[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-122945-en":3,"doc-seo-122945-105":30,"detail-sidebar-cat-0-en-105":92},{"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},122945,4398048950312,"Violet","https://ap-avatar.wpscdn.com/avatar/400002538284de19e3c?_k=1778320343897328908",8,"Research & Report","Classifying the age of a glass based on structural properties - A machine learning approach","Physical aging of amorphous solids is dominated by strong changes in dynamical properties, while structural measures such as the radial distribution function typically show only extremely weak age dependence. This work demonstrates that these minute structural variations still contain enough information to reliably determine a glass’s age using supervised machine learning. A multilayer perceptron predicts the age from the instantaneous radial distribution function of a model glassformer across at least four orders of magnitude in time, and identifies the most informative structural features.","arXiv :2303 .00636v2 [ cond-mat .soft] 23 Feb 2024  \nClassifying the age of a glass based on structural properties: A machine learning  \napproach  \nGiulia Janzen, 1, 2 Casper Smit ∗ , 1, 3 Samantha Visbeek, 1, 3, ∗ Vincent E. Debets, 1, 2 Chengjie Luo, 1, 2 Cornelis Storm, 1, 2 Simone Ciarella, 1, 2, 4, 5,† and Liesbeth M.C. Janssen 1, 2,‡  \n1 Department of Applied Physics, Eindhoven University of Technology,  \nP. O. Box 513, 5600 MB Eindhoven, The Netherlands  \n2 Institute for Complex Molecular Systems, Eindhoven University of Technology,  \nP. O. Box 513, 5600 MB Eindhoven, The Netherlands  \n3 Institute of Physics, University of Amsterdam, Science Park 904, Amsterdam, 1098 XH, The Netherlands  \n4 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  \n5 Netherlands eScience Center, Amsterdam 1098 XG, The Netherlands  \n(Dated: February 26, 2024)  \nIt is well established that physical aging of amorphous solids is governed by a marked change in dynamical properties as the material becomes older. Conversely, structural properties such asthe radial distribution function exhibit only a very weak age dependence, usually deemed negligible with respect to the numerical noise. Here we demonstrate that the extremely weak age-dependent changes in structure are in fact sufficient to reliably assess the age of a glass with the support of machine learning. We employ a supervised learning method to predict the age of a glass based on the system’s instantaneous radial distribution function. Specifically, we train a multilayer perceptron for a model glassformer quenched to different temperatures, and find that this neural network can accurately classify the age of our system across at least four orders of magnitude in time. Our analysis also reveals which structural features encode the most useful information. Overall, this work shows that through the aid of machine learning, a simple structure-dynamics link can indeed be established for physically aged glasses.  \nI. INTRODUCTION  \nThe structural, dynamical and mechanical properties of a material change as it gets older, i.e. it ages [1–9] . Physical aging is particularly well studied for glasses due to their slow relaxation dynamics [10–14] . One of the most common methods to study the aging dynamics of a glass consists of a temperature quench toward a lower temperature [15–18] . After the quench, as the material seeks to recover equilibrium at the new temperature, the relaxation time of the system will increase with its age [10, 19–21] . The physical aging in glassy systems can thus be understood as a gradual approach towards increasingly lower-energy equilibrium states [13] . It is also well known that, besides a rapid short-time change, the structural properties change only extremely weakly with time [22–27] . In contrast, the dynamical properties exhibit significant changes over multiple orders of magnitude in time as shown in Fig. 1 and the Supplementary Material [28] . It is therefore customary to characterize the aging behavior of a system by means of its dynamical properties. At the same time, it remains unclear how these strong dynamical changes of an aging glass are connected to its almost constant structure [24] .  \nTo bridge this gap, Cubuck et al. [29] have recently developed a pioneering approach which demonstrates that  \n∗ These authors contributed equally to this work.