Machine learning accelerated exploration of CO2 reduction electrocatalyst

CO2 reduction is proved to be a possible way to recycle excessive atmospheric CO2 while producing alternative fuels and useful chemicals. Catalysts for electrochemical CO2 reduction reaction (CO2RR) is the key to an efficient conversion towards desired products. Despite the endeavours of many resear...

Full description

Saved in:
Bibliographic Details
Main Author: Hu, Erhai
Other Authors: Alex Yan Qingyu
Format: Final Year Project
Language:English
Published: Nanyang Technological University 2022
Subjects:
Online Access:https://hdl.handle.net/10356/156044
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-156044
record_format dspace
spelling sg-ntu-dr.10356-1560442022-03-31T06:10:37Z Machine learning accelerated exploration of CO2 reduction electrocatalyst Hu, Erhai Alex Yan Qingyu School of Materials Science and Engineering AlexYan@ntu.edu.sg Engineering::Materials::Energy materials Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence CO2 reduction is proved to be a possible way to recycle excessive atmospheric CO2 while producing alternative fuels and useful chemicals. Catalysts for electrochemical CO2 reduction reaction (CO2RR) is the key to an efficient conversion towards desired products. Despite the endeavours of many researchers, the progress in discovering high-performing electrocatalysts has been limited by time-consuming experiments and DFT calculations. Recently, Machine Learning (ML) emerges as a powerful tool in catalysis research due to its high efficiency and accuracy. Therefore, we explore the feasibility of using ML to accelerate the discovery of CO2RR catalysts by predicting their selectivity. A Crystal Graph Convolutional Neural Network (CGCNN) is implemented to predict the adsorption energy of key intermediate on the surface of certain catalysts. Then, the adsorption energies of CO and OH are used to qualitatively predict the major product according to a thermodynamical analysis. Using this method, the selectivity of five single metal catalysts and two bimetallic systems with various compositions are analysed. Experiments are conducted to verify the ML result. As a result, it shows that ML prediction is able to provide useful insight into electrochemical CO2RR catalyst selection. Bachelor of Engineering (Materials Engineering) 2022-03-31T06:10:37Z 2022-03-31T06:10:37Z 2022 Final Year Project (FYP) Hu, E. (2022). Machine learning accelerated exploration of CO2 reduction electrocatalyst. Final Year Project (FYP), Nanyang Technological University, Singapore. https://hdl.handle.net/10356/156044 https://hdl.handle.net/10356/156044 en application/pdf Nanyang Technological University
institution Nanyang Technological University
building NTU Library
continent Asia
country Singapore
Singapore
content_provider NTU Library
collection DR-NTU
language English
topic Engineering::Materials::Energy materials
Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence
spellingShingle Engineering::Materials::Energy materials
Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence
Hu, Erhai
Machine learning accelerated exploration of CO2 reduction electrocatalyst
description CO2 reduction is proved to be a possible way to recycle excessive atmospheric CO2 while producing alternative fuels and useful chemicals. Catalysts for electrochemical CO2 reduction reaction (CO2RR) is the key to an efficient conversion towards desired products. Despite the endeavours of many researchers, the progress in discovering high-performing electrocatalysts has been limited by time-consuming experiments and DFT calculations. Recently, Machine Learning (ML) emerges as a powerful tool in catalysis research due to its high efficiency and accuracy. Therefore, we explore the feasibility of using ML to accelerate the discovery of CO2RR catalysts by predicting their selectivity. A Crystal Graph Convolutional Neural Network (CGCNN) is implemented to predict the adsorption energy of key intermediate on the surface of certain catalysts. Then, the adsorption energies of CO and OH are used to qualitatively predict the major product according to a thermodynamical analysis. Using this method, the selectivity of five single metal catalysts and two bimetallic systems with various compositions are analysed. Experiments are conducted to verify the ML result. As a result, it shows that ML prediction is able to provide useful insight into electrochemical CO2RR catalyst selection.
author2 Alex Yan Qingyu
author_facet Alex Yan Qingyu
Hu, Erhai
format Final Year Project
author Hu, Erhai
author_sort Hu, Erhai
title Machine learning accelerated exploration of CO2 reduction electrocatalyst
title_short Machine learning accelerated exploration of CO2 reduction electrocatalyst
title_full Machine learning accelerated exploration of CO2 reduction electrocatalyst
title_fullStr Machine learning accelerated exploration of CO2 reduction electrocatalyst
title_full_unstemmed Machine learning accelerated exploration of CO2 reduction electrocatalyst
title_sort machine learning accelerated exploration of co2 reduction electrocatalyst
publisher Nanyang Technological University
publishDate 2022
url https://hdl.handle.net/10356/156044
_version_ 1729789496390582272