.png){kind=icon}
返回
Boosting heterogeneous catalyst discovery by structurally constrained deep learning models
.png){kind=icon}
OA
AI
DOI：10.1016/j.mtchem.2023.101541.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
The discovery of new catalysts is one of the significant topics of computational chemistry as it has the potential to accelerate the adoption of renewable energy sources. Recently developed deep learning approaches such as graph neural networks open new opportunity to significantly extend scope for modeling novel high-performance catalysts. Nevertheless, the graph representation of a particular crystal structure is not a straightforward task due to the ambiguous connectivity schemes and numerous embeddings of nodes and edges. Here, we present embedding improvement for graph neural networks that has been modified by Voronoi tessellation and is able to predict the energy of catalytic systems within the Open Catalyst Project dataset. The enrichment of the graph was calculated via Voronoi tessellation, and the corresponding contact solid angles and types (direct/indirect) were considered as edges' features, and Voronoi volumes were used as node characteristics. The auxiliary approach was enriching node representation by intrinsic atomic properties (electronegativity, period, and group po-sition). The proposed modifications allowed us to improve the mean absolute error of the original model, and the final error equals to 651 meV on the Open Catalyst Project dataset and 6 meV/atom on the intermetallics dataset. Also, by the consideration of an additional dataset, we show that a sensible choice of data can decrease the error to values below a physically-based 20 meV/atom threshold. (c) 2023 The Authors. Published by Elsevier Ltd. This is an open access article under the CC BY license (http://creativecommons.org/licenses/by/4.0/).
Keyword:
New material design
Machine Learning
Graph neural networks
Catalysis
Intermetallics
Composition
configuration spaces
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
6.7
论文数:
4.0K
被引数:
1.4W
机构
暂无机构信息
引用论文
Central point sampling from cattle in livestock markets in areas of human sleeping sickness.png)
Acta Tropica
Acta TropicaIF0
PREAI
分享收藏Applied Topological Analysis of Crystal Structures with the Program Package ToposPro用程序包ToposPro对晶体结构进行应用拓扑分析
OAAI
OAAI分享收藏分享收藏Understanding the Composition and Activity of Electrocatalytic Nanoalloys in Aqueous Solvents: A Combination of DFT and Accurate Neural Network PotentialsNANO LETTERS
NANO LETTERSIF9.1
PREAI
分享收藏Acetylcorynoline Impairs the Maturation of Mouse Bone Marrow-Derived Dendritic Cells via Suppression of IκB Kinase and Mitogen-Activated Protein Kinase ActivitiesPLoS ONEOAAI
PLoS ONEIF0
OAAI分享收藏
查看更多内容