Hamiltonian datasets: "Unifying machine learning and quantum chemistry with a deep neural network for molecular wavefunctions""

dc.contributor.authorSchütt, Kristof T.
dc.contributor.authorGastegger, Michael
dc.contributor.authorTkatchenko, Alexandre
dc.contributor.authorMüller, Klaus-Robert
dc.contributor.authorMaurer, Reinhard J.
dc.date.accessioned2020-05-27T11:59:44Z
dc.date.available2020-05-27T11:59:44Z
dc.date.issued2019-09-25
dc.description.abstractMachine learning advances chemistry and materials science by enabling large-scale exploration of chemical space based on quantum chemical calculations. While these models supply fast and accurate predictions of atomistic chemical properties, they do not explicitly capture the electronic degrees of freedom of a molecule, which limits their applicability for reactive chemistry and chemical analysis. Here we present a deep learning framework for the prediction of the quantum mechanical wavefunction in a local basis of atomic orbitals from which all other ground-state properties can be derived. This approach retains full access to the electronic structure via the wavefunction at force-field-like efficiency and captures quantum mechanics in an analytically differentiable representation. On several examples, we demonstrate that this opens promising avenues to perform inverse design of molecular structures for targeting electronic property optimisation and a clear path towards increased synergy of machine learning and quantum chemistry.en
dc.description.sponsorshipEC/H2020/792572/EU/Machine Learning for Catalytic Carbon Dioxide Activation/MachineCaten
dc.description.sponsorshipBMBF, 01IS18037A, Verbundprojekt BIFOLD-BZML: Berlin Institute for the Foundations of Learning and Dataen
dc.description.sponsorshipUKRI, MR/S016023/1, Computational prediction of hot-electron chemistry: Towards electronic control of catalysisen
dc.description.sponsorshipEPSRC, EP/R029431/1, High End Computing materials chemistry consortiumen
dc.identifier.urihttps://depositonce.tu-berlin.de/handle/11303/11216
dc.identifier.urihttp://dx.doi.org/10.14279/depositonce-10104
dc.language.isoenen
dc.relation.referenceshttps://doi.org/10.1038/s41467-019-12875-2
dc.rights.urihttps://choosealicense.com/licenses/mit/en
dc.subject.ddc500 Naturwissenschaften und Mathematikde
dc.subject.othermachine learningen
dc.subject.otherhamiltoniansen
dc.subject.otherSchNOrben
dc.subject.otherquantum chemistryen
dc.titleHamiltonian datasets: "Unifying machine learning and quantum chemistry with a deep neural network for molecular wavefunctions""en
dc.typeGeneric Research Dataen
tub.accessrights.dnbunknown*
tub.affiliationFak. 4 Elektrotechnik und Informatik::Inst. Softwaretechnik und Theoretische Informatik::FG Maschinelles Lernende
tub.affiliation.facultyFak. 4 Elektrotechnik und Informatikde
tub.affiliation.groupFG Maschinelles Lernende
tub.affiliation.instituteInst. Softwaretechnik und Theoretische Informatikde

Files

Original bundle
Now showing 1 - 6 of 6
No Thumbnail Available
Name:
README.txt
Size:
2.5 KB
Format:
Plain Text
Description:
Information on the data format and instructions for accessing the data.
No Thumbnail Available
Name:
schnorb_hamiltonian_ethanol_dft.tgz
Size:
787.12 MB
Format:
Unknown data format
Description:
Tar Gzip of SchNetPack db-file
No Thumbnail Available
Name:
schnorb_hamiltonian_ethanol_hf.tgz
Size:
798.77 MB
Format:
Unknown data format
Description:
Tar Gzip of SchNetPack db-file
No Thumbnail Available
Name:
schnorb_hamiltonian_malondialdehyde.tgz
Size:
1.03 GB
Format:
Unknown data format
Description:
Tar Gzip of SchNetPack db-file
No Thumbnail Available
Name:
schnorb_hamiltonian_water.tgz
Size:
13.86 MB
Format:
Unknown data format
Description:
Tar Gzip of SchNetPack db-file
No Thumbnail Available
Name:
schnorb_hamiltonian_uracil.tgz
Size:
2.42 GB
Format:
Unknown data format
Description:
Tar Gzip of SchNetPack db-file
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
2.71 KB
Format:
Item-specific license agreed upon to submission
Description:

Collections