Exploiting a variational auto-encoder to represent the evolution of sudden stratospheric warmings

Yi-Chang Chen, Yu‐Chiao Liang, Chien-Ming Wu, Jin-De Huang, Simon H Lee, Yih Wang, Yi-Jhen Zeng
{"title":"Exploiting a variational auto-encoder to represent the evolution of sudden stratospheric warmings","authors":"Yi-Chang Chen, Yu‐Chiao Liang, Chien-Ming Wu, Jin-De Huang, Simon H Lee, Yih Wang, Yi-Jhen Zeng","doi":"10.1088/2752-5295/ad3a0d","DOIUrl":null,"url":null,"abstract":"\n Sudden stratospheric warmings (SSWs) are the most dramatic events in the wintertime stratosphere. Such extreme events are characterized by substantial disruption to the stratospheric polar vortex, which can be categorized into displacement and splitting types depending on the morphology of the disrupted vortex. Moreover, SSWs are usually followed by anomalous tropospheric circulation regimes that are important for subseasonal-to-seasonal prediction. Thus, monitoring the genesis and evolution of SSWs is crucial and deserves further advancement. Despite several analysis methods that have been used to study the evolution of SSWs, the ability of deep learning methods has not yet been explored, mainly due to the relative scarcity of observed events. To overcome the limited observational sample size, we use data from historical simulations of the Whole Atmosphere Community Climate Model version 6 to identify thousands of simulated SSWs, and use their spatial patterns to train the deep learning model. We utilize a convolutional neural network combined with a variational auto-encoder – a generative deep learning model – to construct a phase diagram that characterizes the SSW evolution. This approach not only allows us to create a latent space that encapsulates the essential features of the vortex structure during SSWs, but also offers new insights into its spatiotemporal evolution mapping onto the phase diagram. The constructed phase diagram depicts a continuous transition of the vortex pattern during SSWs. Notably, it provides a new perspective for discussing the evolutionary paths of SSWs: the variational auto-encoder gives a better-reconstructed vortex morphology and more clearly organized vortex regimes for both displacement-type and split-type events than those obtained from principal component analysis. Our results provide an innovative phase diagram to portray the evolution of SSWs, in which particularly the splitting SSWs are better characterized. Our findings support the future use of deep learning techniques to study the underlying dynamics of extreme stratospheric vortex phenomena, and to establish a benchmark to evaluate model performance in simulating SSWs.","PeriodicalId":432508,"journal":{"name":"Environmental Research: Climate","volume":"2 4","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2024-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Environmental Research: Climate","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1088/2752-5295/ad3a0d","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

Abstract

Sudden stratospheric warmings (SSWs) are the most dramatic events in the wintertime stratosphere. Such extreme events are characterized by substantial disruption to the stratospheric polar vortex, which can be categorized into displacement and splitting types depending on the morphology of the disrupted vortex. Moreover, SSWs are usually followed by anomalous tropospheric circulation regimes that are important for subseasonal-to-seasonal prediction. Thus, monitoring the genesis and evolution of SSWs is crucial and deserves further advancement. Despite several analysis methods that have been used to study the evolution of SSWs, the ability of deep learning methods has not yet been explored, mainly due to the relative scarcity of observed events. To overcome the limited observational sample size, we use data from historical simulations of the Whole Atmosphere Community Climate Model version 6 to identify thousands of simulated SSWs, and use their spatial patterns to train the deep learning model. We utilize a convolutional neural network combined with a variational auto-encoder – a generative deep learning model – to construct a phase diagram that characterizes the SSW evolution. This approach not only allows us to create a latent space that encapsulates the essential features of the vortex structure during SSWs, but also offers new insights into its spatiotemporal evolution mapping onto the phase diagram. The constructed phase diagram depicts a continuous transition of the vortex pattern during SSWs. Notably, it provides a new perspective for discussing the evolutionary paths of SSWs: the variational auto-encoder gives a better-reconstructed vortex morphology and more clearly organized vortex regimes for both displacement-type and split-type events than those obtained from principal component analysis. Our results provide an innovative phase diagram to portray the evolution of SSWs, in which particularly the splitting SSWs are better characterized. Our findings support the future use of deep learning techniques to study the underlying dynamics of extreme stratospheric vortex phenomena, and to establish a benchmark to evaluate model performance in simulating SSWs.
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
利用变异自动编码器表示平流层突然变暖的演变过程
平流层突然变暖(SSWs)是冬季平流层中最引人注目的事件。这种极端事件的特点是平流层极地涡旋受到严重破坏,根据被破坏涡旋的形态,可分为位移型和分裂型。此外,SSW 之后通常会出现异常的对流层环流机制,这对副季节到季节预测非常重要。因此,监测 SSW 的形成和演变至关重要,值得进一步推进。尽管已有多种分析方法用于研究 SSW 的演变,但深度学习方法的能力尚未得到探索,这主要是由于观测到的事件相对较少。为了克服观测样本量有限的问题,我们利用全大气社区气候模式第 6 版的历史模拟数据来识别成千上万的模拟 SSW,并利用它们的空间模式来训练深度学习模型。我们利用卷积神经网络结合变异自动编码器--一种生成式深度学习模型--来构建表征 SSW 演化的相图。这种方法不仅使我们能够创建一个潜在空间,囊括 SSW 期间涡旋结构的基本特征,而且还为我们提供了关于其与相图映射的时空演变的新见解。所构建的相图描述了 SSW 期间涡旋模式的连续转变。值得注意的是,它为讨论 SSW 的演变路径提供了一个新的视角:与主成分分析法相比,变异自动编码器能更好地重建涡旋形态,并能更清晰地组织位移型和分裂型事件的涡旋机制。我们的研究结果提供了一种创新的相图来描述 SSW 的演变,其中分裂 SSW 的特征更为明显。我们的研究结果支持未来使用深度学习技术来研究极端平流层涡旋现象的基本动态,并建立一个基准来评估模拟 SSW 的模型性能。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 去求助
来源期刊
自引率
0.00%
发文量
0
期刊最新文献
Improvement of decadal predictions of monthly extreme Mei-yu rainfall via a causality guided approach Climate classification systems for validating Earth system models Net evaporation-induced mangrove area loss across low-lying Caribbean islands Using analogues to predict changes in future UK heatwaves Linking local climate scenarios to global warming levels: applicability, prospects and uncertainties
×
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
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 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 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1