SpookyNet: Learning force fields with electronic degrees of freedom and nonlocal effects
| dc.contributor.author | Unke, Oliver T. | |
| dc.contributor.author | Chmiela, Stefan | |
| dc.contributor.author | Gastegger, Michael | |
| dc.contributor.author | Schütt, Kristof T. | |
| dc.contributor.author | Sauceda, Huziel E. | |
| dc.contributor.author | Müller, Klaus-Robert | |
| dc.date.accessioned | 2022-01-07T10:45:39Z | |
| dc.date.available | 2022-01-07T10:45:39Z | |
| dc.date.issued | 2021-12-14 | |
| dc.description.abstract | Machine-learned force fields combine the accuracy of ab initio methods with the efficiency of conventional force fields. However, current machine-learned force fields typically ignore electronic degrees of freedom, such as the total charge or spin state, and assume chemical locality, which is problematic when molecules have inconsistent electronic states, or when nonlocal effects play a significant role. This work introduces SpookyNet, a deep neural network for constructing machine-learned force fields with explicit treatment of electronic degrees of freedom and nonlocality, modeled via self-attention in a transformer architecture. Chemically meaningful inductive biases and analytical corrections built into the network architecture allow it to properly model physical limits. SpookyNet improves upon the current state-of-the-art (or achieves similar performance) on popular quantum chemistry data sets. Notably, it is able to generalize across chemical and conformational space and can leverage the learned chemical insights, e.g. by predicting unknown spin states, thus helping to close a further important remaining gap for today’s machine learning models in quantum chemistry. | en |
| dc.description.sponsorship | BMBF, 01IS14013A, Verbundprojekt: BBDC - Berliner Kompetenzzentrum für Big Data | en |
| dc.description.sponsorship | BMBF, 01GQ1115, D-JPN Verbund: Adaptive Gehirn-Computer-Schnittstellen (BCI) in nichtstationären Umgebungen | en |
| dc.description.sponsorship | BMBF, 01GQ0850, Verbundprojekt: Bernstein Fokus Neurotechnologie - Nichtinvasive Neurotechnologie für Mensch-Maschine Interaktion - Teilprojekte A1, A3, A4, B4, W3, Zentrum | en |
| dc.description.sponsorship | BMBF, 01IS18025A, Verbundprojekt BIFOLD-BBDC: Berlin Institute for the Foundations of Learning and Data | en |
| dc.description.sponsorship | BMBF, 01IS18037A, Verbundprojekt BIFOLD-BZML: Berlin Institute for the Foundations of Learning and Data | en |
| dc.description.sponsorship | DFG, 390685689, EXC 2046: MATH+: Berlin Mathematics Research Center | en |
| dc.identifier.eissn | 2041-1723 | |
| dc.identifier.uri | https://depositonce.tu-berlin.de/handle/11303/16099 | |
| dc.identifier.uri | http://dx.doi.org/10.14279/depositonce-14873 | |
| dc.language.iso | en | en |
| dc.rights.uri | https://creativecommons.org/licenses/by/4.0/ | en |
| dc.subject.ddc | 000 Informatik, Informationswissenschaft, allgemeine Werke | de |
| dc.subject.other | chemical physics | en |
| dc.subject.other | cheminformatics | en |
| dc.subject.other | computational chemistry | en |
| dc.subject.other | method development | en |
| dc.subject.other | quantum chemistry | en |
| dc.title | SpookyNet: Learning force fields with electronic degrees of freedom and nonlocal effects | en |
| dc.type | Article | en |
| dc.type.version | publishedVersion | en |
| dcterms.bibliographicCitation.articlenumber | 7273 | en |
| dcterms.bibliographicCitation.doi | 10.1038/s41467-021-27504-0 | en |
| dcterms.bibliographicCitation.journaltitle | Nature Communications | en |
| dcterms.bibliographicCitation.originalpublishername | Springer Nature | en |
| dcterms.bibliographicCitation.originalpublisherplace | London | en |
| dcterms.bibliographicCitation.volume | 12 | en |
| tub.accessrights.dnb | free | en |
| tub.affiliation | Fak. 4 Elektrotechnik und Informatik::Inst. Softwaretechnik und Theoretische Informatik::FG Maschinelles Lernen | de |
| tub.affiliation.faculty | Fak. 4 Elektrotechnik und Informatik | de |
| tub.affiliation.group | FG Maschinelles Lernen | de |
| tub.affiliation.institute | Inst. Softwaretechnik und Theoretische Informatik | de |
| tub.publisher.universityorinstitution | Technische Universität Berlin | en |