Modelling of photocatalytic Cu2O surfaces with machine learning
| Thesis title in Czech: | Modelování fotokatalytických povrchů Cu2O pomocí metod strojového učení |
|---|---|
| Thesis title in English: | Modelling of photocatalytic Cu2O surfaces with machine learning |
| Key words: | Oxid měďný, potenciály strojového učení, sítě neuronových potenciálů, teorie funkcionálu hustoty, molekulová dynamika, adsorpce, hydroxylace |
| English key words: | Cuprous oxide, Machine Learning, Neural Network Potential, Density Functional Theory, Molecular Dynamics, Adsorption, Hydroxylation |
| Academic year of topic announcement: | 2024/2025 |
| Thesis type: | diploma thesis |
| Thesis language: | angličtina |
| Department: | Department of Physical and Macromolecular Chemistry (31-260) |
| Supervisor: | Christopher James Heard, Ph.D. |
| Author: | hidden - assigned and confirmed by the Study Dept. |
| Date of registration: | 11.11.2024 |
| Date of assignment: | 11.11.2024 |
| Confirmed by Study dept. on: | 13.01.2025 |
| Date of electronic submission: | 17.05.2025 |
| Date of proceeded defence: | 03.06.2025 |
| Opponents: | Dr. Eros Radicchi |
| Advisors: | doc. RNDr. Lukáš Grajciar, Ph.D. |
| Preliminary scope of work |
| DFT calculations (statics and dynamics) for generation of ML training dataset Development, testing and application of novel machine learning potentials for copper oxide surfaces using equivariant NN architecture (PaiNN) Modelling of surface science of (photocatalytically active) Cu2O surfaces - including dynamics, effect of defects, thermal distortions and adsorbates on stability, structure and reactivity of Cu2O. Programming of new NNPs Consultation with experimental collaborators (at TU Wien) Computational generation and comparison of microscopic observables (LEED IV, AFM) |
| Preliminary scope of work in English |
| DFT calculations (statics and dynamics) for generation of ML training dataset Development, testing and application of novel machine learning potentials for copper oxide surfaces using equivariant NN architecture (PaiNN) Modelling of surface science of (photocatalytically active) Cu2O surfaces - including dynamics, effect of defects, thermal distortions and adsorbates on stability, structure and reactivity of Cu2O. Programming of new NNPs Consultation with experimental collaborators (at TU Wien) Computational generation and comparison of microscopic observables (LEED IV, AFM) |