Georgia Institute of Technology
Machine learning the exact exchange potential for single atoms
Abstract
dc:description.abstractRecent developments in machine learning and its applications in the field of quantum mechanics provide an alternative, worth-exploring path to perform quantum structure calculations. In the field of Density functional theory, where many scientific and parametric attempts have been made to develop an accurate exchange-correlation functional, this work aims to apply machine learning in the similar pattern to learn the relation between the electron density along with its derivatives and the exchange-correlation potential. On the way, it includes a finite element based radial Kohn-Sham equation-solver for a single atom, and inversion of the Kohn-Sham equation with hybrid PBE0 exchange-correlation potential.
Degree
thesis:*- Level thesis:degree_level
- Masters
- Department dc:contributor.department
- Civil and Environmental Engineering
- Grantor dc:publisher
- Georgia Institute of Technology
- Year dc:date.issued
- 2024
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Trivedi, Shubhang Krishnakant
- Advisor dc:contributor.advisor
-
- Suryanarayana, Phanish
- Committee members dc:contributor.committeemember
-
- Fedele, Francesco
- Medford, Andrew
Subjects
dc:subject × 5Rights
- Language dc:language.iso
- en_US
Identifiers
dc:identifier.*- Handle dc:identifier.uri
- https://hdl.handle.net/1853/77730