Che, Yu ORCID: 0000-0002-8589-6795
(2023)
Data-driven approach of discovering organic photocatalysts and developing molecular force field by machine learning.
PhD thesis, University of Liverpool.
Text
201158882_May2023.pdf - Author Accepted Manuscript Download (16MB) | Preview |
Abstract
Machine learning techniques are becoming more prevalent in chemistry research as they offer an effective approach for handling large, complex chemical datasets generated from high-throughput experiments and molecular simulations. To gain a comprehensive under- standing of datasets, it is crucial to employ efficient methods for data representation and analysis. This PhD project utilized classical machine learning algorithms to effectively visualize high-dimensional chemical data, ascertain connections between chemical struc- ture and properties, facilitate the discovery of novel organic catalysts, and developing a machine learning potential to describe intermolecular interactions.
Item Type: | Thesis (PhD) |
---|---|
Uncontrolled Keywords: | Bayesian optimization, data visualization, machine learning, machine learning potential, photocatalyst |
Divisions: | Faculty of Science and Engineering > School of Physical Sciences |
Depositing User: | Symplectic Admin |
Date Deposited: | 10 Aug 2023 15:54 |
Last Modified: | 10 Aug 2023 15:55 |
DOI: | 10.17638/03171161 |
Supervisors: |
|
URI: | https://livrepository.liverpool.ac.uk/id/eprint/3171161 |