Molecular dynamics with on-the-fly machine learning of quantum-mechanical forces. Li, Z., Kermode, J. R., & Vita, A. D. Physical Review Letters, American Physical Society, March, 2015. ![Molecular dynamics with on-the-fly machine learning of quantum-mechanical forces [link]](https://bibbase.org/img/filetypes/link.svg "link")
Paper abstract bibtex We present a molecular dynamics scheme which combines first-principles and machine-learning (ML) techniques in a single information-efficient approach. Forces on atoms are either predicted by Bayesian inference or, if necessary, computed by on-the-fly quantum-mechanical (QM) calculations and added to a growing ML database, whose completeness is, thus, never required. As a result, the scheme is accurate and general, while progressively fewer QM calls are needed when a new chemical process is encountered for the second and subsequent times, as demonstrated by tests on crystalline and molten silicon.
@article{wrap66611,
volume = {Volume 114},
month = {March},
title = {Molecular dynamics with on-the-fly machine learning of quantum-mechanical forces},
author = {Zhenwei Li and James R. Kermode and Alessandro De Vita},
publisher = {American Physical Society},
year = {2015},
journal = {Physical Review Letters},
url = {https://wrap.warwick.ac.uk/66611/},
abstract = {We present a molecular dynamics scheme which combines first-principles and machine-learning (ML) techniques in a single information-efficient approach. Forces on atoms are either predicted by Bayesian inference or, if necessary, computed by on-the-fly quantum-mechanical (QM) calculations and added to a growing ML database, whose completeness is, thus, never required. As a result, the scheme is accurate and general, while progressively fewer QM calls are needed when a new chemical process is encountered for the second and subsequent times, as demonstrated by tests on crystalline and molten silicon.}
}
Downloads: 0
{"_id":"auBrTbwbyqh2xJsYt","bibbaseid":"li-kermode-vita-moleculardynamicswithontheflymachinelearningofquantummechanicalforces-2015","author_short":["Li, Z.","Kermode, J. R.","Vita, A. D."],"bibdata":{"bibtype":"article","type":"article","volume":"Volume 114","month":"March","title":"Molecular dynamics with on-the-fly machine learning of quantum-mechanical forces","author":[{"firstnames":["Zhenwei"],"propositions":[],"lastnames":["Li"],"suffixes":[]},{"firstnames":["James","R."],"propositions":[],"lastnames":["Kermode"],"suffixes":[]},{"firstnames":["Alessandro","De"],"propositions":[],"lastnames":["Vita"],"suffixes":[]}],"publisher":"American Physical Society","year":"2015","journal":"Physical Review Letters","url":"https://wrap.warwick.ac.uk/66611/","abstract":"We present a molecular dynamics scheme which combines first-principles and machine-learning (ML) techniques in a single information-efficient approach. Forces on atoms are either predicted by Bayesian inference or, if necessary, computed by on-the-fly quantum-mechanical (QM) calculations and added to a growing ML database, whose completeness is, thus, never required. As a result, the scheme is accurate and general, while progressively fewer QM calls are needed when a new chemical process is encountered for the second and subsequent times, as demonstrated by tests on crystalline and molten silicon.","bibtex":"@article{wrap66611,\n volume = {Volume 114},\n month = {March},\n title = {Molecular dynamics with on-the-fly machine learning of quantum-mechanical forces},\n author = {Zhenwei Li and James R. Kermode and Alessandro De Vita},\n publisher = {American Physical Society},\n year = {2015},\n journal = {Physical Review Letters},\n url = {https://wrap.warwick.ac.uk/66611/},\n abstract = {We present a molecular dynamics scheme which combines first-principles and machine-learning (ML) techniques in a single information-efficient approach. Forces on atoms are either predicted by Bayesian inference or, if necessary, computed by on-the-fly quantum-mechanical (QM) calculations and added to a growing ML database, whose completeness is, thus, never required. As a result, the scheme is accurate and general, while progressively fewer QM calls are needed when a new chemical process is encountered for the second and subsequent times, as demonstrated by tests on crystalline and molten silicon.}\n}\n\n","author_short":["Li, Z.","Kermode, J. R.","Vita, A. D."],"key":"wrap66611","id":"wrap66611","bibbaseid":"li-kermode-vita-moleculardynamicswithontheflymachinelearningofquantummechanicalforces-2015","role":"author","urls":{"Paper":"https://wrap.warwick.ac.uk/66611/"},"metadata":{"authorlinks":{}}},"bibtype":"article","biburl":"http://wrap.warwick.ac.uk/cgi/exportview/author_id/39508/BibTeX/39508.bib","dataSources":["mPSAr4TqWJWGXCQrN"],"keywords":[],"search_terms":["molecular","dynamics","fly","machine","learning","quantum","mechanical","forces","li","kermode","vita"],"title":"Molecular dynamics with on-the-fly machine learning of quantum-mechanical forces","year":2015}