[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-122546-en":3,"doc-seo-122546-105":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":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},122546,1099514068365,"Aurelia","https://ap-avatar.wpscdn.com/avatar/10000253d8d9f28188e?_k=1776742907772140068",8,"Research & Report","Machine Learning Force Fields for Modelling Reactions at Complex Interfaces","Computational modelling at the atomic scale faces a long-standing trade-off between accuracy and computational cost. Machine learning force fields (MLFFs) learn from quantum mechanical data to predict energies and forces with near quantum accuracy at orders-of-magnitude lower cost, and—under locality—scale linearly with system size. This thesis investigates MLFFs for reactive and catalytic processes at complex interfaces, including automated training using model uncertainty, quantum-accurate barrier prediction, and free-energy barrier evaluation capturing entropic finite-temperature effects.","Machine Learning Force Fields  \nfor Modelling Reactions at Complex Interfaces  \nLars Leon Schaaf  \nUniversity of Cambridge Wolfson College  \nThis dissertation is submitted for the degree of Doctor of Philosophy  \nApril 2025  \nTo my parents, for showing me the joy of asking ’why?’. . .  \nDeclaration  \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 or 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 or specified in the text. It does not exceed the prescribed word limit for the relevant Degree Committee.  \nLars Leon Schaaf  \nApril 2025  \nAbstract  \nComputational modelling at the atomic scale has traditionally been constrained by a stark trade-off between accuracy and computational cost. Recently, machine learning (ML) architectures have been trained on highly accurate quantum mechanical calculations to sidestep this constraint [1, 2] . So-called machine learning force fields (MLFFs) predict energies and forces on atomic configurations at near quantum mechanical accuracy with orders-of-magnitude reduction in computational cost. Furthermore, under the assumption of locality, MLFFs scale linearly with system size, while even approximate electronic structure methods such as density functional theory (DFT) scale cubically.  \nIn this thesis, we explore how MLFFs can be used to model complex reactive systems. We examine both catalytic reactions at oxide interfaces and carbon capture in porous materials. A key obstacle to the widespread use of MLFFs for complex systems is the need to curate relevant training datasets that lead to accurate and trustworthy results. We present an automated framework for training force fields for reactive systems which uses model uncertainty to iteratively improve and select new configurations for evaluation with the reference method. The protocol is validated on the extensively explored hydrogenation of carbon dioxide to methanol over indium oxide. We demonstrate that our workflow can be used to determine energy barriers with quantum mechanical accuracy, requiring minimal human supervision.  \nFurthermore, we show that machine learning surrogate modelling not only reduces the computational cost of routine in silico catalytic simulation tasks but also allows for an entirely new approach to computational modelling. We capture entropic finite-temperature effects by computing free-energy barriers. For a single barrier calculation of formaldehyde conversion over indium oxide, this requires 107 energy evaluations. Although quantum mechanical calculations would take more than a century to run on a modern supercomputer, we can obtain the answers within a single day.  \nMoreover, the fractional computational cost allows us to explore reactions in greater detail. Our automated reaction path search identifies an alternative reaction  \nprogression with a 40% reduction in activation energy for the previously assumed rate-limiting step in CO2 hydrogenation to methanol on indium oxide. The ability of MLFFs to enhance our understanding of extensively studied catalysts underscores the need for fast and accurate alternatives to direct ab-initio simulations.  \nNext, we show that the training workflow is also applicable for curating training data for porous metal-organic frameworks to simulate carbon capture. With the help of this workflow, we can decipher previously unexplained NMR spectra, leading to a more accurate understanding of the carbon capture mechanism. Additionally, we explore how recent developments in atomistic foundation models can be used to accelerate the MLFF training workflow through fine-tuning and initial dataset curation.  \nFinally, we address one of the key limitat","cbCain4IdbdEDgka","https://ap.wps.com/l/cbCain4IdbdEDgka","pdf",28289976,1,175,"English","en",105,"# Abstract\n## MLFFs for reactive systems\n## Automated training with uncertainty\n## Surrogate modelling and free-energy barriers\n## Reaction pathway discovery and activation energy reduction\n## Carbon capture in porous materials and NMR interpretation\n## Foundation models for faster MLFF training\n## Non-local architectures via matrix function neural networks\n## Impact on routine computational catalysis","[{\"question\":\"Why are machine learning force fields useful for atomic-scale modelling?\",\"answer\":\"They achieve near quantum mechanical accuracy for energies and forces while dramatically reducing computational cost, and can scale more favorably with system size under locality assumptions.\"},{\"question\":\"What is the main obstacle to using MLFFs for complex reactive systems?\",\"answer\":\"The key challenge is curating relevant training datasets that produce accurate and trustworthy predictions for complex systems and reaction pathways.\"},{\"question\":\"How does the thesis improve MLFF training for reactive modelling?\",\"answer\":\"It presents an automated framework that uses model uncertainty to iteratively select and evaluate new configurations with a reference quantum method, validated on CO2 hydrogenation to methanol over indium oxide.\"}]","Machine Learning Force Fields for Modelling Reactions at Complex Interfaces | PDF",1785811220,441,{"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},"machine-learning-force-fields-for-modelling-reactions-at-complex-interfaces","",{"@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/machine-learning-force-fields-for-modelling-reactions-at-complex-interfaces/122546/",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":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"Why are machine learning force fields useful for atomic-scale modelling?","Question",{"text":75,"@type":76},"They achieve near quantum mechanical accuracy for energies and forces while dramatically reducing computational cost, and can scale more favorably with system size under locality assumptions.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What is the main obstacle to using MLFFs for complex reactive systems?",{"text":80,"@type":76},"The key challenge is curating relevant training datasets that produce accurate and trustworthy predictions for complex systems and reaction pathways.",{"name":82,"@type":73,"acceptedAnswer":83},"How does the thesis improve MLFF training for reactive modelling?",{"text":84,"@type":76},"It presents an automated framework that uses model uncertainty to iteratively select and evaluate new configurations with a reference quantum method, validated on CO2 hydrogenation to methanol over indium oxide.","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"]