Improving the Self-Consistent Field Initial Guess Using a 3D Convolutional Neural Network
KAUST DepartmentPhysical Science and Engineering (PSE) Division
Embargo End Date2022-05-06
Permanent link to this recordhttp://hdl.handle.net/10754/669121
MetadataShow full item record
Access RestrictionsAt the time of archiving, the student author of this thesis opted to temporarily restrict access to it. The full text of this thesis will become available to the public after the expiration of the embargo on 2022-05-06.
AbstractMost ab initio simulation packages based on Density Functional Theory (DFT) use the Superposition of Atomic Densities (SAD) as a starting point of the self-consistent fi eld (SCF) iteration. However, this trial charge density without modeling atomic iterations nonlinearly may lead to a relatively slow or even failed convergence. This thesis proposes a machine learning-based scheme to improve the initial guess. We train a 3-Dimensional Convolutional Neural Network (3D CNN) to map the SAD initial guess to the corresponding converged charge density with simple structures. We show that the 3D CNN-processed charge density reduces the number of required SCF iterations at different unit cell complexity levels.
CitationZhang, Z. (2021). Improving the Self-Consistent Field Initial Guess Using a 3D Convolutional Neural Network. KAUST Research Repository. https://doi.org/10.25781/KAUST-542XY