[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-117506-en":3,"doc-seo-117506-105":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},117506,1099514067438,"River Wang","https://ap-avatar.wpscdn.com/avatar/100002539ee87300030?x-image-process=image/resize,m_fixed,w_180,h_180&k=1780474512215547542",8,"Research & Report","Improving XRD Analysis with Machine Learning - Thesis","X-ray diffraction analysis (XRD) quantifies relative mineral phase proportions in rock or soil samples, yet traditional software demands extensive user-driven phase selection. Analytical accuracy therefore depends heavily on analyst experience, especially as the number of phases increases. This project evaluates whether integrating machine learning into XRD software can enhance phase-picking accuracy. A training dataset of 1.5 million realistic calculated XRD patterns was generated from crystal structures and geologic occurrence knowledge. Multiple model types were trained and refined to identify the most accurate approach for phase identification.","Improving XRD Analysis with Machine Learning  \nRachel E. Drapeau  \nA thesis submitted to the faculty of Brigham Young University  \nin partial fulfillment of the requirements for the degree of  \nMaster of Science  \nBarry R. Bickmore, Chair Emily J. Evans  \nStephen T. Nelson  \nDepartment of Geological Sciences Brigham Young University  \nCopyright ©2023 Rachel E. Drapeau All Rights Reserved  \nABSTRACT  \nImproving XRD Analysis with Machine Learning  \nRachel E. Drapeau  \nDepartment of Geological Sciences, BYU  \nMaster of Science  \nX-ray diffraction analysis (XRD) is an inexpensive method to quantify the relative proportions of mineral phases in a rock or soil sample. However, the analytical software available for XRD requires extensive user input to choose phases to include in the analysis. Consequently, analysis accuracy depends greatly on the experience of the analyst, especially asthe number of phases in a sample increases (Raven & Self, 2017; Omotoso, 2006) . The purpose of this project is to test whether incorporating machine learning methods into XRD software can improve the accuracy of analyses by assisting in the phase-picking process. In order to provide a large enough sample of X-ray diffraction (XRD) patterns and their known compositions to train the machine learning models, I created a dataset of 1.5 million calculated XRD patterns of realistic mineral mixtures. These synthetic XRD patterns were calculated using crystal structure files from the American Mineralogist Crystal Structure Database (AMCSD) with mineral occurrence data from the Mineral Evolution Database (MED) to mimic geologic knowledge used by expert analysts. Using this dataset, I trained and refined a variety of machine learning models to determine which model is most accurate in identifying the correct mineral phases.  \nKeywords: X-ray diffraction analysis, XRD, machine learning, Rietveld method, crystal  \nstructure, classification, decision trees, bagged decision trees, data generation, mineral, mixture  \nACKNOWLEDGEMENTS  \nFirst and foremost, I would like to thank my husband, Joseph. I would never have completed my degree without his loving support and encouragement. He was the one who would help me out of my slumps and provide invaluable insight when problems occurred. I am immensely grateful and so lucky to have such a loving and selfless spouse. Thank you, and our children, for being my light and my motivation.  \nThank you to my advisor, Dr. Barry Bickmore, for all of his support and flexibility. I really appreciate his understanding when trying to balance my master’s program with raising my family. I’m very grateful he gave me this opportunity and for his continued support.  \nI would also like to thank Dr. Emily Evans for her assistance and advisement on this project. Her machine learning and math expertise was invaluable. Thank you to Dr. Stephen Nelson as well for his input and insight into the practicality of this project as well.  \nThank you to Steve Maroney in the Mathematics Department for his assistance with the computer servers I used to generate the data and train the models.  \nMany thanks to Karla Ward and Dr. John McBride for helping me with the administrative hiccups I came across and their support and encouragement.  \nThank you to my family and friends for their support with our family and vast encouragement as I worked on my thesis. They helped get me through the home stretch and I’m lucky to have so many people on my side.  \nTABLE OF CONTENTS  \nAbstract ........................................................................................................................................... ii  \nAcknowledgements ........................................................................................................................ iii  \nTable of Contents ........................................................................................................................... iv  \nList of Figures ......................................","cbCaityN9wGwKauc","https://ap.wps.com/l/cbCaityN9wGwKauc","pdf",2491059,1,99,"English","en",105,"# Abstract\n# Acknowledgements\n# Table of Contents\n# List of Figures\n# List of Tables\n# Introduction\n# Background\n## XRD by Full-Pattern Fitting\n## XRD by the Rietveld Method\n### Rietveld Analysis to Determine Phases\n### Calculating a Pattern from Crystal Structure\n## Machine Learning Algorithms\n### Decision Trees and Random Forests\n### Boosted Decision Trees\n### K-Nearest Neighbors (KNN)\n### Support Vector Machines (SVM)\n### Neural Networks\n### Logistic Regression\n# Methods\n## Synthetic Data Set","[{\"question\":\"Why does phase-picking accuracy in XRD depend on analyst experience?\",\"answer\":\"Conventional XRD software requires users to select phases to include in the analysis. As the number of phases increases, accurate selection becomes more challenging, making results highly experience-dependent.\"},{\"question\":\"How was the machine learning training data created?\",\"answer\":\"A dataset of 1.5 million calculated XRD patterns was generated using crystal structure files from the American Mineralogist Crystal Structure Database and mineral occurrence data from the Mineral Evolution Database to mimic expert geologic knowledge.\"},{\"question\":\"What models were trained to identify the correct mineral phases?\",\"answer\":\"The work trains and refines multiple machine learning model types, including decision trees/random forests, boosted decision trees, K-nearest neighbors, support vector machines, neural networks, and logistic regression, then compares their accuracy for phase identification.\"}]","Improving XRD Analysis with Machine Learning - Thesis | PDF",1785676440,249,{"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},"improving-xrd-analysis-with-machine-learning-thesis","",{"@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/improving-xrd-analysis-with-machine-learning-thesis/117506/",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","2026-08-02",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 does phase-picking accuracy in XRD depend on analyst experience?","Question",{"text":76,"@type":77},"Conventional XRD software requires users to select phases to include in the analysis. As the number of phases increases, accurate selection becomes more challenging, making results highly experience-dependent.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"How was the machine learning training data created?",{"text":81,"@type":77},"A dataset of 1.5 million calculated XRD patterns was generated using crystal structure files from the American Mineralogist Crystal Structure Database and mineral occurrence data from the Mineral Evolution Database to mimic expert geologic knowledge.",{"name":83,"@type":74,"acceptedAnswer":84},"What models were trained to identify the correct mineral phases?",{"text":85,"@type":77},"The work trains and refines multiple machine learning model types, including decision trees/random forests, boosted decision trees, K-nearest neighbors, support vector machines, neural networks, and logistic regression, then compares their accuracy for phase identification.","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"]