{"id":{"repo_id":"cambridge","oai_identifier":"oai:www.repository.cam.ac.uk:1810/367702"},"canonical_url":"https://search.dev.ndltd.org/etd/cambridge/oai:www.repository.cam.ac.uk:1810/367702","repository":{"repo_id":"cambridge","name":"Cambridge University","base_url":"https://api.repository.cam.ac.uk/server/oai/request"},"display":{"title":"Machine Learning Force Fields for Molecular Chemistry","abstract":"The first principles computational modelling of molecular systems is a long-standing pursuit in the scientific community. It has traditionally been tackled by developing approximate solutions to quantum mechanics. Simulations using these electronic structure based methods can be highly accurate but are limited to small system sizes or short time scales. The traditional alternative is force fields that enable fast and accurate simulations by bypassing the treatment of the electrons and describing the system solely in terms of the atomic positions. The emergence of machine learning tools has opened up the opportunity for the development of high accuracy force fields trained directly to reproduce the results of electronic structure calculations. This thesis presents new developments that lead to improved machine learning force fields for molecular chemistry. Firstly, a set of linearly complete basis functions, called ACE, is demonstrated to yield high accuracy custom made force fields for small molecules. By recognising the symmetric tensor structure of these basis functions, the framework is extended to enable the simultaneous description of a large number of chemical elements. Next, multi-ACE is proposed, which provides a unifying theory of most classical and machine learning force fields. Using the design space set out in this theory, a new method, called MACE is created. MACE is shown to provide simple, robust, accurate, and efficient force fields for a wide range of molecular systems. Finally, MACE-OFF23 a new transferable force field for organic molecules is proposed and demonstrated to be capable of accurately describing not only molecules in vacuum but also in the condensed phase.","abstract_html":"The first principles computational modelling of molecular systems is a long-standing pursuit in the scientific community. It has traditionally been tackled by developing approximate solutions to quantum mechanics. Simulations using these electronic structure based methods can be highly accurate but are limited to small system sizes or short time scales. The traditional alternative is force fields that enable fast and accurate simulations by bypassing the treatment of the electrons and describing the system solely in terms of the atomic positions. The emergence of machine learning tools has opened up the opportunity for the development of high accuracy force fields trained directly to reproduce the results of electronic structure calculations. This thesis presents new developments that lead to improved machine learning force fields for molecular chemistry. Firstly, a set of linearly complete basis functions, called ACE, is demonstrated to yield high accuracy custom made force fields for small molecules. By recognising the symmetric tensor structure of these basis functions, the framework is extended to enable the simultaneous description of a large number of chemical elements. Next, multi-ACE is proposed, which provides a unifying theory of most classical and machine learning force fields. Using the design space set out in this theory, a new method, called MACE is created. MACE is shown to provide simple, robust, accurate, and efficient force fields for a wide range of molecular systems. Finally, MACE-OFF23 a new transferable force field for organic molecules is proposed and demonstrated to be capable of accurately describing not only molecules in vacuum but also in the condensed phase.","abstract_has_math":false,"creators":["Kovács, Dávid"],"institution":"University of Cambridge","degree_name":"Doctor of Philosophy (PhD)","degree_level":"Doctoral","degree_discipline":null,"degree_department":null,"school":null,"contributors":[],"advisors":["Csanyi, Gabor"],"committee_chairs":[],"committee_members":[],"year":2024,"date_issued":"2024-02-06","date_published":"2024-02-06","updated_at":"2026-07-22T22:24:27Z","subjects":["chemistry","computational chemistry","graph neural network","machine learning"],"languages":["eng"],"rights":[],"rights_urls":["https://apollo8-f-pro.lib.cam.ac.uk/bitstreams/ff249f4b-58ce-4b25-aa83-254072fd0b96/download","https://creativecommons.org/licenses/by/4.0/"],"identifier_entries":[]},"links":{"outbound_url":"https://doi.org/10.17863/CAM.108180","outbound_label":"DOI","outbound_source":"dc:identifier.doi"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Csanyi, Gabor"]},{"key":"dc:creator","label":"Author","values":["Kovács, Dávid"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.issued","label":"Date","values":["2024-02-06"]},{"key":"dc:publisher.institution","label":"Dc Publisher Institution","values":["University of Cambridge"]},{"key":"dc:relation.isreferencedby.uri","label":"Dc Relation Isreferencedby URI","values":["https://www.repository.cam.ac.uk/handle/1810/367702"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]},{"key":"dc:type.qualificationlevel","label":"Dc Type Qualificationlevel","values":["Doctoral"]},{"key":"dc:type.qualificationname","label":"Dc Type Qualificationname","values":["Doctor of Philosophy (PhD)"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["chemistry","computational chemistry","graph neural network","machine learning"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["eng"]},{"key":"dc:rights","label":"Dc Rights","values":["https://apollo8-f-pro.lib.cam.ac.uk/bitstreams/ff249f4b-58ce-4b25-aa83-254072fd0b96/download","https://creativecommons.org/licenses/by/4.0/"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.doi","label":"DOI","values":["https://doi.org/10.17863/CAM.108180"]},{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://apollo8-f-pro.lib.cam.ac.uk/bitstreams/40173ba8-a370-4f68-8a32-e19227ac3e44/download"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["The first principles computational modelling of molecular systems is a long-standing pursuit in the scientific community. It has traditionally been tackled by developing approximate solutions to quantum mechanics. Simulations using these electronic structure based methods can be highly accurate but are limited to small system sizes or short time scales. The traditional alternative is force fields that enable fast and accurate simulations by bypassing the treatment of the electrons and describing the system solely in terms of the atomic positions. The emergence of machine learning tools has opened up the opportunity for the development of high accuracy force fields trained directly to reproduce the results of electronic structure calculations. This thesis presents new developments that lead to improved machine learning force fields for molecular chemistry. Firstly, a set of linearly complete basis functions, called ACE, is demonstrated to yield high accuracy custom made force fields for small molecules. By recognising the symmetric tensor structure of these basis functions, the framework is extended to enable the simultaneous description of a large number of chemical elements. Next, multi-ACE is proposed, which provides a unifying theory of most classical and machine learning force fields. Using the design space set out in this theory, a new method, called MACE is created. MACE is shown to provide simple, robust, accurate, and efficient force fields for a wide range of molecular systems. Finally, MACE-OFF23 a new transferable force field for organic molecules is proposed and demonstrated to be capable of accurately describing not only molecules in vacuum but also in the condensed phase."]},{"key":"dc:format.checksum.md5","label":"Dc Format Checksum Md5","values":["321a82aa510514af6570d5ec3f2d7b47","87eda9de84448d1f82354d60eee3eb5f"]},{"key":"dc:title","label":"Title","values":["Machine Learning Force Fields for Molecular Chemistry"]}]}],"canonical_facts":{"dc:contributor.advisor":["Csanyi, Gabor"],"dc:creator":["Kovács, Dávid"],"dc:date.issued":["2024-02-06"],"dc:description.abstract":["The first principles computational modelling of molecular systems is a long-standing pursuit in the scientific community. It has traditionally been tackled by developing approximate solutions to quantum mechanics. Simulations using these electronic structure based methods can be highly accurate but are limited to small system sizes or short time scales. The traditional alternative is force fields that enable fast and accurate simulations by bypassing the treatment of the electrons and describing the system solely in terms of the atomic positions. The emergence of machine learning tools has opened up the opportunity for the development of high accuracy force fields trained directly to reproduce the results of electronic structure calculations. This thesis presents new developments that lead to improved machine learning force fields for molecular chemistry. Firstly, a set of linearly complete basis functions, called ACE, is demonstrated to yield high accuracy custom made force fields for small molecules. By recognising the symmetric tensor structure of these basis functions, the framework is extended to enable the simultaneous description of a large number of chemical elements. Next, multi-ACE is proposed, which provides a unifying theory of most classical and machine learning force fields. Using the design space set out in this theory, a new method, called MACE is created. MACE is shown to provide simple, robust, accurate, and efficient force fields for a wide range of molecular systems. Finally, MACE-OFF23 a new transferable force field for organic molecules is proposed and demonstrated to be capable of accurately describing not only molecules in vacuum but also in the condensed phase."],"dc:format.checksum.md5":["321a82aa510514af6570d5ec3f2d7b47","87eda9de84448d1f82354d60eee3eb5f"],"dc:identifier.doi":["https://doi.org/10.17863/CAM.108180"],"dc:identifier.uri":["https://apollo8-f-pro.lib.cam.ac.uk/bitstreams/40173ba8-a370-4f68-8a32-e19227ac3e44/download"],"dc:language":["eng"],"dc:publisher.institution":["University of Cambridge"],"dc:relation.isreferencedby.uri":["https://www.repository.cam.ac.uk/handle/1810/367702"],"dc:rights":["https://apollo8-f-pro.lib.cam.ac.uk/bitstreams/ff249f4b-58ce-4b25-aa83-254072fd0b96/download","https://creativecommons.org/licenses/by/4.0/"],"dc:subject":["chemistry","computational chemistry","graph neural network","machine learning"],"dc:title":["Machine Learning Force Fields for Molecular Chemistry"],"dc:type":["Thesis"],"dc:type.qualificationlevel":["Doctoral"],"dc:type.qualificationname":["Doctor of Philosophy (PhD)"]},"updated_at":"2026-07-22T22:24:27Z"}