[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-123963-en":3,"doc-seo-123963-105":30,"detail-sidebar-cat-0-en-105":95},{"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},123963,2336464648322,"Aria","https://ap-avatar.wpscdn.com/avatar/2200025388227c56fec?_k=1778556882303663488",8,"Research & Report","Towards Machine Learning Foundation Models for Materials Chemistry - Doctoral Dissertation","This PhD thesis shows how recent machine learning advances for materials can accelerate the search for new stable inorganic crystals. It compares model utility, defines expected coverage for a foundational ML force field, and identifies remaining limitations of current ML potentials with approaches to address them. The work introduces Matbench Discovery as an evaluation framework resembling real materials campaigns, establishing universal interatomic potentials as state of the art for thermodynamically stable crystal discovery. An ML-guided dielectric discovery workflow enables rapid screening, crystal generation, and high-throughput ab-initio validation feeding experimental characterization, culminating in synthesis of CsTaTeO6 and Bi2Zr2O7. Finally, it analyzes MACE-MP as a versatile foundation model for atomistic simulations and demonstrates strong qualitative and quantitative agreement with density functional theory across 36 diverse test cases.","Towards Machine Learning Foundation Models for Materials Chemistry  \nJanosh Riebesell  \nUniversity of Cambridge St. Catherine's College Department of Physics  \nThis dissertation is submitted for the degree of Doctor of Philosophy  \nSupervisors Alpha Lee, Ulrich Keyser  \nAdvisors Anubhav Jain, Rhys Goodall, Kristin Persson  \nExaminers Chris Pickard, Aaron Walsh  \nSubmission Date June 2024  \nDeclaration of Authorship  \nThis thesis is the result of my own work and includes nothing which is the outcome of work done in collaboration except as declared in the preface and specified in the text. It is not substantially the same as any work that has already been submitted, or, is being concurrently submitted, for any degree, diploma or other qualification at the University of Cambridge or any other University or similar institution except as declared in the preface and specified in the text. It does not exceed the prescribed word limit for the relevant Degree Committee.  \nAbstract  \nThis thesis demonstrates how recent advances in machine learning (ML) for materials can accelerate our search for new stable inorganic crystals. We show how best to measure and compare the utility of different models, what range of applications a foundational ML force field can be expected to cover, what remaining shortcomings current ML potentials exhibit and how some of them can be overcome. Specifically, we present Matbench Discovery, an evaluation framework that closely mimics a real-world materials discovery campaign and establishes universal interatomic potentials (UIPs) as the state-of-the-art ML method for accelerating the discovery of thermodynamically stable inorganic crystals.  \nNext, we design and execute an ML-guided dielectric discovery workflow that integrates rapid ML screening, targeted crystal generation and high-throughput ab-initio validation all feeding into informed experimental characterization which culminated in the synthesis of two novel dielectric materials, CsTaTeO6 and Bi2 Zr2 O7 , with CsTaTeO6 generated by our workflow.  \nFinally, we comprehensively analyze MACE-MP, the best-performing model we trained for Matbench Discovery, which has since proven to be a highly versatile foundation model for atomistic simulations. While pre-trained purely on inorganic bulk crystals, it exhibits unexpected extrapolation to diverse chemistries and material classes far beyond its training distribution, as evidenced by its qualitative and often even quantitative agreement with density functional theory (DFT) in 36 diverse test cases, including phonon spectra, ammonia/borane, amorphous carbon, aqueous interfaces, batteries, carburane, cathode materials, combustion, dichalcogenides, dislocation, dissolution, heterogeneous catalysis, hydrogen, ice & water, MOFs, molten salts, multi-component alloys, nanoparticles, Perovskites, polymerization, Pt surface, Si interstitial, solvent mixtures, zeolites and more.  \nTaken together, these projects showcase how graph neural network (GNN) force fields can form a central pillar of computational materials science, inhabiting a different point on the cost-accuracy Pareto front than DFT, not much worse in accuracy yet orders of magnitude cheaper thanks to linear instead of cubic scaling with system size. Machine learning force fields  \nhave thus unlocked the study of complex phenomena over length and time scales previously inaccessible to numerical simulation.  \nUniversity of Cambridge, June 2024 Janosh Riebesell  \nAcknowledgements  \nBig thanks to Alpha, Anubhav, Kristin and Rhys who all massively inspired and influenced my work, offering valuable advice and ideas that helped me navigate a quickly evolving research landscape. I am deeply grateful to Hai-Chen Wang, Silvana Botti and Miguel A. L. Marques for their extremely valuable data contributions which they freely share with the community. The Wang-Botti-Marques (WBM) dataset [1] was instrumental in the design of Matbench Discovery (Chapter 3), and I anticipa","cbCaih0wnV83cMGi","https://ap.wps.com/l/cbCaih0wnV83cMGi","pdf",19438031,1,181,"English","en",105,"# Abstract\n# Declaration of Authorship\n# Acknowledgements","[{\"question\":\"What problem does this thesis focus on in materials chemistry?\",\"answer\":\"It addresses how machine learning can accelerate the discovery of new thermodynamically stable inorganic crystals by improving models and workflows for materials search and validation.\"},{\"question\":\"What is Matbench Discovery and why is it important?\",\"answer\":\"Matbench Discovery is an evaluation framework that mimics real-world materials discovery campaigns, used to establish universal interatomic potentials as a state-of-the-art ML approach for stable crystal discovery.\"},{\"question\":\"How did the thesis achieve dielectric material synthesis?\",\"answer\":\"It designed and executed an ML-guided dielectric discovery workflow combining rapid ML screening, targeted crystal generation, and high-throughput ab-initio validation, which then informed experimental characterization to synthesize CsTaTeO6 and Bi2Zr2O7.\"},{\"question\":\"What does the thesis claim about MACE-MP’s generalization ability?\",\"answer\":\"MACE-MP, trained on inorganic bulk crystals, shows unexpected extrapolation across diverse chemistries and material classes, aligning qualitatively and often quantitatively with density functional theory in 36 varied test cases.\"}]","Towards Machine Learning Foundation Models for Materials Chemistry - Doctoral Dissertation | PDF",1785819468,456,{"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":90,"head_meta":92,"extra_data":94,"updated_unix":28},"towards-machine-learning-foundation-models-for-materials-chemistry-doctoral-dissertation","",{"@graph":36,"@context":89},[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/towards-machine-learning-foundation-models-for-materials-chemistry-doctoral-dissertation/123963/",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",[71,77,81,85],{"name":72,"@type":73,"acceptedAnswer":74},"What problem does this thesis focus on in materials chemistry?","Question",{"text":75,"@type":76},"It addresses how machine learning can accelerate the discovery of new thermodynamically stable inorganic crystals by improving models and workflows for materials search and validation.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What is Matbench Discovery and why is it important?",{"text":80,"@type":76},"Matbench Discovery is an evaluation framework that mimics real-world materials discovery campaigns, used to establish universal interatomic potentials as a state-of-the-art ML approach for stable crystal discovery.",{"name":82,"@type":73,"acceptedAnswer":83},"How did the thesis achieve dielectric material synthesis?",{"text":84,"@type":76},"It designed and executed an ML-guided dielectric discovery workflow combining rapid ML screening, targeted crystal generation, and high-throughput ab-initio validation, which then informed experimental characterization to synthesize CsTaTeO6 and Bi2Zr2O7.",{"name":86,"@type":73,"acceptedAnswer":87},"What does the thesis claim about MACE-MP’s generalization ability?",{"text":88,"@type":76},"MACE-MP, trained on inorganic bulk crystals, shows unexpected extrapolation across diverse chemistries and material classes, aligning qualitatively and often quantitatively with density functional theory in 36 varied test cases.","https://schema.org",{"og:url":52,"og:type":91,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":93,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":96},[97,101,105,109,114,119,124,127,132,135,139],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":106,"show_sort_weight":107,"slug":108},"Exam",70,"exam",{"id":110,"doc_module":4,"doc_module_name":46,"category_name":111,"show_sort_weight":112,"slug":113},5,"Comic",60,"comic",{"id":115,"doc_module":4,"doc_module_name":46,"category_name":116,"show_sort_weight":117,"slug":118},6,"Technology",50,"technology",{"id":120,"doc_module":4,"doc_module_name":46,"category_name":121,"show_sort_weight":122,"slug":123},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":125,"slug":126},30,"research-report",{"id":128,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":130,"slug":131},9,"Religion & Spirituality",20,"religion-spirituality",{"id":130,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":130,"slug":134},"World Cup","world-cup",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":136,"slug":138},10,"Lifestyle","lifestyle",{"id":140,"doc_module":4,"doc_module_name":46,"category_name":141,"show_sort_weight":110,"slug":142},19,"General","general"]