[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-121130-en":3,"doc-seo-121130-105":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},121130,8796095461610,"Oliver","https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c",8,"Research & Report","Describe, Transform, Machine Learning - Feature Engineering for Grain Boundaries and Other Variable-Sized Atom Clusters","Obtaining microscopic structure-property relationships for grain boundaries is difficult due to complex atomic structures underlying their behavior, making machine-learning representations nontrivial. Property prediction for grain boundaries and other variable-sized atom clustered structures follows three shared steps: describe atomic structures as feature matrices, transform variable-sized matrices to a fixed common length, and apply machine learning for property prediction. Using a dataset of over 7000 grain boundaries, the study evaluates feature-engineering combinations and their accuracy impacts, while also assessing interpretability through extracting physical insights.","Describe, Transform, Machine Learning: Feature Engineering for Grain Boundaries  \nand Other Variable-Sized Atom Clusters  \nC. Braxton Owensa , Nithin Mathewb , Tyce W. Olavesonf , Jacob P. Tavennerd , Edward M. Koberb , Garritt J. Tuckere ,  \nGus L. W. Hartf,∗, Eric R. Homerg,∗  \na Department of Computer Science Brigham Young University, Provo, 84602, UT, USA  \nb Group T-1, Theoretical Division, Los Alamos National Laboratory, Los Alamos, 87544, NM, USAc Center for Non-Linear Studies, Theoretical Division, Los Alamos National Laboratory, Los Alamos, 87544, NM, USA dKBR, Inc., Intelligent Systems Division, NASA Ames Research Center, Moffett Field, 94035, CA, USA e Department of Physics, Baylor University, Waco, 76798, TX, USA  \nfDepartment of Physics and Astronomy Brigham Young University, Provo, 84602, UT, USA  \ng Department of Mechanical Engineering Brigham Young University, Provo, 84602, UT, USA  \nAbstract  \nObtaining microscopic structure-property relationships for grain boundaries are challenging because of the complex atomic structures that underlie their behavior. This has led to recent efforts to obtain these relationships with machine learning, but representing a grain boundary structure in a manner suitable for machine learning is not a trivial task.  \n30 Jul 2024  \nThere are three key steps common to property prediction in grain boundaries and other variable-sized atom clustered structures. These are: (1) describe the atomic structure as a feature matrix, (2) transform the variable-sized feature matrices of different structures to a fixed length common to all structures, and (3) apply machine learning to predict properties from the transformed feature matrices. We examine these feature engineering steps to understand how they impact the accuracy of grain boundary energy predictions. A database of over 7000 grain boundaries serves to evaluate the different feature engineering combinations. We also examine how these combination of engineered features provide interpretability, or the ability to extract insightful physics from the obtained structure-property relationships.  \nKeywords: Grain Boundaries, Atomic Structure, Structure Descriptor, Machine learning, Feature Engineering, Structure-Property Relationships  \nIntroduction  \nDue to the impact of grain boundaries (GBs) on material properties [1–4], there is a need to better understand the relationship between the structure of a GB and its corresponding properties. With expanding computing power, increasingly large amounts of data, and advances in data-driven approaches, there has been a push for suitable representations of GBs in order to predict their properties [5–37] . However, accurate property prediction is not the only measure of success. Models and representations that provide insight into structure-property relationships are key to advance our understanding.  \nRepresenting a GB starts with defining its structure, since it has both macroscopic and microscopic characteristics. Macroscopically, five degrees of freedom are used to define the GB character: Three to define a misorientation between two crystals, (often given by a normalized rotation axis [uvw] and angle θ), and two to define a boundary plane (hkl) . Microscopically, the positions of the atoms  \nresult in 3n degrees of freedom. Additionally, a GB can assume various metastable configurations under any given set of macroscopic constraints.[13, 24, 38–42] .  \nWhile there have been impressive developments in macroscopic representations for better understanding GBs [12, 35, 43–46], the atomic structure is what defines a GB’s properties. This article concentrates on the microscopic structure-property relationships since the macroscopic structure acts as a constraint on the microscopic structure.  \nOne microscopic method for defining a GB is the structural unit model [47–50] . This model describes the atomic structure of a quasi two-dimensional GB as a series of repeating atomic “structural units” that are c","cbCaiamdqznwDxto","https://ap.wps.com/l/cbCaiamdqznwDxto","pdf",3072561,1,18,"English","en",105,"# Abstract\n# Introduction\n## Structure-property relationships for grain boundaries\n## Defining grain boundary structure: macroscopic and microscopic degrees of freedom\n## Microscopic modeling approaches and local atomic environment descriptors\n## Feature engineering workflow for machine learning property prediction\n# Figure 1: Workflow overview","[{\"question\":\"Why is representing grain boundary structures for machine learning challenging?\",\"answer\":\"Grain boundaries have complex atomic structures, and converting those structures into machine-learning-ready representations is not trivial. Accurate learning requires suitable descriptors and consistent feature formats.\"},{\"question\":\"What are the three key steps used for property prediction in grain boundaries and variable-sized atom clusters?\",\"answer\":\"First, atomic structures are described as feature matrices. Second, variable-sized feature matrices are transformed into a fixed-length common representation. Third, machine learning predicts properties from the transformed matrices.\"},{\"question\":\"How is interpretability addressed in the proposed feature engineering approach?\",\"answer\":\"By using engineered features that enable extracting insightful physics from the learned structure-property relationships, not only improving prediction accuracy.\"}]","Describe, Transform, Machine Learning - Feature Engineering for Grain Boundaries and Other Variable-Sized Atom Clusters | PDF",1785733926,45,{"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},"describe-transform-machine-learning-feature-engineering-for-grain-boundaries-and-other-variable-sized-atom-clusters","",{"@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/describe-transform-machine-learning-feature-engineering-for-grain-boundaries-and-other-variable-sized-atom-clusters/121130/",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},"Why is representing grain boundary structures for machine learning challenging?","Question",{"text":75,"@type":76},"Grain boundaries have complex atomic structures, and converting those structures into machine-learning-ready representations is not trivial. Accurate learning requires suitable descriptors and consistent feature formats.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What are the three key steps used for property prediction in grain boundaries and variable-sized atom clusters?",{"text":80,"@type":76},"First, atomic structures are described as feature matrices. Second, variable-sized feature matrices are transformed into a fixed-length common representation. Third, machine learning predicts properties from the transformed matrices.",{"name":82,"@type":73,"acceptedAnswer":83},"How is interpretability addressed in the proposed feature engineering approach?",{"text":84,"@type":76},"By using engineered features that enable extracting insightful physics from the learned structure-property relationships, not only improving prediction accuracy.","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"]