[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-121601-en":3,"doc-seo-121601-105":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":20,"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},121601,7971461741311,"Ophelia","https://ap-avatar.wpscdn.com/avatar/74000253aff267980c6?x-image-process=image/resize,m_fixed,w_180,h_180&k=1779345379180704826",8,"Research & Report","Advancing Machine Learning for Large Eddy Simulation of Offshore Wind Farms - Doctor of Philosophy Thesis","Subgrid-scale modelling in large eddy simulation remains an open challenge in turbulence modelling, especially for complex flows such as offshore wind-farm conditions. The thesis addresses how to represent unresolved small-scale turbulent motions and avoid inaccuracies caused by overly simplifying assumptions like isotropy, which can lead to over- or under-dissipation and reduce predictive accuracy and stability. It proposes a machine-learning-facilitated turbulence modelling framework for offshore wind farms using actuator-disk simulations and wind-tunnel comparison data.","Advancing Machine Learning for Large Eddy Simulation of O􀀋shore Wind Farms  \nby  \n􀀍c H . Ali Marefat  \nA thesis submitted to the School of Graduate Studies in partial ful􀀌llment of the requirements for the  \ndegree of Doctor of Philosophy.  \nScienti􀀌c Computing Program Memorial University of Newfoundland  \nFebruary 2025  \nSt. John's, Newfoundland and Labrador, Canada  \n\\When I meet God,  \nI'm going to ask him two questions: why relativity? And why turbulence?  \nI really believe he'll have an answer for the 􀀌rst. \"  \n| Werner Heisenberg  \nAbstract  \nSubgrid-scale modelling in large eddy simulation remains an open problem in the 􀀌eld of turbulence modelling, particularly when dealing with complex 􀀍ows like those ino􀀋shore wind farms. The core challenge in subgrid-scale modelling is accurately representing the e􀀋ects of unresolved small-scale turbulent motions on the larger, resolved scales of the 􀀍ow. Traditional models frequently rely on simplifying assumptions, such as isotropy, to characterize eddy viscosity. However, these assumptions often fall short in accurately capturing the complex, anisotropic, and multiscale nature of turbulence in real-world o􀀋shore conditions. Such limitations can lead to inaccuracies, including over- or under-dissipation of energy from the resolved scales, ultimately impacting the predictive accuracy and stability of large eddy simulations. Machine learning and data-driven approaches o􀀋er promising alternatives, focusing on developing robust, generalizable subgrid-scale models that enhance the scalability and performance of large eddy simulations without compromising computational e􀀎ciency.  \nThis thesis proposes an advanced machine-learning-facilitated approach to improve turbulence modelling within the large eddy simulation framework, with a focus ono􀀋shore wind farms. By incorporating machine learning techniques, this research addresses the inherent challenges of capturing the complex, multiscale turbulent 􀀍ow behaviours typical in o􀀋shore environments. The work is centred on the development and assessment of machine-learning-based subgrid-scale models aimed at improving the predictability, performance, and scalability of turbulence models for o􀀋shore wind farm applications.  \nTo establish the machine-learning-based subgrid-scale model, an o􀀋shore wind farm was simulated using the actuator disk method, with simulated data compared against wind tunnel measurements before model training. Both standard a-priori and  \na-posteriori analyses were performed to evaluate the machine learning model's e􀀋ectiveness comprehensively. The study began by leveraging a scale-adaptive large eddy simulation of 􀀍ow past a sphere, which o􀀋ers insights into turbulent wake dynamicsand essential features of the turbulence energy cascade. Based on this analysis, a novel subgrid-scale model using a wavelet-assisted encoder-decoder architecture with skip connections was introduced to predict subgrid-scale stresses in the wake of a sphere using the Germano-Lilly framework. Results demonstrated that this model is particularly adept at capturing 􀀍ow intermittency and preserving spatial 􀀍ow information in the wake of a sphere at Reynolds numbers of Re = 103 and Re = 104 .  \nTo enhance the scalability and generalizability of the wavelet-assisted encoderdecoder subgrid-scale model, the study undertook an in-depth examination of its interpretability. The e􀀎cacy of encoder-decoder models, particularly in turbulence modelling, depends signi􀀌cantly on their latent representations. As such, the nonlinearity of the encoder-decoder's latent space was scrutinized, revealing promising results in capturing the intermittency and chaotic nature of turbulent 􀀍ows. Achieving scalability necessitates testing the model in both a-priori and a-posteriori setups, which led to the development of the Scale-Adaptive Machine-learning Subgrid-Scale (SAM-SGS ) model for large eddy simulations of o􀀋shore wind farms. Building upon prior mathematical insig","cbCaidS3oMqhTrY1","https://ap.wps.com/l/cbCaidS3oMqhTrY1","pdf",17010442,1,198,"English","en",105,"# Abstract\n# Subgrid-scale modelling challenge and motivation\n## Limitations of traditional turbulence models\n## Role of machine learning in SGS modelling\n# Proposed ML-based SGS modelling approach\n## Actuator disk simulation and data comparison\n## Wavelet-assisted encoder-decoder with skip connections (Germano-Lilly)\n## Interpretability and latent-space analysis\n## Scale-Adaptive Machine-learning Subgrid-Scale (SAM-SGS) model\n# Evaluation: a-priori and a-posteriori analyses\n## Capturing intermittency and spatial information\n## Generalization across conditions and filter widths\n# Lay summary\n## Multiscale turbulence and practical alternatives to DNS\n## LES with SGS models for offshore applications","[{\"question\":\"What problem does the thesis target in large eddy simulation?\",\"answer\":\"It targets subgrid-scale (SGS) modelling, where unresolved small-scale turbulence effects must be represented accurately in large eddy simulation. The work focuses on overcoming inaccuracies from traditional simplifying assumptions.\"},{\"question\":\"How is the machine-learning SGS model developed and trained?\",\"answer\":\"An offshore wind farm is simulated using the actuator disk method, and simulated data are compared against wind-tunnel measurements before training. The study then applies standard a-priori and a-posteriori analyses to evaluate performance.\"},{\"question\":\"What modelling approach is used to predict SGS stresses in the wake of a sphere?\",\"answer\":\"A wavelet-assisted encoder-decoder architecture with skip connections is introduced, using the Germano-Lilly framework to predict SGS stresses. Results highlight improved capture of intermittency and preservation of spatial information at specified Reynolds numbers.\"}]","Advancing Machine Learning for Large Eddy Simulation of Offshore Wind Farms - Doctor of Philosophy Thesis | PDF",1785736428,499,{"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},"advancing-machine-learning-for-large-eddy-simulation-of-offshore-wind-farms-doctor-of-philosophy-thesis","",{"@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/advancing-machine-learning-for-large-eddy-simulation-of-offshore-wind-farms-doctor-of-philosophy-thesis/121601/",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","2026-08-03",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What problem does the thesis target in large eddy simulation?","Question",{"text":75,"@type":76},"It targets subgrid-scale (SGS) modelling, where unresolved small-scale turbulence effects must be represented accurately in large eddy simulation. The work focuses on overcoming inaccuracies from traditional simplifying assumptions.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How is the machine-learning SGS model developed and trained?",{"text":80,"@type":76},"An offshore wind farm is simulated using the actuator disk method, and simulated data are compared against wind-tunnel measurements before training. The study then applies standard a-priori and a-posteriori analyses to evaluate performance.",{"name":82,"@type":73,"acceptedAnswer":83},"What modelling approach is used to predict SGS stresses in the wake of a sphere?",{"text":84,"@type":76},"A wavelet-assisted encoder-decoder architecture with skip connections is introduced, using the Germano-Lilly framework to predict SGS stresses. Results highlight improved capture of intermittency and preservation of spatial information at specified Reynolds numbers.","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"]