{"file_date_updated":"2025-10-13T07:54:51Z","oa_version":"Published Version","external_id":{"pmid":["41034200"]},"language":[{"iso":"eng"}],"tmp":{"image":"/images/cc_by.png","legal_code_url":"https://creativecommons.org/licenses/by/4.0/legalcode","short":"CC BY (4.0)","name":"Creative Commons Attribution 4.0 International Public License (CC-BY 4.0)"},"quality_controlled":"1","article_processing_charge":"Yes","acknowledgement":"We thank Chunyi Zhang for providing the TiO2(101)/NaCl+NaOH+HCl(aq) dataset and for useful discussions. We thank Jia-Xin Zhu for providing the Pt(111)/KF(aq) dataset. We thank Tsz Wai Ko and Jonas Finkler for useful discussions and for the DFT-optimized Au2-MgO(001) structures. We thank Junmin Chen for discussions. D.K and B.C. acknowledge funding from Toyota Research Institute Synthesis Advanced Research Challenge. D.S.K. and P.Z. acknowledge funding from BIDMaP Postdoctoral Fellowship.","title":"Machine learning of charges and long-range interactions from energies and forces","publication_identifier":{"eissn":["2041-1723"]},"user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","doi":"10.1038/s41467-025-63852-x","date_published":"2025-10-01T00:00:00Z","oa":1,"file":[{"relation":"main_file","creator":"dernst","content_type":"application/pdf","access_level":"open_access","checksum":"34b6005d349bbff85839c4e51d6c8725","success":1,"date_created":"2025-10-13T07:54:51Z","file_name":"2025_NatureComm_King.pdf","file_size":4907055,"date_updated":"2025-10-13T07:54:51Z","file_id":"20460"}],"ddc":["000"],"article_type":"original","citation":{"ama":"King DS, Kim D, Zhong P, Cheng B. Machine learning of charges and long-range interactions from energies and forces. <i>Nature Communications</i>. 2025;16. doi:<a href=\"https://doi.org/10.1038/s41467-025-63852-x\">10.1038/s41467-025-63852-x</a>","ista":"King DS, Kim D, Zhong P, Cheng B. 2025. Machine learning of charges and long-range interactions from energies and forces. Nature Communications. 16, 8763.","short":"D.S. King, D. Kim, P. Zhong, B. Cheng, Nature Communications 16 (2025).","mla":"King, Daniel S., et al. “Machine Learning of Charges and Long-Range Interactions from Energies and Forces.” <i>Nature Communications</i>, vol. 16, 8763, 2025, doi:<a href=\"https://doi.org/10.1038/s41467-025-63852-x\">10.1038/s41467-025-63852-x</a>.","ieee":"D. S. King, D. Kim, P. Zhong, and B. Cheng, “Machine learning of charges and long-range interactions from energies and forces,” <i>Nature Communications</i>, vol. 16. 2025.","apa":"King, D. S., Kim, D., Zhong, P., &#38; Cheng, B. (2025). Machine learning of charges and long-range interactions from energies and forces. <i>Nature Communications</i>. <a href=\"https://doi.org/10.1038/s41467-025-63852-x\">https://doi.org/10.1038/s41467-025-63852-x</a>","chicago":"King, Daniel S., Dongjin Kim, Peichen Zhong, and Bingqing Cheng. “Machine Learning of Charges and Long-Range Interactions from Energies and Forces.” <i>Nature Communications</i>, 2025. <a href=\"https://doi.org/10.1038/s41467-025-63852-x\">https://doi.org/10.1038/s41467-025-63852-x</a>."},"scopus_import":"1","date_updated":"2025-10-13T08:00:31Z","PlanS_conform":"1","pmid":1,"has_accepted_license":"1","type":"journal_article","day":"01","month":"10","department":[{"_id":"BiCh"}],"DOAJ_listed":"1","intvolume":"        16","_id":"20452","corr_author":"1","volume":16,"publication":"Nature Communications","status":"public","publication_status":"published","OA_type":"gold","abstract":[{"lang":"eng","text":"Accurate modeling of long-range forces is critical in atomistic simulations, as they play a central role in determining the properties of material and chemical systems. However, standard machine learning interatomic potentials (MLIPs) often rely on short-range approximations, limiting their applicability to systems with significant electrostatics and dispersion forces. We recently introduced the Latent Ewald Summation (LES) method, which captures long-range electrostatics without explicitly learning atomic charges or charge equilibration. We benchmark LES on diverse and challenging systems, including charged molecules, ionic liquids, electrolyte solutions, polar dipeptides, surface adsorption, electrolyte/solid interfaces, and solid-solid interfaces. Here we show that LES can reproduce the exact atomic charges for classical systems with fixed charges and can infer dipole and quadrupole moments, as well as the dipole derivative with respect to atomic positions, for quantum mechanical systems. Moreover, LES can achieve better accuracy in energy and force predictions compared to methods that explicitly learn from charges."}],"year":"2025","author":[{"last_name":"King","full_name":"King, Daniel S.","first_name":"Daniel S."},{"first_name":"Dongjin","full_name":"Kim, Dongjin","last_name":"Kim"},{"full_name":"Zhong, Peichen","first_name":"Peichen","last_name":"Zhong"},{"first_name":"Bingqing","orcid":"0000-0002-3584-9632","full_name":"Cheng, Bingqing","last_name":"Cheng","id":"cbe3cda4-d82c-11eb-8dc7-8ff94289fcc9"}],"article_number":"8763","date_created":"2025-10-12T22:01:25Z","OA_place":"publisher"}