将热量收支动态纳入基于变压器的深度学习模型,以熟练预测厄尔尼诺/南方涛动

IF 8.5 1区 地球科学 Q1 METEOROLOGY & ATMOSPHERIC SCIENCES npj Climate and Atmospheric Science Pub Date : 2024-09-06 DOI:10.1038/s41612-024-00741-y
Bin Mu, Yuehan Cui, Shijin Yuan, Bo Qin
{"title":"将热量收支动态纳入基于变压器的深度学习模型,以熟练预测厄尔尼诺/南方涛动","authors":"Bin Mu, Yuehan Cui, Shijin Yuan, Bo Qin","doi":"10.1038/s41612-024-00741-y","DOIUrl":null,"url":null,"abstract":"While deep learning models have shown promising capabilities in ENSO prediction, their inherent black-box nature often leads to a lack of physical consistency and interpretability. Here, we introduce ENSO-PhyNet, a Transformer-based model for ENSO prediction, which incorporates heat budget dynamical processes through self-attention computations. The model predicts sea surface temperature (SST) in the equatorial Pacific and achieves skillful predictions of the Niño 3.4 index with a lead time of up to 22 months. The self-attention maps reveal how the model makes predictions by focusing on specific processes in certain regions. Case analyses of recent El Niño and La Niña events underscore the impact of thermocline feedback and zonal advection feedback on the warming of the 2015 event, as well as the crucial role of anomalous easterlies in the emergence of the second-year La Niña in 2021. These findings demonstrate the model’s interpretability and its ability to identify signals that are physically consistent with the development of ENSO events.","PeriodicalId":19438,"journal":{"name":"npj Climate and Atmospheric Science","volume":" ","pages":"1-15"},"PeriodicalIF":8.5000,"publicationDate":"2024-09-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.nature.com/articles/s41612-024-00741-y.pdf","citationCount":"0","resultStr":"{\"title\":\"Incorporating heat budget dynamics in a Transformer-based deep learning model for skillful ENSO prediction\",\"authors\":\"Bin Mu, Yuehan Cui, Shijin Yuan, Bo Qin\",\"doi\":\"10.1038/s41612-024-00741-y\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"While deep learning models have shown promising capabilities in ENSO prediction, their inherent black-box nature often leads to a lack of physical consistency and interpretability. Here, we introduce ENSO-PhyNet, a Transformer-based model for ENSO prediction, which incorporates heat budget dynamical processes through self-attention computations. The model predicts sea surface temperature (SST) in the equatorial Pacific and achieves skillful predictions of the Niño 3.4 index with a lead time of up to 22 months. The self-attention maps reveal how the model makes predictions by focusing on specific processes in certain regions. Case analyses of recent El Niño and La Niña events underscore the impact of thermocline feedback and zonal advection feedback on the warming of the 2015 event, as well as the crucial role of anomalous easterlies in the emergence of the second-year La Niña in 2021. These findings demonstrate the model’s interpretability and its ability to identify signals that are physically consistent with the development of ENSO events.\",\"PeriodicalId\":19438,\"journal\":{\"name\":\"npj Climate and Atmospheric Science\",\"volume\":\" \",\"pages\":\"1-15\"},\"PeriodicalIF\":8.5000,\"publicationDate\":\"2024-09-06\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://www.nature.com/articles/s41612-024-00741-y.pdf\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"npj Climate and Atmospheric Science\",\"FirstCategoryId\":\"89\",\"ListUrlMain\":\"https://www.nature.com/articles/s41612-024-00741-y\",\"RegionNum\":1,\"RegionCategory\":\"地球科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"METEOROLOGY & ATMOSPHERIC SCIENCES\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"npj Climate and Atmospheric Science","FirstCategoryId":"89","ListUrlMain":"https://www.nature.com/articles/s41612-024-00741-y","RegionNum":1,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"METEOROLOGY & ATMOSPHERIC SCIENCES","Score":null,"Total":0}
引用次数: 0

摘要

虽然深度学习模型在厄尔尼诺/南方涛动预测中表现出了良好的能力,但其固有的黑箱性质往往导致缺乏物理一致性和可解释性。在此,我们介绍一种基于 Transformer 的厄尔尼诺/南方涛动预测模型 ENSO-PhyNet,该模型通过自我关注计算纳入了热预算动态过程。该模型可预测赤道太平洋的海面温度(SST),并能在长达 22 个月的时间内准确预测 3.4 级厄尔尼诺指数。自我关注图揭示了该模式如何通过关注某些区域的特定过程来进行预测。对近期厄尔尼诺和拉尼娜事件的案例分析强调了热层反馈和地带平流反馈对 2015 年事件变暖的影响,以及异常东风对 2021 年第二年拉尼娜出现的关键作用。这些发现证明了该模式的可解释性及其识别与厄尔尼诺/南方涛动事件发展相一致的物理信号的能力。
本文章由计算机程序翻译,如有差异,请以英文原文为准。

摘要图片

摘要图片

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
Incorporating heat budget dynamics in a Transformer-based deep learning model for skillful ENSO prediction
While deep learning models have shown promising capabilities in ENSO prediction, their inherent black-box nature often leads to a lack of physical consistency and interpretability. Here, we introduce ENSO-PhyNet, a Transformer-based model for ENSO prediction, which incorporates heat budget dynamical processes through self-attention computations. The model predicts sea surface temperature (SST) in the equatorial Pacific and achieves skillful predictions of the Niño 3.4 index with a lead time of up to 22 months. The self-attention maps reveal how the model makes predictions by focusing on specific processes in certain regions. Case analyses of recent El Niño and La Niña events underscore the impact of thermocline feedback and zonal advection feedback on the warming of the 2015 event, as well as the crucial role of anomalous easterlies in the emergence of the second-year La Niña in 2021. These findings demonstrate the model’s interpretability and its ability to identify signals that are physically consistent with the development of ENSO events.
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
npj Climate and Atmospheric Science
npj Climate and Atmospheric Science Earth and Planetary Sciences-Atmospheric Science
CiteScore
8.80
自引率
3.30%
发文量
87
审稿时长
21 weeks
期刊介绍: npj Climate and Atmospheric Science is an open-access journal encompassing the relevant physical, chemical, and biological aspects of atmospheric and climate science. The journal places particular emphasis on regional studies that unveil new insights into specific localities, including examinations of local atmospheric composition, such as aerosols. The range of topics covered by the journal includes climate dynamics, climate variability, weather and climate prediction, climate change, ocean dynamics, weather extremes, air pollution, atmospheric chemistry (including aerosols), the hydrological cycle, and atmosphere–ocean and atmosphere–land interactions. The journal welcomes studies employing a diverse array of methods, including numerical and statistical modeling, the development and application of in situ observational techniques, remote sensing, and the development or evaluation of new reanalyses.
期刊最新文献
Mortality burden of diabetes attributable to high temperature and heatwave under climate change scenarios in China Impact of fuel sulfur regulations on carbonaceous particle emission from a marine engine A new global carbon flux estimation methodology by assimilation of both in situ and satellite CO2 observations Dominance of open burning signatures in PM2.5 near coal plant should redefine pollutant priorities of India Climate model trend errors are evident in seasonal forecasts at short leads
×
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