[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-125640-en":3,"doc-seo-125640-105":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},125640,962075006959,"Anda","https://ap-avatar.wpscdn.com/avatar/e0002397efbe92a78e?_k=1776741047341049297",8,"Research & Report","Predicting Pair Correlation Functions of Glasses using Machine Learning - Research","Glasses provide tunable thermophysical properties that depend on composition, yet deriving a universal composition–property relation is difficult because of the vast composition and chemical space. This work builds a machine-learning metamodel linking composition to atomistic structure for glassy materials. An unsupervised CNN autoencoder and a Random Forest regression model are combined in a fully automated pipeline to predict atom spatial distributions. The RF model predicts the pair correlation function in a latent space, and the CNN decoder reconstructs the actual pair correlation function. Atomistic structures of SiO2 and NBS-based glasses from MD simulations validate accurate predictions for many unseen compositions.","Predicting Pair Correlation Functions of Glasses using Machine Learning  \nKumar Ayush\\#, Pooja Sahu$, Sk Musharaf Ali$* and Tarak K Patra\\#*  \n\\#Department of Chemical Engineering and Center for Atomistic Modeling and Materials Design, Indian Institute of Technology Madras, Chennai, TN 600036, India  \n$Chemical Engineering Division, Bhabha Atomic Research Center, Mumbai, 400085, India.  \nAbstract  \nGlasses offer a broad range of tunable thermophysical properties that are linked to their compositions. However, it is challenging to establish a universal composition-property relation of glasses due to their enormous composition and chemical space. Here, we address this problem and develop a metamodel of composition-atomistic structure relation of a class of glassy material via a machine learning (ML) approach. Within this ML framework, an unsupervised deep learning technique, viz. convolutional neural network (CNN) autoencoder, and a regression algorithm, viz. random forest (RF), are integrated into a fully automated pipeline to predict the spatial distribution of atoms in a glass. The RF regression model predicts the pair correlation function of a glass in a latent space. Subsequently, the decoder of the CNN converts the latent space representation to the actual pair correlation function of the given glass. The atomistic structures of silicate (SiO2) and sodium borosilicate (NBS) based glasses with varying compositions and dopants are collected from molecular dynamics (MD) simulations to establish and validate this ML pipeline. The model is found to predict the atom pair correlation function for many unknown glasses very accurately. This method is very generic and can accelerate the design, discovery, and fundamental understanding of composition-atomistic structure relations of glasses and other materials.  \nKeywords: Glasses, Pair Correlation Function, ML, Autoencoder and Random Forest Corresponding Authors:  \nTKP: [tpatra@iitm.ac.in](tpatra@iitm.ac.in)  \n[SMA:](SMA: musharaf@barc.gov.in)[ ](SMA: musharaf@barc.gov.in)[musharaf@barc.gov.in](SMA: musharaf@barc.gov.in)  \nI. Introduction  \nGlasses are a unique class of materials that exhibit a disordered atomic structure, unlike crystalline materials.1 They exhibit a wide range of tunable properties, including transparency, chemical durability, and mechanical strength.2 They are commonly used in optical, household, and labware applications. Glasses are also used for the immobilization ofradioactive waste2,3 as they can easily accommodate the miscellaneous waste stream composition containing 137Cs, 90Sr, 106Ru, U, Pu, Th, and their isotopes.2 However, the maximum loading of these ions and isotopes in a glass is limited by many factors such as solubility, melting temperature, nucleation, crystallization, and phase separation.2,4,5 Therefore, the appropriate selection of elements is crucial in determining the glass-forming ability and properties of the final material.6 Elements with large differences in atomic size and positive heat of mixing are often preferred to promote glass formation. By carefully selecting the alloy composition and applying specific processing techniques, it is possible to control the atomic-scale structure and properties of metallic glasses. Added elements can influence properties like hardness, strength, corrosion resistance, and magnetic properties.7–10 Processing parameters such as the cooling rate can affect the final atomistic structure, including grain size, homogeneity, and the presence of residual crystalline phases.11–13 Therefore, the design of metallic glasses requires considering both thermodynamic and kinetic factors.14 Thermodynamic considerations involve assessing the alloy's stability against crystallization, while kinetic considerations involve determining the cooling rate necessary to suppress the nucleation and growth of crystals. Precisely, the glass formation is controlled by too many factors including composition, melt temperature, quench ","cbCaicqz5o98gcXZ","https://ap.wps.com/l/cbCaicqz5o98gcXZ","pdf",1613820,1,19,"English","en",105,"# Abstract\n# Introduction\n## Challenges in glass composition–property mapping\n## Computational approaches and their limitations\n## Motivation for machine learning","[{\"question\":\"How does the proposed machine-learning pipeline predict pair correlation functions for glasses?\",\"answer\":\"It combines an unsupervised CNN autoencoder with a Random Forest regression model. The RF predicts the pair correlation function in a latent space, and the CNN decoder reconstructs the actual pair correlation function from that latent representation.\"},{\"question\":\"What data are used to train and validate the model?\",\"answer\":\"The model is established and validated using atomistic structures of silicate (SiO2) and sodium borosilicate (NBS) based glasses. These structures come from molecular dynamics (MD) simulations with varying compositions and dopants.\"},{\"question\":\"Why is predicting composition–property relations for glasses considered difficult?\",\"answer\":\"Glasses have an enormous composition and chemical space, making it challenging to learn a universal composition–property mapping. The formation and properties depend on many factors, increasing the complexity of screening and prediction.\"}]","Predicting Pair Correlation Functions of Glasses using Machine Learning - Research | PDF",1785900364,48,{"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},"predicting-pair-correlation-functions-of-glasses-using-machine-learning-research","",{"@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/predicting-pair-correlation-functions-of-glasses-using-machine-learning-research/125640/",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},"How does the proposed machine-learning pipeline predict pair correlation functions for glasses?","Question",{"text":75,"@type":76},"It combines an unsupervised CNN autoencoder with a Random Forest regression model. The RF predicts the pair correlation function in a latent space, and the CNN decoder reconstructs the actual pair correlation function from that latent representation.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What data are used to train and validate the model?",{"text":80,"@type":76},"The model is established and validated using atomistic structures of silicate (SiO2) and sodium borosilicate (NBS) based glasses. These structures come from molecular dynamics (MD) simulations with varying compositions and dopants.",{"name":82,"@type":73,"acceptedAnswer":83},"Why is predicting composition–property relations for glasses considered difficult?",{"text":84,"@type":76},"Glasses have an enormous composition and chemical space, making it challenging to learn a universal composition–property mapping. The formation and properties depend on many factors, increasing the complexity of screening and prediction.","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":21,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":106,"slug":137},"General","general"]