Machine learning discovery of multi metal oxide catalyst for oxygen evolution reaction
The depletion of fossil fuels and environmental issues have highlighted the need for a green and sustainable alternative energy source for the future economy. Among the various solutions, hydrogen production from the electrolysis of water is a promising solution. Extensive efforts have been devoted...
Saved in:
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Final Year Project |
| Language: | English |
| Published: |
Nanyang Technological University
2022
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/156307 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Institution: | Nanyang Technological University |
| Language: | English |
| Summary: | The depletion of fossil fuels and environmental issues have highlighted the need for a green and sustainable alternative energy source for the future economy. Among the various solutions, hydrogen production from the electrolysis of water is a promising solution. Extensive efforts have been devoted in research to find high-performance electrocatalysts for oxygen evolution reaction (OER) to improve the efficiency of electrolysis of water. In recent years, spinel oxides have gained extensive interest in the field of OER electrocatalyst as they demonstrate excellent catalytic activity while being cost-effective. However, there are numerous spinel oxides and their catalytic performance vary in terms of different compositions. It will be extremely time consuming to measure the catalytic performance for each spinel oxide through experiment in order to determine the optimum catalyst. In this study, machine learning (ML) techniques are adopted to accelerate the discovery of the optimum OER catalyst using basic electronic parameters such as octahedral factor, electronegativity and ionic radii as predictors. Spinel [Li0.25Mn0.75]Mn2O4 oxide is predicted to be a highly active OER catalyst. |
|---|