[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-117359-en":3,"doc-seo-117359-105":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},117359,687197207639,"Asher","https://ap-avatar.wpscdn.com/davatar_a8503ba1806abce46bf441b54a3ca4cd",8,"Research & Report","Roadmap for the development of machine learning-based interatomic potentials","An interatomic potential is used to describe atomic interactions in molecules or solids by relating potential energy to atom positions. Such potentials enable atomic-scale simulations that support predictive materials behavior, faster discovery, and property optimization. Machine learning-based interatomic potentials extend this idea beyond traditional analytical functions, including neural networks, kernel methods, deep learning, and physics-informed models with distinct capabilities. The roadmap assesses the current landscape, summarizes key challenges in data quality, computational cost, transferability, interpretability, and robustness, and outlines progress toward reliable adoption in materials science and engineering.","Modelling and  \nSimulation in Materials  \nScience and  \n Engineering   \nROADMAP • OPEN ACCESS  \nRoadmap for the development of machine learning-based interatomic potentials  \nTo cite this article: Yong-Wei Zhang et al 2025 Modelling Simul. Mater. Sci. Eng. 33 023301  \nView the article online for updates and enhancements.  \nYou may also like  \n-Effects of composition ratio and crystal orientation on nanoindentation behavior of monocrystal AuPt alloys  \nJiajun Lin, Hao Xu, Yuanyuan Tian et al.  \n-Triple junction benchmark for multiphasefield models combining capillary and bulk driving forces  \nP W Hoffrogge, S Daubner, D Schneider et al.  \n-Chemo-mechanical benchmark for phasefield approaches  \nThea Kannenberg, Andreas Prahs, Bob Svendsen et al.  \nThis content was downloaded from IP address [78.211.222.53](78.211.222.53) on 20/02/2025 at 19:53  \nModelling Simul. Mater. Sci. Eng. 33 (2025) 023301 (54pp) [https://doi.org/10.1088/1361-651X/ad9d63](https://doi.org/10.1088/1361-651X/ad9d63)  \nRoadmap  \nRoadmap for the development of machine learning-based interatomic potentials  \nYong-Wei Zhang 1, 16, ∗ 􀁂, Viacheslav Sorkin1 􀁂 ,  \nZachary H Aitken 1, Antonio Politano2, 16, ∗ 􀁂, Jörg Behler3,4 􀁂 , Aidan P Thompson5 􀁂, Tsz Wai Ko6 􀁂, Shyue Ping Ong6, Olga Chalykh7 􀁂, Dmitry Korogod8 􀁂 ,  \nEvgeny Podryabinkin7 􀁂, Alexander Shapeev7, Ju Li9 􀁂 , Yuri Mishin 10 􀁂, Zongrui Pei11 􀁂, Xianglin Liu12 􀁂 , Jaesun Kim 13 􀁂, Yutack Park13 􀁂, Seungwoo Hwang13 􀁂 , Seungwu Han 13, 14, Killian Sheriff 15, Yifan Cao 15  \nand Rodrigo Freitas 15 􀁂  \n1 Institute of High-Performance Computing (IHPC), Agency for Science, Technology and Research (A∗ STAR), 1 Fusionopolis Way, \\#16-16 Connexis, Singapore 138632, Singapore  \n2 Department of Physical and Chemical Sciences, University of L’Aquila, via Vetoio, 67100 L’Aquila, Italy  \n3 Lehrstuhl für Theoretische Chemie II, Ruhr-Universität Bochum, 44780 Bochum, Germany  \n4 Research Center Chemical Sciences and Sustainability, Research Alliance Ruhr, 44780 Bochum, Germany  \n5 Center for Computing Research, Sandia National Laboratories, Albuquerque, New Mexico, United States of America  \n6 Aiiso Yufeng Li Family Department of Chemical and Nano Engineering, University of California, San Diego, 9500 Gilman Dr Mail Code \\#0448, La Jolla, CA 92093-0448, United States of America  \n7 Skolkovo Institute of Science and Technology, Russia, Bolshoy Boulevard 30, bld.  \n1., Skolkovo 121205, Russia  \n8 Moscow Institute of Physics and Technology, Russia, Institutsky lane 9, Dolgoprudny, Moscow region 141700, Russia  \n9 Department of Nuclear Science and Engineering and Department of Materials Science and Engineering, Massachusetts Institute of Technology, Cambridge, MA 02139, United States of America  \n16  \n∗  \nGuest Editor of the roadmap.  \nAuthors to whom any correspondence should be addressed.  \nOriginal content from this work may be used under the terms of the Creative Commons Attribution  \n4.0 licence. Any further distribution of this work must maintain attribution to the author(s) and the title of the work, journal citation and DOI.  \n© 2025 The Author(s) . Published by IOP Publishing Ltd 1  \n10 Department of Physics and Astronomy, George Mason University, 4400 University Drive, MSN 3F3, Fairfax, VA 22030, United States of America  \n11 New York University, New York, NY 10012, United States of America  \n12 Peng Cheng Laboratory, Shenzhen 518066, People’s Republic of China  \n13 Department of Materials Science and Engineering, Seoul National University, Seoul 08826, Republic of Korea  \n14 Korea Institute for Advanced Study, Seoul 02455, Republic of Korea  \n15 Department of Materials Science and Engineering, Massachusetts Institute of Technology, Cambridge, MA, United States of America  \nE-mail: [zhangyw@ihpc.a-star.edu.sg and antonio.politano@univaq.it](zhangyw@ihpc.a-star.edu.sg and antonio.politano@univaq.it)  \nReceived 2 August 2024; revised 13 November 2024  \nAccepted for publication 11 December 2024  \nPublished 28 January","cbCaiqc4kqMFzPSB","https://ap.wps.com/l/cbCaiqc4kqMFzPSB","pdf",2457857,1,55,"English","en",105,"# Introduction\n# Databases for machine learning-based interatomic potentials","[{\"question\":\"What role do interatomic potentials play in materials science?\",\"answer\":\"Interatomic potentials describe atomic interactions by expressing potential energy as a function of atom positions. They underpin atomic-scale simulations that support predictive behavior, discovery acceleration, and property optimization.\"},{\"question\":\"How do machine learning-based interatomic potentials differ from traditional approaches?\",\"answer\":\"Machine learning-based potentials replace or transcend conventional mathematical functional forms by learning the relationship between atomic configurations and potential energies. They include approaches such as neural networks, kernel methods, deep learning, and physics-informed models.\"},{\"question\":\"What challenges must be overcome for widespread adoption of machine learning-based interatomic potentials?\",\"answer\":\"Key challenges include data quality, computational demands, transferability to new conditions, interpretability, and robustness. Addressing these issues is necessary to ensure accuracy, efficiency, and dependability.\"}]","Roadmap for the development of machine learning-based interatomic potentials | PDF",1785675356,139,{"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},"roadmap-for-the-development-of-machine-learning-based-interatomic-potentials","",{"@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/roadmap-for-the-development-of-machine-learning-based-interatomic-potentials/117359/",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","2026-08-02",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},"What role do interatomic potentials play in materials science?","Question",{"text":75,"@type":76},"Interatomic potentials describe atomic interactions by expressing potential energy as a function of atom positions. They underpin atomic-scale simulations that support predictive behavior, discovery acceleration, and property optimization.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How do machine learning-based interatomic potentials differ from traditional approaches?",{"text":80,"@type":76},"Machine learning-based potentials replace or transcend conventional mathematical functional forms by learning the relationship between atomic configurations and potential energies. They include approaches such as neural networks, kernel methods, deep learning, and physics-informed models.",{"name":82,"@type":73,"acceptedAnswer":83},"What challenges must be overcome for widespread adoption of machine learning-based interatomic potentials?",{"text":84,"@type":76},"Key challenges include data quality, computational demands, transferability to new conditions, interpretability, and robustness. Addressing these issues is necessary to ensure accuracy, efficiency, and dependability.","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"]