storyline-based climate attribution due to their short inference\ntimes, which can accelerate the number of events studied, and provide real time\nattributions when public attention is heightened. The analysis is framed on the\nextreme atmospheric river episode of February 2017 that contributed to the\nOroville dam spillway incident in Northern California. Past and future\nsimulations are generated by perturbing the initial conditions with the\npre-industrial and the late-21st century temperature climate change signals,\nrespectively. The simulations are compared to results from a dynamical model\nwhich represents plausible pseudo-realities under both climate environments.\nOverall, the AI models show promising results, projecting a 5-6 % increase in\nthe integrated water vapor over the Oroville dam in the present day compared to\nthe pre-industrial, in agreement with the dynamical model. Different\ngeopotential-moisture-temperature dependencies are unveiled for each of the\nAI-models tested, providing valuable information for understanding the\nphysicality of the attribution response. However, the AI models tend to\nsimulate weaker attribution values than the pseudo-reality imagined by the\ndynamical model, suggesting some reduced extrapolation skill, especially for\nthe late-21st century regime. Large ensembles generated with an AI model (>500\nmembers) produced statistically significant present-day to pre-industrial\nattribution results, unlike the >20-member ensemble from the dynamical model.\nThis analysis highlights the potential of AI models to conduct attribution\nanalysis, while emphasizing future lines of work on explainable artificial\nintelligence to gain confidence in these tools, which can enable reliable\nattribution studies in real-time.","PeriodicalId":501166,"journal":{"name":"arXiv - PHYS - Atmospheric and Oceanic Physics","volume":"52 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2024-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Harnessing AI data-driven global weather models for climate attribution: An analysis of the 2017 Oroville Dam extreme atmospheric river\",\"authors\":\"Jorge Baño-Medina, Agniv Sengupta, Allison Michaelis, Luca Delle Monache, Julie Kalansky, Duncan Watson-Parris\",\"doi\":\"arxiv-2409.11605\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"AI data-driven models (Graphcast, Pangu Weather, Fourcastnet, and SFNO) are\\nexplored for storyline-based climate attribution due to their short inference\\ntimes, which can accelerate the number of events studied, and provide real time\\nattributions when public attention is heightened. The analysis is framed on the\\nextreme atmospheric river episode of February 2017 that contributed to the\\nOroville dam spillway incident in Northern California. Past and future\\nsimulations are generated by perturbing the initial conditions with the\\npre-industrial and the late-21st century temperature climate change signals,\\nrespectively. The simulations are compared to results from a dynamical model\\nwhich represents plausible pseudo-realities under both climate environments.\\nOverall, the AI models show promising results, projecting a 5-6 % increase in\\nthe integrated water vapor over the Oroville dam in the present day compared to\\nthe pre-industrial, in agreement with the dynamical model. Different\\ngeopotential-moisture-temperature dependencies are unveiled for each of the\\nAI-models tested, providing valuable information for understanding the\\nphysicality of the attribution response. However, the AI models tend to\\nsimulate weaker attribution values than the pseudo-reality imagined by the\\ndynamical model, suggesting some reduced extrapolation skill, especially for\\nthe late-21st century regime. Large ensembles generated with an AI model (>500\\nmembers) produced statistically significant present-day to pre-industrial\\nattribution results, unlike the >20-member ensemble from the dynamical model.\\nThis analysis highlights the potential of AI models to conduct attribution\\nanalysis, while emphasizing future lines of work on explainable artificial\\nintelligence to gain confidence in these tools, which can enable reliable\\nattribution studies in real-time.\",\"PeriodicalId\":501166,\"journal\":{\"name\":\"arXiv - PHYS - Atmospheric and Oceanic Physics\",\"volume\":\"52 1\",\"pages\":\"\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-09-17\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"arXiv - PHYS - Atmospheric and Oceanic Physics\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/arxiv-2409.11605\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - PHYS - Atmospheric and Oceanic Physics","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2409.11605","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

摘要

人工智能数据驱动模型(Graphcast、盘古气象、Fourcastnet 和 SFNO)因其推断时间短,可加快研究事件的数量,并在公众关注度提高时提供实时归因,因此被用于基于故事情节的气候归因研究。该分析以 2017 年 2 月导致北加州奥罗维尔大坝泄洪道事件的极端大气河流事件为框架。通过分别使用工业化前和 21 世纪晚期的温度气候变化信号对初始条件进行扰动,生成了过去和未来模拟。总体而言,人工智能模型显示出良好的结果,预测与工业化前相比,目前奥罗维尔大坝上空的综合水汽增加了 5-6%,这与动力学模型一致。所测试的每个人工智能模型都揭示了不同的地势-水汽-温度依赖关系,为理解归因响应的物理性提供了有价值的信息。然而,人工智能模式模拟的归因值往往弱于动力模式想象的假现实,这表明外推技能有所下降,特别是在 21 世纪晚期。用人工智能模型生成的大型集合(大于 500 个成员)产生了具有统计意义的从现在到工业化前的归因结果,这与动力学模型生成的大于 20 个成员的集合不同。这项分析突出了人工智能模型进行归因分析的潜力,同时强调了可解释人工智能的未来工作方向,以获得对这些工具的信心,从而能够实时进行可靠的归因研究。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Harnessing AI data-driven global weather models for climate attribution: An analysis of the 2017 Oroville Dam extreme atmospheric river
AI data-driven models (Graphcast, Pangu Weather, Fourcastnet, and SFNO) are explored for storyline-based climate attribution due to their short inference times, which can accelerate the number of events studied, and provide real time attributions when public attention is heightened. The analysis is framed on the extreme atmospheric river episode of February 2017 that contributed to the Oroville dam spillway incident in Northern California. Past and future simulations are generated by perturbing the initial conditions with the pre-industrial and the late-21st century temperature climate change signals, respectively. The simulations are compared to results from a dynamical model which represents plausible pseudo-realities under both climate environments. Overall, the AI models show promising results, projecting a 5-6 % increase in the integrated water vapor over the Oroville dam in the present day compared to the pre-industrial, in agreement with the dynamical model. Different geopotential-moisture-temperature dependencies are unveiled for each of the AI-models tested, providing valuable information for understanding the physicality of the attribution response. However, the AI models tend to simulate weaker attribution values than the pseudo-reality imagined by the dynamical model, suggesting some reduced extrapolation skill, especially for the late-21st century regime. Large ensembles generated with an AI model (>500 members) produced statistically significant present-day to pre-industrial attribution results, unlike the >20-member ensemble from the dynamical model. This analysis highlights the potential of AI models to conduct attribution analysis, while emphasizing future lines of work on explainable artificial intelligence to gain confidence in these tools, which can enable reliable attribution studies in real-time.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信