[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-119572-en":3,"doc-seo-119572-105":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},119572,1374391974585,"Genevieve","https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c",6,"Technology","COMBINING MACHINE LEARNING WITH COMPUTATIONAL FLUID DYNAMICS USING OPENFOAM AND SMARTSIM - OpenFOAM+SmartSim as an OpenFOAM Module - Overview","This workshop presents an integrated workflow for combining machine learning with computational fluid dynamics using OpenFOAM and SmartSim. It introduces data-driven modeling approaches, including ML+CFD data patterns and online post-processing during simulation runs. The material highlights how SmartSim orchestrates the computational pipeline, with data storage and model inference supported through SmartRedis, and APIs usable from both Python and C++. It further demonstrates online ML for mesh-motion approximation and the synchronization requirements in distributed (MPI) training and inference.","COMBINING MACHINE LEARNING WITH COMPUTATIONAL FLUID DYNAMICS USING OPENFOAM AND SMARTSIM  \n© Thomas Ott  \n25.06.2024 T. Maric (TU Darmstadt) | A. E. Shao (HPE) | A. Rigazzi (HPE) | M. Ellis (HPE) | E. Fadeli (TU Darmstadt) | Y. Kai ( Intel) | A. Weiner (TU Dresden) 1  \nDATA-DRIVEN MODELING SPECIAL INTEREST GROUP  \nInformation about the Data-Driven SIG:  \n[https://wiki.openfoam.com/Data_Driven_Modelling_Special_Interest_Group](https://wiki.openfoam.com/Data_Driven_Modelling_Special_Interest_Group)  \nWe organize hackathons on combining ML+CFD in OpenFOAM  \n[https://github.com/OFDataCommittee/OFMLHackathon](https://github.com/OFDataCommittee/OFMLHackathon)  \nCombining CFD and ML with OpenFOAM and SmartSim  \n[https://github.com/OFDataCommittee/openfoam-smartsim](https://github.com/OFDataCommittee/openfoam-smartsim)  \n[https://doi.org/10.1007/s11012-024-01797-z](https://doi.org/10.1007/s11012-024-01797-z)[ ](https://doi.org/10.1007/s11012-024-01797-z)[OpenFOAM-SmartSim as an OpenFOAM Module](OpenFOAM-SmartSim as an OpenFOAM Module)[ ](OpenFOAM-SmartSim as an OpenFOAM Module)OpenFOAM + SmartSim OFW18 Training  \n25.06.2024 T. Maric (TU Darmstadt) | A. E. Shao (HPE) | A. Rigazzi (HPE) | M. Ellis (HPE) | E. Fadeli (TU Darmstadt) | Y. Kai ( Intel) | A. Weiner (TU Dresden) 2  \nML+CFD DATA PATTERNS I  \n25.06.2024 T. Maric (TU Darmstadt) | A. E. Shao (HPE) | A. Rigazzi (HPE) | M. Ellis (HPE) | E. Fadeli (TU Darmstadt) | Y. Kai ( Intel) | A. Weiner (TU Dresden) 3  \nML+CFD DATA PATTERNS II  \n26.06.2024 T. Maric (TU Darmstadt) | A. E. Shao (HPE) | A. Rigazzi (HPE) | M. Ellis (HPE) | E. Fadeli (TU Darmstadt) | Y. Kai ( Intel) | A. Weiner (TU Dresden) 4  \nOPENFOAM + SMARTSIM + ML  \nPYTORCH | TENSORFLOW | ONNX  \n• SmartSim Orchestrator: implementing the computational workflow.  \n• Jupyter Notebook or Python script – straightforward API.  \n• SmartRedis Database: CFD data, trained model, model inference.  \n• Straightforward API in C++ (!!) and Python.  \n26.06.2024 T. Maric (TU Darmstadt) | A. E. Shao (HPE) | A. Rigazzi (HPE) | M. Ellis (HPE) | E. Fadeli (TU Darmstadt) | Y. Kai ( Intel) | A. Weiner (TU Dresden) 6  \nONLINE POST-PROCESSING  \nOn-line Machine Learning while the simulation is running.  \nRank1  \nPrimary (CFD) Data  \nRankN  \nPrimary (CFD) Data  \n\n| \u003Cbr>\u003Cbr>\u003Cbr>\u003Cbr>\u003Cbr>Training Data\u003Cbr>\u003Cbr>ML Model\u003Cbr>\u003Cbr>\u003Cbr>\u003Cbr> | \u003Cbr>\u003Cbr>\u003Cbr>\u003Cbr>\u003Cbr>Visualize\u003Cbr>…\u003Cbr>Calculate DRL reward |\n| --- | --- |\n\n25.06.2024 T. Maric (TU Darmstadt) | A. E. Shao (HPE) | A. Rigazzi (HPE) | M. Ellis (HPE) | E. Fadeli (TU Darmstadt) | Y. Kai ( Intel) | A. Weiner (TU Dresden) 8  \nONLINE ML MESH MOTION  \n• Use a machine-learning model to approximate mesh-motion displacements.  \nwhile (runTime.loop())  \nMPI Rank 0 MPI Rank 1  \nMPI_Rank 2 MPI_Rank 3  \nTraining Data  \n• Agglomerates training data.  \n• Trains on other resources.  \n• Online training and inference requires synchronization with the CFD algorithm.  \n26.06.2024 T. Maric (TU Darmstadt) | A. E. Shao (HPE) | A. Rigazzi (HPE) | M. Ellis (HPE) | E. Fadeli (TU Darmstadt) | Y. Kai ( Intel) | A. Weiner (TU Dresden) 10","cbCaig1nUV7xzbdD","https://ap.wps.com/l/cbCaig1nUV7xzbdD","pdf",1457142,1,19,"English","en",105,"# Overview and ecosystem\n## Data-Driven SIG and hackathon resources\n## OpenFOAM-SmartSim module concept\n# Training and online ML integration\n## ML+CFD data patterns I\n## ML+CFD data patterns II\n## Online post-processing\n# SmartSim orchestration and implementations\n## SmartSim Orchestrator and data/model services\n## APIs in Jupyter/Python and C++\n# Online mesh motion and distributed execution\n## Online ML mesh motion\n## MPI synchronization for training and inference","[{\"question\":\"What role does SmartSim play when combining ML with CFD in OpenFOAM?\",\"answer\":\"SmartSim orchestrates the computational workflow and enables online interactions between the simulation and machine learning components.\"},{\"question\":\"How is CFD data and ML model inference integrated during runtime?\",\"answer\":\"CFD primary data is fed into training and inference steps while the simulation is running, with model computation and visualization tied to online post-processing.\"},{\"question\":\"How does online ML mesh motion work, and what is required for distributed execution?\",\"answer\":\"A machine-learning model approximates mesh-motion displacements, and online training/inference must synchronize with the CFD algorithm across MPI ranks for consistent execution.\"}]","COMBINING MACHINE LEARNING WITH COMPUTATIONAL FLUID DYNAMICS USING OPENFOAM AND SMARTSIM - OpenFOAM+SmartSim as an OpenFOAM Module - Overview | PDF",1785725031,48,{"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},"combining-machine-learning-with-computational-fluid-dynamics-using-openfoam-and-smartsim-openfoamsmartsim-as-an-openfoam-module-overview","",{"@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/technology/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/combining-machine-learning-with-computational-fluid-dynamics-using-openfoam-and-smartsim-openfoamsmartsim-as-an-openfoam-module-overview/119572/",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":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What role does SmartSim play when combining ML with CFD in OpenFOAM?","Question",{"text":75,"@type":76},"SmartSim orchestrates the computational workflow and enables online interactions between the simulation and machine learning components.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How is CFD data and ML model inference integrated during runtime?",{"text":80,"@type":76},"CFD primary data is fed into training and inference steps while the simulation is running, with model computation and visualization tied to online post-processing.",{"name":82,"@type":73,"acceptedAnswer":83},"How does online ML mesh motion work, and what is required for distributed execution?",{"text":84,"@type":76},"A machine-learning model approximates mesh-motion displacements, and online training/inference must synchronize with the CFD algorithm across MPI ranks for consistent execution.","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},[93,97,101,105,110,113,118,123,128,131,135],{"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":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":111,"slug":112},50,"technology",{"id":114,"doc_module":4,"doc_module_name":46,"category_name":115,"show_sort_weight":116,"slug":117},7,"Healthcare",40,"healthcare",{"id":119,"doc_module":4,"doc_module_name":46,"category_name":120,"show_sort_weight":121,"slug":122},8,"Research & Report",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":21,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":106,"slug":137},"General","general"]