{"title":"U-Net卡尔曼滤波(UNetKF):机器学习辅助数据同化的一个例子","authors":"Feiyu Lu","doi":"10.1029/2023MS003979","DOIUrl":null,"url":null,"abstract":"<p>Machine learning techniques have seen a tremendous rise in popularity in weather and climate sciences. Data assimilation (DA), which combines observations and numerical models, has great potential to incorporate machine learning and artificial intelligence (ML/AI) techniques. In this paper, we use U-Net, a type of convolutional neutral network (CNN), to improve the localized error covariances for the Ensemble Kalman Filter (EnKF) algorithm. Using a 2-layer quasi-geostrophic model, U-Nets are trained using data from EnKF DA experiments. The trained U-Nets are then successfully implemented in U-Net Kalman Filter (UNetKF) experiments to predict localized error covariances that possess adaptive localization and some state-dependent features of the model error covariances. UNetKF is compared to traditional 3-dimensional variational (3DVar), ensemble 3DVar (En3DVar) and EnKF methods. The performance of UNetKF can match or exceed that of 3DVar, or En3DVar and EnKF for small to moderate ensemble sizes. We also demonstrate that trained U-Nets can be transferred to a higher-resolution model for UNetKF implementation, which again performs competitively to 3DVar and EnKF, particularly for small ensemble sizes.</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/10.1029/2023MS003979","citationCount":"0","resultStr":"{\"title\":\"U-Net Kalman Filter (UNetKF): An Example of Machine Learning-Assisted Data Assimilation\",\"authors\":\"Feiyu Lu\",\"doi\":\"10.1029/2023MS003979\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p>Machine learning techniques have seen a tremendous rise in popularity in weather and climate sciences. Data assimilation (DA), which combines observations and numerical models, has great potential to incorporate machine learning and artificial intelligence (ML/AI) techniques. In this paper, we use U-Net, a type of convolutional neutral network (CNN), to improve the localized error covariances for the Ensemble Kalman Filter (EnKF) algorithm. Using a 2-layer quasi-geostrophic model, U-Nets are trained using data from EnKF DA experiments. The trained U-Nets are then successfully implemented in U-Net Kalman Filter (UNetKF) experiments to predict localized error covariances that possess adaptive localization and some state-dependent features of the model error covariances. UNetKF is compared to traditional 3-dimensional variational (3DVar), ensemble 3DVar (En3DVar) and EnKF methods. The performance of UNetKF can match or exceed that of 3DVar, or En3DVar and EnKF for small to moderate ensemble sizes. We also demonstrate that trained U-Nets can be transferred to a higher-resolution model for UNetKF implementation, which again performs competitively to 3DVar and EnKF, particularly for small ensemble sizes.</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/10.1029/2023MS003979\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Journal of Advances in Modeling Earth Systems\",\"FirstCategoryId\":\"89\",\"ListUrlMain\":\"https://onlinelibrary.wiley.com/doi/10.1029/2023MS003979\",\"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/10.1029/2023MS003979","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}
U-Net Kalman Filter (UNetKF): An Example of Machine Learning-Assisted Data Assimilation
Machine learning techniques have seen a tremendous rise in popularity in weather and climate sciences. Data assimilation (DA), which combines observations and numerical models, has great potential to incorporate machine learning and artificial intelligence (ML/AI) techniques. In this paper, we use U-Net, a type of convolutional neutral network (CNN), to improve the localized error covariances for the Ensemble Kalman Filter (EnKF) algorithm. Using a 2-layer quasi-geostrophic model, U-Nets are trained using data from EnKF DA experiments. The trained U-Nets are then successfully implemented in U-Net Kalman Filter (UNetKF) experiments to predict localized error covariances that possess adaptive localization and some state-dependent features of the model error covariances. UNetKF is compared to traditional 3-dimensional variational (3DVar), ensemble 3DVar (En3DVar) and EnKF methods. The performance of UNetKF can match or exceed that of 3DVar, or En3DVar and EnKF for small to moderate ensemble sizes. We also demonstrate that trained U-Nets can be transferred to a higher-resolution model for UNetKF implementation, which again performs competitively to 3DVar and EnKF, particularly for small ensemble sizes.
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.