{"citation":{"ista":"Cheng B. 2024. Cartesian atomic cluster expansion for machine learning interatomic potentials. npj Computational Materials. 10, 157.","chicago":"Cheng, Bingqing. “Cartesian Atomic Cluster Expansion for Machine Learning Interatomic Potentials.” Npj Computational Materials. Springer Nature, 2024. https://doi.org/10.1038/s41524-024-01332-4.","short":"B. Cheng, Npj Computational Materials 10 (2024).","apa":"Cheng, B. (2024). Cartesian atomic cluster expansion for machine learning interatomic potentials. Npj Computational Materials. Springer Nature. https://doi.org/10.1038/s41524-024-01332-4","ieee":"B. Cheng, “Cartesian atomic cluster expansion for machine learning interatomic potentials,” npj Computational Materials, vol. 10. Springer Nature, 2024.","ama":"Cheng B. Cartesian atomic cluster expansion for machine learning interatomic potentials. npj Computational Materials. 2024;10. doi:10.1038/s41524-024-01332-4","mla":"Cheng, Bingqing. “Cartesian Atomic Cluster Expansion for Machine Learning Interatomic Potentials.” Npj Computational Materials, vol. 10, 157, Springer Nature, 2024, doi:10.1038/s41524-024-01332-4."},"oa":1,"publisher":"Springer Nature","user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","publication_identifier":{"eissn":["2057-3960"]},"scopus_import":"1","publication_status":"epub_ahead","day":"18","main_file_link":[{"url":"https://doi.org/10.1038/s41524-024-01332-4","open_access":"1"}],"oa_version":"Published Version","status":"public","year":"2024","author":[{"full_name":"Cheng, Bingqing","id":"cbe3cda4-d82c-11eb-8dc7-8ff94289fcc9","first_name":"Bingqing","last_name":"Cheng","orcid":"0000-0002-3584-9632"}],"language":[{"iso":"eng"}],"date_created":"2024-07-28T22:01:08Z","title":"Cartesian atomic cluster expansion for machine learning interatomic potentials","date_published":"2024-07-18T00:00:00Z","intvolume":" 10","acknowledgement":"B.C. thanks Ralf Drautz and Ngoc Cuong Nguyen for illuminating discussions.","external_id":{"arxiv":["2402.07472"]},"article_type":"original","corr_author":"1","month":"07","department":[{"_id":"BiCh"}],"publication":"npj Computational Materials","date_updated":"2024-07-29T11:23:41Z","type":"journal_article","_id":"17322","article_processing_charge":"Yes","abstract":[{"lang":"eng","text":"Machine learning interatomic potentials are revolutionizing large-scale, accurate atomistic modeling in material science and chemistry. Many potentials use atomic cluster expansion or equivariant message-passing frameworks. Such frameworks typically use spherical harmonics as angular basis functions, followed by Clebsch-Gordan contraction to maintain rotational symmetry. We propose a mathematically equivalent and simple alternative that performs all operations in the Cartesian coordinates. This approach provides a complete set of polynormially independent features of atomic environments while maintaining interaction body orders. Additionally, we integrate low-dimensional embeddings of various chemical elements, trainable radial channel coupling, and inter-atomic message passing. The resulting potential, named Cartesian Atomic Cluster Expansion (CACE), exhibits good accuracy, stability, and generalizability. We validate its performance in diverse systems, including bulk water, small molecules, and 25-element high-entropy alloys."}],"article_number":"157","doi":"10.1038/s41524-024-01332-4","quality_controlled":"1","volume":10}