[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-117256-en":3,"doc-seo-117256-105":29,"detail-sidebar-cat-0-en-105":90},{"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":13,"seo_description":14,"update_tm":27,"read_time":28},117256,8796095462418,"Noah","https://ap-avatar.wpscdn.com/avatar/80000253c1241d02b47?x-image-process=image/resize,m_fixed,w_180,h_180&k=1778826106357471780",8,"Research & Report","Introduction to machine learning potentials for atomistic simulations","Machine learning potentials have transformed atomistic simulations, becoming a practical mainstay for computational scientists. This topical review provides an overview of machine learning potentials and their real-world use in scientific problems. It gives a systematic pathway for building such potentials, including chemical descriptors, regression models, and end-to-end workflows for data generation and validation. The article contrasts earlier model generations, then discusses recent advances in depth, referencing expert reviews and open-source tools before concluding with selected showcase applications.","J. Phys.: Condens. Matter 37 (2025) 073002 (35pp) [https://doi.org/10.1088/1361-648X/ad9657](https://doi.org/10.1088/1361-648X/ad9657)[ ](https://doi.org/10.1088/1361-648X/ad9657)Topical Review  \nIntroduction to machine learning potentials for atomistic simulations  \nFabian L Thiemann 1,2 􀁂, Niamh O’Neill2,3,4 􀁂, Venkat Kapil3,4,5,6 􀁂 , Angelos Michaelides3,4 􀁂 and Christoph Schran2,4, ∗ 􀁂  \n1 IBM Research Europe, Daresbury, Warrington WA4 4AD, United Kingdom  \n2 Cavendish Laboratory, Department of Physics, University of Cambridge, Cambridge CB3 0HE, United Kingdom  \n3 Yusuf Hamied Department of Chemistry, University of Cambridge, Lensfield Road, Cambridge CB2 1EW, United Kingdom  \n4 Lennard-Jones Centre, University of Cambridge, Trinity Ln, Cambridge CB2 1TN, United Kingdom  \n5 Department of Physics and Astronomy, University College London, London, United Kingdom  \n6 Thomas Young Centre and London Centre for Nanotechnology, London, United Kingdom  \nE-mail: [cs2121@cam.ac.uk](cs2121@cam.ac.uk)  \nReceived 16 July 2024, revised 22 October 2024 Accepted for publication 22 November 2024 Published 6 December 2024  \nAbstract  \nMachine learning potentials have revolutionised the field of atomistic simulations in recent years and are becoming a mainstay in the toolbox of computational scientists. This paper aims to provide an overview and introduction into machine learning potentials and their practical application to scientific problems. We provide a systematic guide for developing machine learning potentials, reviewing chemical descriptors, regression models, data generation and validation approaches. We begin with an emphasis on the earlier generation of models, such as high-dimensional neural network potentials and Gaussian approximation potentials, to provide historical perspective and guide the reader towards the understanding of recent developments, which are discussed in detail thereafter. Furthermore, we refer to relevant expert reviews, open-source software, and practical examples—further lowering the barrier to exploring these methods. The paper ends with selected showcase examples, highlighting the capabilities of machine learning potentials and how they can be applied to push the boundaries in atomistic simulations.  \nKeywords: machine learning potentials, atomistic simulations, potential energy surfaces, interatomic interactions  \n∗ Author to whom any correspondence should be addressed.  \nOriginal Content from this work may be used under the terms of the Creative Commons Attribution 4.0 licence. Any  \nfurther distribution of this work must maintain attribution to the author(s) and the title of the work, journal citation and DOI.  \n1 © 2024 The Author(s) . Published by IOP Publishing Ltd  \nContents  \n1. Introduction 2  \n2. Chemical descriptors 3  \n2.1. ACSFs 4  \n2.2. Smooth overlap of atomic positions 5  \n2.3. Discussion and outlook on chemical descriptors 6  \n3. Regression models 8  \n3.1. Artificial neural networks 8  \n3.1.1. High–dimensional neural network potentials 10  \n3.1.2. Obtaining analytical derivatives 11  \n3.1.3. Training 11  \n3.2. Gaussian process (GP) and kernel ridge regression (KRR) 12  \n3.2.1. Weight-space view 12  \n3.2.2. Function-space view 13  \n3.2.3. GAPs 14  \n3.3. Discussion and outlook of regression models 16  \n4. Current developments 17  \n4.1. Completeness of descriptors 17  \n4.2. Learnable descriptors: graph neural networks (GNNs) 18  \n4.3. Beyond locality 18  \n4.4. General purpose and foundational models 19  \n5. Data set generation 20  \n5.1. Structural selection techniques 20  \n5.2. Active learning 20  \n5.3. Reinforcement workflows 22  \n6. Validation 22  \n6.1. Primary properties and numerical errors 22  \n6.2. Validation of secondary properties 23  \n7. Showcase examples 24  \n8. Summary and outlook 