[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-121834-en":3,"doc-seo-121834-105":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},121834,1649267921044,"Ava Thompson","https://us-avatar.wpscdn.com/avatar/1800007509477c92dfb?_k=1782875107921204101",8,"Research & Report","Roadmap on machine learning glassy dynamics - Perspective","Unraveling links between microscopic structure, emergent properties, and slow dynamics is central to understanding the glass transition, yet amorphous configurations lack clear visible structural order and equilibrated low-temperature sampling remains difficult. This perspective article evaluates how machine learning techniques can address these barriers, citing advances inspired by computer vision and outlining open challenges such as transferability and interpretability. It introduces the GlassBench dataset and proposes benchmark metrics to guide development of ML for glassy liquids.","arXiv :2311 . 14752v2 [ cond-mat .soft] 26 Sep 2024  \nRoadmap on machine learning glassy dynamics  \nGerhard Jung, 1, 2 Rinske M. Alkemade,3 Victor Bapst,4 Daniele Coslovich,5 Laura Filion,3 Fran¸cois P. Landes,6 Andrea Liu,7, 8 Francesco Saverio Pezzicoli,6 Hayato Shiba,9 Giovanni Volpe, 10 Francesco Zamponi, 11 Ludovic Berthier, 1, 12 and Giulio Biroli 11  \n1 Laboratoire Charles Coulomb (L2C), Universit´e de Montpellier, CNRS, 34095 Montpellier, France  \n2 Laboratoire Interdisciplinaire de Physique (LIPhy),  \nUniversit´e Grenoble Alpes, 38402 Saint-Martin-d’H`eres, France  \n3 Soft Condensed Matter and Biophysics, Debye Institute for Nanomaterials Science, Utrecht University, Utrecht, Netherlands  \n4 GoogleDeepMind, London, UK  \n5 Dipartimento di Fisica, Universit`a di Trieste, Strada Costiera 11, 34151, Trieste, Italy  \n6 Universit´e Paris-Saclay, CNRS, INRIA, Laboratoire Interdisciplinaire  \ndes Sciences du Num´erique, TAU team, 91190 Gif-sur-Yvette, France  \n7 Department of Physics and Astronomy, University of Pennsylvania, Philadelphia, PA 19104, USA  \n8 Santa Fe Institute, 1399 Hyde Park Road, Santa Fe, NM 87501, USA  \n9 Graduate School of Information Science, University of Hyogo, Kobe 650-0047, Japan  \n10 Department of Physics, University of Gothenburg, Origov¨agen 6B, Gothenburg 41296, Sweden  \n11 Laboratoire de Physique de l’Ecole Normale Sup´erieure, ENS, Universit´e PSL,  \nCNRS, Sorbonne Universit´e, Universit´e de Paris, F-75005 Paris, France  \n12 Gulliver, UMR CNRS 7083, ESPCI Paris, PSL Research University, 75005 Paris, France  \n(Dated: September 27, 2024)  \nUnraveling the connections between microscopic structure, emergent physical properties, and slow dynamics has long been a challenge when studying the glass transition. The absence of clear visible structural order in amorphous configurations complicates the identification of the key physical mechanisms underpinning slow dynamics. The difficulty in sampling equilibrated configurations at low temperatures hampers thorough numerical and theoretical investigations. This perspective article explores the potential of machine learning (ML) techniques to face these challenges, building on the algorithms that have revolutionized computer vision and image recognition. We present recent successful ML applications, as well as many open problems for the future, such as transferability and interpretability of ML approaches. We highlight new ideas and directions in which ML could provide breakthroughs to better understand the fundamental mechanisms at play in glass-forming liquids. To foster a collaborative community effort, this article also introduces the “GlassBench” dataset, providing simulation data and benchmarks for both two-dimensional and three-dimensional glassformers. We propose critical metrics to compare the performance of emerging ML methodologies, in line with benchmarking practices in image and text recognition. The goal of this roadmap is to provide guidelines for the development of ML techniques in systems displaying slow dynamics, while inspiring new directions to improve our theoretical understanding of glassy liquids.  \nI. INTRODUCTION  \nWhen supercooled liquids undergo a glass transition, a dramatic slowdown of transport properties is observed and the resulting material dynamically resembles a crystalline solid — yet one of the main characteristic of glasses is that they maintain their amorphous liquid structure [1] . While glasses and other amorphous materials have been used since prehistoric times, their technological applications have blossomed in recent years [2], including, e.g., metallic glasses for biomedical implants [3] and vapor-deposited organic films used extensively in visual displays [4] . Despite several decades of research involving experiments, theory and computer simulations, many fundamental mechanisms remain to be elucidated, such as macroscopic mechanical properties, highly cooperative stress relaxation in glasses, and the statistic","cbCaiqlEEctmvNjQ","https://ap.wps.com/l/cbCaiqlEEctmvNjQ","pdf",5559295,1,27,"English","en",105,"# Introduction\n## Glass transition and slow dynamics\n## Challenges in microscopic structural identification\n## Need for machine learning methods\n## Benchmarking and the GlassBench dataset","[{\"question\":\"What motivates the roadmap on machine learning for glassy dynamics?\",\"answer\":\"The roadmap targets the difficulty of connecting amorphous microscopic structure to emergent physical properties and slow dynamics, especially where visible structural order is absent and equilibrated sampling at low temperatures is hard.\"},{\"question\":\"What kinds of machine learning capabilities are discussed in the perspective?\",\"answer\":\"The article focuses on using machine learning to overcome structural identification challenges and to better understand mechanisms behind slow and glassy dynamics, drawing inspiration from successes in computer vision.\"},{\"question\":\"What is the GlassBench dataset and what is it used for?\",\"answer\":\"The article introduces the “GlassBench” dataset, providing simulation data and benchmarks for two-dimensional and three-dimensional glassformers to support evaluation of ML approaches.\"}]","Roadmap on machine learning glassy dynamics - Perspective | PDF",1785807133,68,{"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},"roadmap-on-machine-learning-glassy-dynamics-perspective","",{"@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/roadmap-on-machine-learning-glassy-dynamics-perspective/121834/",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","2026-08-04",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 motivates the roadmap on machine learning for glassy dynamics?","Question",{"text":75,"@type":76},"The roadmap targets the difficulty of connecting amorphous microscopic structure to emergent physical properties and slow dynamics, especially where visible structural order is absent and equilibrated sampling at low temperatures is hard.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What kinds of machine learning capabilities are discussed in the perspective?",{"text":80,"@type":76},"The article focuses on using machine learning to overcome structural identification challenges and to better understand mechanisms behind slow and glassy dynamics, drawing inspiration from successes in computer vision.",{"name":82,"@type":73,"acceptedAnswer":83},"What is the GlassBench dataset and what is it used for?",{"text":84,"@type":76},"The article introduces the “GlassBench” dataset, providing simulation data and benchmarks for two-dimensional and three-dimensional glassformers to support evaluation of ML approaches.","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"]