[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-118564-en":3,"doc-seo-118564-105":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},118564,13056703019662,"Evangeline","https://ap-avatar.wpscdn.com/avatar/be000253a8e92610077?_k=1778726343310543188",8,"Research & Report","Discovering Thermoelectric Materials with Modern Machine Learning Approaches","Machine learning is increasingly used to accelerate the discovery and design of new materials. Thermoelectrics are energy materials with strong potential to mitigate environmental challenges. This thesis develops machine learning methodologies for predicting material properties and generating crystal structures to enable the discovery of new, more effective thermoelectric materials. Approaches include formula-only distributed representations, attention-based transport-property prediction with reduced ab initio cost, and generative crystal-structure suggestions from chemical compositions.","University of Reading Department of Chemistry  \nDiscovering Thermoelectric Materials with Modern Machine Learning Approaches  \nLuis M. Antunes  \nSupervisors: Dr Ricardo Grau-Crespo, Dr Keith Butler  \nA thesis submitted in partial ful􀀌lment of the requirements of the University of Reading for the degree of  \nDoctor of Philosophy in Chemistry  \nSeptember 2024  \nDeclaration  \nI, Luis M. Antunes, of the Department of Chemistry, University of Reading, con􀀌rm that this is my own work, and that all 􀀌gures, tables, equations, code snippets, artworks, and illustrations in this report are original and have not been taken from any other person's work, except where the works of others have been explicitly acknowledged, quoted, and referenced. I understand that failure to do so will be considered a case of plagiarism. Plagiarism is a form of academic misconduct and will be penalised accordingly.  \nLuis M. Antunes September 2024  \nAbstract  \nMachine learning is increasingly utilized to accelerate the discovery and design of new materials. Thermoelectrics are an important class of energy materials with the potential to help address pressing environmental challenges. This thesis presents novel machine learning-based methodologies for predicting material properties and generating crystal structures, with a focus on the discovery of new, and more e􀀋ective, thermoelectric materials. First, a method is introduced for deriving distributed representations of materials solely from their chemical formulas, which demonstrates competitive performance in predicting various properties, such as formation energy and band gap. Next, an attention-based deep learning model is developed to predict thermoelectric transport properties, which incorporates the distributed representations, and proves capable of making useful predictions with a signi􀀌cantly reduced computational cost compared to traditional ab initio methods. Finally, a generative model is proposed that is capable of suggesting crystal structures for chemical compositions, which is vital for progressing from estimates of thermoelectric performance from composition, to deeper investigation based on structure. The results from these studies demonstrate the potential for modern machine learning techniques in the 􀀌eld of materials discovery, and particularly for accelerating the discovery of novel thermoelectrics.  \nKeywords: thermoelectrics, machine learning, large language models  \nAcknowledgements  \nI would like to express my deepest gratitude to my supervisor, Dr Ricardo Grau-Crespo, who has been my unwavering partner on this voyage. His continual guidance, support, and encouragement have been invaluable, especially during the challenging times when things didn't go as planned. His patience and belief in me and my work helped me navigate some rough seas, and kept me on course. I would also like to sincerely thank my second supervisor, Dr Keith Butler, for his insightful feedback and steadfast belief in me and my ideas. His expertise and input have been instrumental in re􀀌ning my work, and in helping me approach challenges from new perspectives. I owe them immensely for their mentorship, patience, and the profound impact they've had on this thesis and on my personal and professional growth.  \nI am extremely grateful for having been granted access to the supercomputing facilities, ARCHER/ARCHER2, the UK's national high-performance computing service, via the UK's HPC materials chemistry consortium and Young supercomputer, via the UK's materials and molecular modelling hub.  \nFinally, I would like to thank my family for their unwavering love, understanding, and endless support throughout this journey. Their encouragement and belief in me gave me the strength to persevere. They too have endured challenges along the way, and for that, I will be forever grateful.  \nThank you to everyone who has supported me along this journey.  \nList of Publications  \nThe work presented in this thesis has been published (o","cbCaiijvhEsTNlBL","https://ap.wps.com/l/cbCaiijvhEsTNlBL","pdf",21179516,1,199,"English","en",105,"# Introduction\n## Machine Learning Approaches for the Discovery of New Thermoelectrics\n## Aims and Objectives of the Thesis\n# Methodology\n## Deep Learning\n## Local and Distributed Representations","[{\"question\":\"What is the main goal of the thesis?\",\"answer\":\"To use modern machine learning methods to predict thermoelectric material properties and generate crystal structures, accelerating the discovery of new and more effective thermoelectrics.\"},{\"question\":\"How does the thesis derive material representations?\",\"answer\":\"It introduces distributed representations derived solely from chemical formulas, enabling competitive prediction of properties such as formation energy and band gap.\"},{\"question\":\"What kinds of machine learning models are proposed and what do they do?\",\"answer\":\"An attention-based deep learning model predicts thermoelectric transport properties with significantly reduced computational cost, and a generative model suggests crystal structures for given chemical compositions.\"}]","Discovering Thermoelectric Materials with Modern Machine Learning Approaches | PDF",1785684256,501,{"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},"discovering-thermoelectric-materials-with-modern-machine-learning-approaches","",{"@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/discovering-thermoelectric-materials-with-modern-machine-learning-approaches/118564/",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","2026-08-02",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 is the main goal of the thesis?","Question",{"text":75,"@type":76},"To use modern machine learning methods to predict thermoelectric material properties and generate crystal structures, accelerating the discovery of new and more effective thermoelectrics.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does the thesis derive material representations?",{"text":80,"@type":76},"It introduces distributed representations derived solely from chemical formulas, enabling competitive prediction of properties such as formation energy and band gap.",{"name":82,"@type":73,"acceptedAnswer":83},"What kinds of machine learning models are proposed and what do they do?",{"text":84,"@type":76},"An attention-based deep learning model predicts thermoelectric transport properties with significantly reduced computational cost, and a generative model suggests crystal structures for given chemical compositions.","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"]