[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-125542-en":3,"doc-seo-125542-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},125542,1099513958607,"Jiven","https://ap-avatar.wpscdn.com/avatar/100002390cf8733938c?x-image-process=image/resize,m_fixed,w_180,h_180&k=1778829742770036399",8,"Research & Report","A hybrid data assimilation system based on machine learning","Numerical weather prediction depends on accurate initial conditions, and data assimilation (DA) supplies them by combining forecast model outputs with imperfect observations. This work introduces a machine-learning-based hybrid DA approach (HDA-ML) to address drawbacks of the hybrid 4DVar-EnKF, including difficult tangent linear/adjoint model development and empirical fusion of results. Bilinear neural networks replace the 4DVar forecast models, while a CNN adaptively fuses 4DVar and EnKF analyses to learn optimal combination coefficients. Experiments on the Lorenz-96 setting show improved assimilation performance and reduced computation time. Training with observations instead of true values yields comparable performance, indicating strong potential for operational NWP.","TYPE Original Research PUBLISHED 05 January 2023 DOI 10.3389/feart.2022.1012165  \nOPEN ACCESS  \nEDITED BY  \nJing-Jia Luo,  \nNanjing University of Information Science and Technology, China  \nREVIEWED BY  \nAndrey Popov,  \nVirginia Tech, United States Guojie Wang,  \nNanjing University of Information Science and Technology, China  \n*CORRESPONDENCE  \nChengwu Zhao,  \n[zhaochengwu12@nudt.edu.cn](zhaochengwu12@nudt.edu.cn)  \n†These authors have contributed equally to this work and share first authorship  \nSPECIALTY SECTION  \nThis article was submitted to Atmospheric Science, a section of the journal Frontiers in Earth Science  \nRECEIVED 05 August 2022  \nACCEPTED 15 September 2022  \nPUBLISHED 05 January 2023  \nCITATION  \nDong R, Leng H, Zhao C, Song J, Zhao Jand Cao X (2023), A hybrid data assimilation system based on machine learning.  \nFront. Earth Sci. 10:1012165 .  \ndoi: 10.3389/feart.2022.1012165  \nCOPYRIGHT  \n© 2023 Dong, Leng, Zhao, Song, Zhao and Cao. This is an open-access article distributed under the terms of the  \nCreative Commons Attribution License (CC BY) . The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.  \nA hybrid data assimilation system based on machine learning  \nRenze Dong†, Hongze Leng†, Chengwu Zhao*, Junqiang Song, Juan Zhao and Xiaoqun Cao  \nCollege of Meteorology and Oceanology, National University of Defense Technology, Changsha, China  \nIn the earth sciences, numerical weather prediction (NWP) is the primary method of predicting future weather conditions, and its accuracy is affected by the initial conditions. Data assimilation (DA) can provide high-precision initial conditions for NWP. The hybrid 4DVar-EnKF is currently an advanced DA method used by many operational NWP centres. However, it has two major shortcomings: The complex development and maintenance of the tangent linear and adjoint models and the empirical combination of the results of 4DVarand EnKF. In this paper, a new hybrid DA method based on machine learning (HDA-ML) is presented to overcome these drawbacks. In the new method, the tangent linear and adjoint models in the 4DVar part of the hybrid algorithm can be easily obtained by using a bilinear neural network to replace the forecast model, and a CNN model is adopted to fuse the analysis of 4DVar and EnKF to adaptively obtain the optimal coefficient of combination rather than the empirical coefficient as in the traditional hybrid DA method. The hybrid DA methods are compared with the Lorenz-96 model using the true values as labels. The experimental results show that HDA-ML improves the assimilation performance and significantly reduces the time cost. Furthermore, using observations instead of the true values as labels in the training system is more realistic. The results show comparable assimilation performance to that in the experiments with the true values used as the labels. The experimental results show that the new method has great potential for application to operational NWP systems.  \nKEYWORDS  \nnumerical weather prediction, data assimilation, machine learning, tangent linear and adjoint models, hybrid  \n1 Introduction  \nWeather forecast is a pre-estimation and prediction of weather changes in the future, which has significant social value (Gettelman et al., 2022) . Numerical weather prediction (NWP) is a crucial method. Mathematically, weather forecast is an initial value problem. The initial conditions can affect the accuracy of the prediction results (Bjerknes, 1904; Haltiner and Williams, 1980; Bauer et al., 2015) . Therefore, NWP requires sufficiently precise initial conditions. Data assimilation (DA) is an approach to providing exact initial conditions. DA obtains initial conditions that are closest to","cbCaif5jCFq4UW61","https://ap.wps.com/l/cbCaif5jCFq4UW61","pdf",3895426,1,15,"English","en",105,"# Introduction\n## Data assimilation for numerical weather prediction\n## Variational DA and ensemble DA\n## Limitations of 4DVar and EnKF\n## Motivation for coupling DA methods","[{\"question\":\"What problem does the paper address in hybrid 4DVar-EnKF DA?\",\"answer\":\"It addresses the difficulty of building and maintaining tangent linear and adjoint models and the reliance on empirical combination of 4DVar and EnKF results.\"},{\"question\":\"How does HDA-ML replace components inside the 4DVar part?\",\"answer\":\"It uses a bilinear neural network to replace the forecast model so that tangent linear and adjoint models can be obtained more easily.\"},{\"question\":\"How is the fusion between 4DVar and EnKF handled in the proposed method?\",\"answer\":\"A CNN model adaptively fuses the analyses and learns an optimal combination coefficient rather than using an empirical coefficient.\"}]","A hybrid data assimilation system based on machine learning | PDF",1785899770,38,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"a-hybrid-data-assimilation-system-based-on-machine-learning","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/a-hybrid-data-assimilation-system-based-on-machine-learning/125542/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-05",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What problem does the paper address in hybrid 4DVar-EnKF DA?","Question",{"text":75,"@type":76},"It addresses the difficulty of building and maintaining tangent linear and adjoint models and the reliance on empirical combination of 4DVar and EnKF results.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does HDA-ML replace components inside the 4DVar part?",{"text":80,"@type":76},"It uses a bilinear neural network to replace the forecast model so that tangent linear and adjoint models can be obtained more easily.",{"name":82,"@type":73,"acceptedAnswer":83},"How is the fusion between 4DVar and EnKF handled in the proposed method?",{"text":84,"@type":76},"A CNN model adaptively fuses the analyses and learns an optimal combination coefficient rather than using an empirical coefficient.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]