[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-124143-en":3,"doc-seo-124143-105":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},124143,7971461740909,"Levi","https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d",8,"Research & Report","Development and Application of Scalable Density Functional Theory Machine Learning Models - Dissertation","Electronic structure simulations enable computation of fundamental material properties without experiments, accelerating progress in materials science and chemical applications. Density functional theory (DFT) has become a dominant method by balancing accuracy and computational cost, but growing societal and technological demands require solutions for increasingly complex problems. Even efficient DFT implementations struggle to meet time and resource constraints. This motivates machine learning (ML) models that aim to reproduce DFT predictive power at negligible cost. The thesis shows that prior ML-DFT approaches fail to fully match DFT-level predictions and introduces a scalable ML-DFT framework.","Faculty of Physics Institute of Nuclear and Particle Physics, Chair of Radiation Physics  \nDevelopment and Application of Scalable Density Functional Theory Machine Learning Models  \nLenz Fiedler  \nDissertation  \nto achieve the academic degree  \nDoktor rerum naturalium (Dr. rer. nat.)  \nFirst referee  \nProf. Dr. Thomas Cowan Second referee  \nProf. Dr. Aurora Pribram-Jones Supervisor  \nDr. Attila Cangi Supervising professor  \nProf. Dr. Thomas Cowan  \nSubmitted on: 15th February 2024  \nDefended on: 28th August 2024  \n“Ludwig Boltzmann, who spent much of his life studying statistical mechanics, died in 1906, by his own hand. Paul Ehrenfest, carrying on the work, died similarly in 1933 . Now it is our turn to study statistical mechanics. Perhaps it will be wise to approach the subject cautiously.”  \nDavid L. Goodstein, States of Matter  \nAcknowledgments  \nIt is said that it takes a village to raise a child. If that is true, then it takes similarly sized settlement to help that child obtain their doctoral degree. In writing the final words of this thesis, I am overcome with gratitude towards the many different people that supported and cared for me over the last years. First and foremost, I would like to extend my unquantifiable gratefulness to my supervisor, Dr. Attila Cangi, who has not only been a constant source of advice and knowledge, but further never failed to look out and stand up for me or my peers. No metaphorical village could ever ask for a better elder. Secondly, I would like to deeply thank my good friend and co-worker Pia Hanfeld for her continued support and useful remarks in writing this thesis. I would especially like to extend my gratitude to her for making me aware of a village I may otherwise have never found. I would further like to deeply thank my supervising professor, Prof. Dr. Thomas E. Cowan, for giving me the opportunity to pursue my doctoral degree under his supervision.  \nNo scientific progress is a solitary effort. Over the last years I had the opportunity to collaborate with many wonderful scientists, mainly at the Center of Advanced Systems Understanding and the Sandia National Laboratories, as well as other institutions. I am deeply grateful to all these collaborations and connections, and the insights and discussions I was able to enjoy as a result. I would like to thank all collaborators of my publications, but especially acknowledge Dr. Austin J. Ellis, Kyle D. Miller, Dr. Zhandos A. Moldabekov, Dr. Sivasankaran Rajamanickam, Karan Shah, Dr. Aidan P. Thompson, Dr. D. Jon Vogel as well as Dr. Normand A. Modine, who also provided useful remarks for this work.  \nPursuing my doctoral degree at the Center for Advanced Systems Understanding allowed me to thrive in a unique environment. Not many people get to rediscover their hometown with a group of international scientists, but I am one of the lucky few. I would like to extend my gratitude to the wonderful people of the Center for Advanced Systems Understanding,(former) student researchers, and alumni for creating such a vibrant scientific atmosphere. A special thanks is reserved for the teenagers of Jugend Hackt Görlitz, who I had the pleasure to mentor in the last years. I have found their earnest fascination of computer science a constant source of inspiration.  \nIn a similar vein I would like to extend my gratitude to my friends and family, who balanced out even the intensest of workloads. Some of whom even were so kind as to directly further this work by providing useful remarks and feedback, and for that I would like to acknowledge Dr. Timothy J. Callow, Dr. Sebastian Schwalbe and Anja Weber. I would also like to deeply thank my childhood friends Lukas Jonscher and Yvonne Geißler for being calming constants through the turmoil of the past years. For her unwavering support, love, and patience over the last months, as well as useful remarks, I would especially like to extend my deepest, most heartfelt gratitude to my wonderful partner, Emilia Za","cbCaird6dXlzWvVY","https://ap.wps.com/l/cbCaird6dXlzWvVY","pdf",27716337,1,199,"English","en",105,"# Acknowledgments\n## Collaborations and support\n## Mentoring and community\n# Abstract\n## Motivation and challenges\n## Proposed ML-DFT framework","[{\"question\":\"Why are electronic structure simulations important in materials science?\",\"answer\":\"They compute fundamental material properties without experiments, supporting scientific advances across materials science and chemical applications.\"},{\"question\":\"What limitation of DFT motivates the use of machine learning?\",\"answer\":\"DFT becomes too slow for increasingly complex problems when considering available computational resources and required turnaround time.\"},{\"question\":\"What does the thesis contribute to ML-DFT?\",\"answer\":\"It assesses shortcomings of existing ML-DFT approaches and presents a new framework for training ML-DFT models using a local representation, including detailed treatment of data generation and hyperparameter optimization.\"}]","Development and Application of Scalable Density Functional Theory Machine Learning Models - Dissertation | PDF",1785820685,501,{"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},"development-and-application-of-scalable-density-functional-theory-machine-learning-models-dissertation","",{"@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/development-and-application-of-scalable-density-functional-theory-machine-learning-models-dissertation/124143/",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","2026-08-04",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 are electronic structure simulations important in materials science?","Question",{"text":75,"@type":76},"They compute fundamental material properties without experiments, supporting scientific advances across materials science and chemical applications.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What limitation of DFT motivates the use of machine learning?",{"text":80,"@type":76},"DFT becomes too slow for increasingly complex problems when considering available computational resources and required turnaround time.",{"name":82,"@type":73,"acceptedAnswer":83},"What does the thesis contribute to ML-DFT?",{"text":84,"@type":76},"It assesses shortcomings of existing ML-DFT approaches and presents a new framework for training ML-DFT models using a local representation, including detailed treatment of data generation and hyperparameter optimization.","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"]