27  \nData availability statement 28  \nAcknowledgments 28  \nAppendix 28  \nReferences 30  \n1. Introduction  \nMost of the chemistry and physics of molecular systems and materials is governed by the potentia","cbCaipNfJUPFomJo","https://ap.wps.com/l/cbCaipNfJUPFomJo","pdf",3018393,1,35,"English","en",105,"# 1. Introduction\n# 2. Chemical descriptors\n## 2.1. ACSFs\n## 2.2. Smooth overlap of atomic positions\n# 3. Regression models\n## 3.1. Artificial neural networks\n## 3.2. Gaussian process (GP) and kernel ridge regression (KRR)\n# 4. Current developments\n# 5. Data set generation\n# 6. Validation\n# 7. Showcase examples\n# 8. Summary and outlook","[{\"question\":\"What is the purpose of this review on machine learning potentials?\",\"answer\":\"It provides an overview and introduction to machine learning potentials and explains how they are practically applied to scientific problems in atomistic simulations.\"},{\"question\":\"Which core topics are covered for developing machine learning potentials?\",\"answer\":\"The review covers chemical descriptors, regression models, and approaches for data generation and validation, including systematic development guidance.\"},{\"question\":\"How does the review structure the discussion of model development?\",\"answer\":\"It begins with earlier generations of models such as high-dimensional neural network potentials and Gaussian approximation potentials, then moves into more detailed discussion of recent developments.\"}]",1785674731,88,{"code":4,"msg":30,"data":31},"ok",{"site_id":24,"language":23,"slug":32,"title":13,"keywords":33,"description":14,"schema_data":34,"social_meta":85,"head_meta":87,"extra_data":89,"updated_unix":27},"introduction-to-machine-learning-potentials-for-atomistic-simulations","",{"@graph":35,"@context":84},[36,53,67],{"@type":37,"itemListElement":38},"BreadcrumbList",[39,43,47,50],{"item":40,"name":41,"@type":42,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":44,"name":45,"@type":42,"position":46},"https://docshare.wps.com/document/","Document",2,{"item":48,"name":12,"@type":42,"position":49},"https://docshare.wps.com/document/research-report/",3,{"item":51,"name":13,"@type":42,"position":52},"https://docshare.wps.com/document/introduction-to-machine-learning-potentials-for-atomistic-simulations/117256/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":23,"description":14,"dateModified":61,"datePublished":61,"encodingFormat":60,"isAccessibleForFree":62,"interactionStatistic":63},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":40,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-08-02",true,{"@type":64,"interactionType":65,"userInteractionCount":4},"InteractionCounter",{"@type":66},"ViewAction",{"@type":68,"mainEntity":69},"FAQPage",[70,76,80],{"name":71,"@type":72,"acceptedAnswer":73},"What is the purpose of this review on machine learning potentials?","Question",{"text":74,"@type":75},"It provides an overview and introduction to machine learning potentials and explains how they are practically applied to scientific problems in atomistic simulations.","Answer",{"name":77,"@type":72,"acceptedAnswer":78},"Which core topics are covered for developing machine learning potentials?",{"text":79,"@type":75},"The review covers chemical descriptors, regression models, and approaches for data generation and validation, including systematic development guidance.",{"name":81,"@type":72,"acceptedAnswer":82},"How does the review structure the discussion of model development?",{"text":83,"@type":75},"It begins with earlier generations of models such as high-dimensional neural network potentials and Gaussian approximation potentials, then moves into more detailed discussion of recent developments.","https://schema.org",{"og:url":51,"og:type":86,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":88,"canonical":51},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":91},[92,96,100,104,109,114,119,122,127,130,134],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":93,"show_sort_weight":94,"slug":95},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":97,"show_sort_weight":98,"slug":99},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":45,"category_name":101,"show_sort_weight":102,"slug":103},"Exam",70,"exam",{"id":105,"doc_module":4,"doc_module_name":45,"category_name":106,"show_sort_weight":107,"slug":108},5,"Comic",60,"comic",{"id":110,"doc_module":4,"doc_module_name":45,"category_name":111,"show_sort_weight":112,"slug":113},6,"Technology",50,"technology",{"id":115,"doc_module":4,"doc_module_name":45,"category_name":116,"show_sort_weight":117,"slug":118},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":45,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":45,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":45,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":45,"category_name":136,"show_sort_weight":105,"slug":137},19,"General","general"]