Prediction of crystal structure, phase group, and stability of 2D materials through data science coupled with DFT DOI

N. Nagappan,

G. Sudha Priyanga,

Tiju Thomas

et al.

Physica B Condensed Matter, Journal Year: 2024, Volume and Issue: unknown, P. 416638 - 416638

Published: Oct. 1, 2024

Language: Английский

Graph-Text Contrastive Learning of Inorganic Crystal Structure toward a Foundation Model of Inorganic Materials DOI Creative Commons
Keisuke Ozawa, Teppei Suzuki, Shunsuke Tonogai

et al.

Published: April 1, 2024

Developing foundation models for materials science has attracted attention. However, there is a lack of studies on inorganic due to the difficulty in comprehensive representation geometric concepts composing crystals: local atomic environments, their connections, and global symmetries. We present contrastive learning crystal structure (CLICS) embedding concepts, which contrasts texts representing contextual patterns geometries with graphs. demonstrate that are integrally embedded CLICS feature space, through experiments concept retrieval from graphs, similar search, few-shot/imbalanced classification.

Language: Английский

Citations

0
Graph-Text Contrastive Learning of Inorganic Crystal Structure toward a Foundation Model of Inorganic Materials DOI Creative Commons
Keisuke Ozawa, Teppei Suzuki, Shunsuke Tonogai

et al.

Published: April 3, 2024

Developing foundation models for materials science has attracted attention. However, there is a lack of studies on inorganic due to the difficulty in comprehensive representation geometric concepts composing crystals: local atomic environments, their connections, and global symmetries. We present contrastive learning crystal structure (CLICS) embedding concepts, which contrasts texts representing contextual patterns geometries with graphs. demonstrate that are integrally embedded CLICS feature space, through experiments concept retrieval from graphs, similar search, few-shot/imbalanced classification.

Language: Английский

Citations

0
Graph-Text Contrastive Learning of Inorganic Crystal Structure toward a Foundation Model of Inorganic Materials DOI Creative Commons
Keisuke Ozawa, Teppei Suzuki, Shunsuke Tonogai

et al.

Published: April 15, 2024

Developing foundation models for materials science has attracted attention. However, there is a lack of studies on inorganic due to the difficulty in comprehensive representation geometric concepts composing crystals: local atomic environments, their connections, and global symmetries. We present contrastive learning crystal structure (CLICS) embedding concepts, which contrasts texts representing contextual patterns geometries with graphs. demonstrate that are integrally embedded CLICS feature space, through experiments concept retrieval from graphs, similar search, few-shot/imbalanced classification.

Language: Английский

Citations

0
Graph-text contrastive learning of inorganic crystal structure toward a foundation model of inorganic materials DOI Creative Commons
Keisuke Ozawa, Teppei Suzuki, Shunsuke Tonogai

et al.

Science and Technology of Advanced Materials Methods, Journal Year: 2024, Volume and Issue: unknown

Published: Sept. 23, 2024

Language: Английский

Citations

0
Prediction of crystal structure, phase group, and stability of 2D materials through data science coupled with DFT DOI

N. Nagappan,

G. Sudha Priyanga,

Tiju Thomas

et al.

Physica B Condensed Matter, Journal Year: 2024, Volume and Issue: unknown, P. 416638 - 416638

Published: Oct. 1, 2024

Language: Английский

Citations

0