[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-124658-en":3,"doc-seo-124658-105":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},124658,962075006959,"Anda","https://ap-avatar.wpscdn.com/avatar/e0002397efbe92a78e?_k=1776741047341049297",8,"Research & Report","BubbleML: A Multi-Physics Dataset and Benchmarks for Machine Learning - Overview","BubbleML addresses the lack of open, diverse, high-fidelity datasets for machine learning in phase-change and boiling. The BubbleML Dataset uses physics-driven simulations to provide accurate ground truth for nucleate pool boiling, flow boiling, and sub-cooled boiling, spanning gravity, flow rate, sub-cooling, and wall superheat across 79 simulations. The dataset is validated against experimental observations and trends. Two benchmarks extend downstream usage: optical flow to capture bubble dynamics and operator networks to learn temperature dynamics.","arXiv :2307 . 14623v2 [ cs .LG] 25 Aug 2023  \nBUBBLEML: A MULTI-PHYSICS DATASET AND BENCHMARKS  \nFOR MACHINE LEARNING  \nSheikh Md Shakeel Hassan 1† Arthur Feeney 1† Akash Dhruv2 Jihoon Kim3 Youngjoon Suh 1 Jaiyoung Ryu3 Yoonjin Won 1 Aparna Chandramowlishwaran 1  \n1University of California, Irvine 2Argonne National Laboratory 3 Korea University  \n† Equal contributions  \n{sheikhh1,afeeney,ysuh2,won,[amowli}@uci.edu](amowli}@uci.edu)  \n[adhruv@anl.gov](adhruv@anl.gov)  \n{kimjihoon,[jryu}@korea.ac.kr](jryu}@korea.ac.kr)  \nAugust 28, 2023  \nABSTRACT  \nIn the field of phase change phenomena, the lack of accessible and diverse datasets suitable for machine learning (ML) training poses a significant challenge. Existing experimental datasets are often restricted, with limited availability and sparse ground truth data, impeding our understanding of this complex multiphysics phenomena. To bridge this gap, we present the BubbleML Dataset 1 which leverages physics-driven simulations to provide accurate ground truth information for various boiling scenarios, encompassing nucleate pool boiling, flow boiling, and sub-cooled boiling. This extensive dataset covers a wide range of parameters, including varying gravity conditions, flow rates, sub-cooling levels, and wall superheat, comprising 79 simulations. BubbleML is validated against experimental observations and trends, establishing it as an invaluable resource for ML research.  \nFurthermore, we showcase its potential to facilitate exploration of diverse downstream tasks by introducing two benchmarks: (a) optical flow analysis to capture bubble dynamics, and (b) operator networks for learning temperature dynamics. The BubbleML dataset and its benchmarks serve as a catalyst for advancements in ML-driven research on multiphysics phase change phenomena, enabling the development and comparison of state-of-the-art techniques and models.  \n1 Introduction  \nPhase-change phenomena, such as boiling, involve complex multiphysics processes and dynamics that are not fully understood. The interplay between bubble dynamics and heat transfer performance during boiling presents significant challenges in accurately predicting and modeling these heat and mass transfer processes. Machine learning (ML) offers the potential to revolutionize this field, enabling data-driven discovery to unravel new physical insights, develop accurate surrogate and predictive models, optimize the design of heat transfer systems, and facilitate adaptive real-time monitoring and control.  \nThe applications of ML in this domain are diverse and impactful. Consider the context of high-performance computing in data centers, where efficient cooling is critical. Boiling-based cooling techniques, such as two-phase liquid cooling, offer enhanced heat dissipation capabilities, ensuring reliable and optimal operation of power-intensive electronic components such as GPUs. Moreover, boiling phenomena play a crucial role in complex processes like nuclear fuel reprocessing, where precise modeling and prediction of boiling dynamics contribute to the safe and efficient management of nuclear waste. In the realm of water desalination, boiling processes are integral, playing a vital role in thermal desalination methods that provide clean drinking water in water-scarce regions . These advancements in pivotal areas such as thermal management, energy efficiency, and heat transfer applications, driven by ML techniques  \n1[https://github.com/HPCForge/BubbleML](https://github.com/HPCForge/BubbleML)  \nA PREPRINT-AUGUST 28, 2023  \nFigure 1: BubbleML Dataset. Capturing diverse two-phase boiling phenomena with ground truth for key physical variables–velocity, temperature, and pressure. (a) Single bubble rising from a nucleation site on the heater surface.(b) Chaotic multi-bubble dynamics—merging, splitting. (c) Flow boiling transitions from bubbly to slug regime with increasing inlet velocity. The velocity and temperature fields are obtained by solving equatio","cbCaictEBwNcZXoH","https://ap.wps.com/l/cbCaictEBwNcZXoH","pdf",6434339,1,32,"English","en",105,"# Abstract\n# Introduction\n## Motivation: dataset scarcity in boiling\n## Dataset design: physics-driven simulations and ground truth\n## Benchmarks: optical flow and operator networks","[{\"question\":\"BubbleML Dataset解决了相位变化与沸腾领域的什么关键问题？\",\"answer\":\"它弥补了用于机器学习训练的开放且多样化、高保真数据集不足的问题。通过仿真提供可获得的ground truth来支撑模型学习与评估。\"},{\"question\":\"BubbleML Dataset覆盖哪些沸腾场景与参数范围？\",\"answer\":\"它覆盖nucleate pool boiling、flow boiling与sub-cooled boiling，并包含重力条件、流量、过冷度以及壁面过热等多种参数变化，总计79组仿真。\"},{\"question\":\"文中提出的两个benchmark分别用于什么任务？\",\"answer\":\"一个使用optical flow分析捕捉气泡动力学，另一个使用operator networks学习温度动力学，从而支持下游多种研究任务。\"}]","BubbleML: A Multi-Physics Dataset and Benchmarks for Machine Learning - Overview | PDF",1785893597,81,{"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},"bubbleml-a-multi-physics-dataset-and-benchmarks-for-machine-learning-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/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/bubbleml-a-multi-physics-dataset-and-benchmarks-for-machine-learning-overview/124658/",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},"BubbleML Dataset解决了相位变化与沸腾领域的什么关键问题？","Question",{"text":75,"@type":76},"它弥补了用于机器学习训练的开放且多样化、高保真数据集不足的问题。通过仿真提供可获得的ground truth来支撑模型学习与评估。","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"BubbleML Dataset覆盖哪些沸腾场景与参数范围？",{"text":80,"@type":76},"它覆盖nucleate pool boiling、flow boiling与sub-cooled boiling，并包含重力条件、流量、过冷度以及壁面过热等多种参数变化，总计79组仿真。",{"name":82,"@type":73,"acceptedAnswer":83},"文中提出的两个benchmark分别用于什么任务？",{"text":84,"@type":76},"一个使用optical flow分析捕捉气泡动力学，另一个使用operator networks学习温度动力学，从而支持下游多种研究任务。","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"]