使用黑森近似和反向传播的4D-Var应用于自动可微数值和机器学习模型

IF 4.4 2区 地球科学 Q1 METEOROLOGY & ATMOSPHERIC SCIENCES
Kylen Solvik, Stephen G. Penny, Stephan Hoyer
{"title":"使用黑森近似和反向传播的4D-Var应用于自动可微数值和机器学习模型","authors":"Kylen Solvik,&nbsp;Stephen G. Penny,&nbsp;Stephan Hoyer","doi":"10.1029/2024MS004608","DOIUrl":null,"url":null,"abstract":"<p>Constraining a numerical weather prediction (NWP) model with observations via 4D variational (4D-Var) Data assimilation (DA) is often difficult to implement due to the need to develop and maintain a software-based tangent linear model and adjoint model. One of the most common 4D-Var algorithms uses an incremental update procedure, which has been shown to be an approximation of the Gauss-Newton method. Here we demonstrate that when using a forecast model that supports flexible automatic differentiation, an efficient and in some cases more accurate alternative approximation of the Gauss-Newton method can be applied by combining backpropagation of errors with a Hessian approximation. This approach can be used with either a conventional physical model implemented with automatic differentiation or a machine learning (ML) based surrogate model. We test the new approach on a variety of Lorenz-96 and quasi-geostrophic models. The results indicate potential for a deeper integration of modeling, DA, and new technologies in a next-generation of operational forecast systems that leverage weather models designed to support flexible, on-the-fly automatic differentiation.</p>","PeriodicalId":14881,"journal":{"name":"Journal of Advances in Modeling Earth Systems","volume":"17 4","pages":""},"PeriodicalIF":4.4000,"publicationDate":"2025-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1029/2024MS004608","citationCount":"0","resultStr":"{\"title\":\"4D-Var Using Hessian Approximation and Backpropagation Applied to Automatically Differentiable Numerical and Machine Learning Models\",\"authors\":\"Kylen Solvik,&nbsp;Stephen G. Penny,&nbsp;Stephan Hoyer\",\"doi\":\"10.1029/2024MS004608\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p>Constraining a numerical weather prediction (NWP) model with observations via 4D variational (4D-Var) Data assimilation (DA) is often difficult to implement due to the need to develop and maintain a software-based tangent linear model and adjoint model. One of the most common 4D-Var algorithms uses an incremental update procedure, which has been shown to be an approximation of the Gauss-Newton method. Here we demonstrate that when using a forecast model that supports flexible automatic differentiation, an efficient and in some cases more accurate alternative approximation of the Gauss-Newton method can be applied by combining backpropagation of errors with a Hessian approximation. This approach can be used with either a conventional physical model implemented with automatic differentiation or a machine learning (ML) based surrogate model. We test the new approach on a variety of Lorenz-96 and quasi-geostrophic models. The results indicate potential for a deeper integration of modeling, DA, and new technologies in a next-generation of operational forecast systems that leverage weather models designed to support flexible, on-the-fly automatic differentiation.</p>\",\"PeriodicalId\":14881,\"journal\":{\"name\":\"Journal of Advances in Modeling Earth Systems\",\"volume\":\"17 4\",\"pages\":\"\"},\"PeriodicalIF\":4.4000,\"publicationDate\":\"2025-04-05\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://onlinelibrary.wiley.com/doi/epdf/10.1029/2024MS004608\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Journal of Advances in Modeling Earth Systems\",\"FirstCategoryId\":\"89\",\"ListUrlMain\":\"https://onlinelibrary.wiley.com/doi/10.1029/2024MS004608\",\"RegionNum\":2,\"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":"Journal of Advances in Modeling Earth Systems","FirstCategoryId":"89","ListUrlMain":"https://onlinelibrary.wiley.com/doi/10.1029/2024MS004608","RegionNum":2,"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

由于需要开发和维护基于软件的切线模型和伴随模型,通过4D变分(4D- var)数据同化(DA)观测来约束数值天气预报(NWP)模型通常很难实现。最常见的4D-Var算法之一使用增量更新过程,这已被证明是高斯-牛顿方法的近似。在这里,我们证明了当使用支持灵活自动微分的预测模型时,可以通过将误差的反向传播与Hessian近似相结合来应用高斯-牛顿方法的有效且在某些情况下更精确的替代近似。这种方法既可以用于使用自动微分实现的传统物理模型,也可以用于基于机器学习(ML)的代理模型。我们在各种Lorenz-96和准地转模型上测试了新方法。结果表明,在下一代业务预报系统中,建模、数据分析和新技术的深度集成具有潜力,这些系统利用天气模型来支持灵活、动态的自动区分。
本文章由计算机程序翻译,如有差异,请以英文原文为准。

4D-Var Using Hessian Approximation and Backpropagation Applied to Automatically Differentiable Numerical and Machine Learning Models

4D-Var Using Hessian Approximation and Backpropagation Applied to Automatically Differentiable Numerical and Machine Learning Models

Constraining a numerical weather prediction (NWP) model with observations via 4D variational (4D-Var) Data assimilation (DA) is often difficult to implement due to the need to develop and maintain a software-based tangent linear model and adjoint model. One of the most common 4D-Var algorithms uses an incremental update procedure, which has been shown to be an approximation of the Gauss-Newton method. Here we demonstrate that when using a forecast model that supports flexible automatic differentiation, an efficient and in some cases more accurate alternative approximation of the Gauss-Newton method can be applied by combining backpropagation of errors with a Hessian approximation. This approach can be used with either a conventional physical model implemented with automatic differentiation or a machine learning (ML) based surrogate model. We test the new approach on a variety of Lorenz-96 and quasi-geostrophic models. The results indicate potential for a deeper integration of modeling, DA, and new technologies in a next-generation of operational forecast systems that leverage weather models designed to support flexible, on-the-fly automatic differentiation.

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
Journal of Advances in Modeling Earth Systems
Journal of Advances in Modeling Earth Systems METEOROLOGY & ATMOSPHERIC SCIENCES-
CiteScore
11.40
自引率
11.80%
发文量
241
审稿时长
>12 weeks
期刊介绍: The Journal of Advances in Modeling Earth Systems (JAMES) is committed to advancing the science of Earth systems modeling by offering high-quality scientific research through online availability and open access licensing. JAMES invites authors and readers from the international Earth systems modeling community. Open access. Articles are available free of charge for everyone with Internet access to view and download. Formal peer review. Supplemental material, such as code samples, images, and visualizations, is published at no additional charge. No additional charge for color figures. Modest page charges to cover production costs. Articles published in high-quality full text PDF, HTML, and XML. Internal and external reference linking, DOI registration, and forward linking via CrossRef.
×
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