† [simoneciarella@gmail.com](simoneciarella@gmail.com)  \n‡ [l.m.c.janssen@tue.nl](l.m.c.janssen@tue.nl)  \nmachine learning techniques can in fact successfully correlate structure and dynamics in glassy systems. Cubucket al. have introduced a machine learning microscopic structural quantity, so-called softness, which characterizes the local structure around each particle. Based on this approach, several recent works [30–41] have extended our conceptual understanding of glassy liquids by convincingly demonstrating that","cbCaijd2CKSsFqYJ","https://ap.wps.com/l/cbCaijd2CKSsFqYJ","pdf",1560077,1,11,"English","en",105,"# Introduction\n## Motivation: structure vs dynamics in glass aging\n## Softness-based machine learning background\n## Goal: classify age from structural snapshots","[{\"question\":\"Why is the age classification challenging when structural changes are weak?\",\"answer\":\"Structural properties like the radial distribution function change only extremely weakly with time, and this is often considered negligible compared with numerical noise. The document addresses whether these subtle structural changes are still sufficient for reliable age assessment.\"},{\"question\":\"What machine-learning method is used to predict the glass age?\",\"answer\":\"A supervised learning approach trains a multilayer perceptron to predict the age using the system’s instantaneous radial distribution function computed at each age.\"},{\"question\":\"Which time range does the model successfully classify?\",\"answer\":\"The neural network can accurately classify the age of the system across at least four orders of magnitude in time.\"}]","Classifying the age of a glass based on structural properties - A machine learning approach | PDF",1785813823,28,{"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":87,"head_meta":89,"extra_data":91,"updated_unix":28},"classifying-the-age-of-a-glass-based-on-structural-properties-a-machine-learning-approach","",{"@graph":36,"@context":86},[37,54,69],{"@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/classifying-the-age-of-a-glass-based-on-structural-properties-a-machine-learning-approach/122945/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-05","2026-08-04",true,{"@type":66,"interactionType":67,"userInteractionCount":20},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72,78,82],{"name":73,"@type":74,"acceptedAnswer":75},"Why is the age classification challenging when structural changes are weak?","Question",{"text":76,"@type":77},"Structural properties like the radial distribution function change only extremely weakly with time, and this is often considered negligible compared with numerical noise. The document addresses whether these subtle structural changes are still sufficient for reliable age assessment.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"What machine-learning method is used to predict the glass age?",{"text":81,"@type":77},"A supervised learning approach trains a multilayer perceptron to predict the age using the system’s instantaneous radial distribution function computed at each age.",{"name":83,"@type":74,"acceptedAnswer":84},"Which time range does the model successfully classify?",{"text":85,"@type":77},"The neural network can accurately classify the age of the system across at least four orders of magnitude in time.","https://schema.org",{"og:url":52,"og:type":88,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":90,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":93},[94,98,102,106,111,116,121,124,129,132,136],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":103,"show_sort_weight":104,"slug":105},"Exam",70,"exam",{"id":107,"doc_module":4,"doc_module_name":46,"category_name":108,"show_sort_weight":109,"slug":110},5,"Comic",60,"comic",{"id":112,"doc_module":4,"doc_module_name":46,"category_name":113,"show_sort_weight":114,"slug":115},6,"Technology",50,"technology",{"id":117,"doc_module":4,"doc_module_name":46,"category_name":118,"show_sort_weight":119,"slug":120},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":122,"slug":123},30,"research-report",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":126,"show_sort_weight":127,"slug":128},9,"Religion & Spirituality",20,"religion-spirituality",{"id":127,"doc_module":4,"doc_module_name":46,"category_name":130,"show_sort_weight":127,"slug":131},"World Cup","world-cup",{"id":133,"doc_module":4,"doc_module_name":46,"category_name":134,"show_sort_weight":133,"slug":135},10,"Lifestyle","lifestyle",{"id":137,"doc_module":4,"doc_module_name":46,"category_name":138,"show_sort_weight":107,"slug":139},19,"General","general"]