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

Machine learning in energy storage material discovery and performance prediction DOI

Guo-Chang Huang,

Fuqiang Huang, Wujie Dong

et al.

Chemical Engineering Journal, Journal Year: 2024, Volume and Issue: 492, P. 152294 - 152294

Published: May 16, 2024

Language: Английский

Citations

16
DFT-PBE band gap correction using machine learning with a reduced set of features DOI
Ibnu Jihad, Miftah Hadi S. Anfa, Saad M. Alqahtani

et al.

Computational Materials Science, Journal Year: 2024, Volume and Issue: 244, P. 113153 - 113153

Published: June 15, 2024

Language: Английский

Citations

4
Enhancing Elastic Energy Focusing in Multimode Strain Regions Via Bayesian Optimization of Gradient-Index Phononic Crystals for Energy Harvesting DOI
Wabi Demeke, Sangryun Lee, Wonju Jeon

et al.

Published: Jan. 1, 2025

Language: Английский

Citations

0
GCPNet: An interpretable Generic Crystal Pattern graph neural Network for predicting material properties DOI

H. Gao,

Xiaowei Guo,

Genglin Li

et al.

Neural Networks, Journal Year: 2025, Volume and Issue: 188, P. 107466 - 107466

Published: April 12, 2025

Language: Английский

Citations

0
Anions’ Radii — New data points calibrated to match Shannon’s table DOI

Mohammed Alsalman,

Mahmoud Hezam, Saad M. Alqahtani

et al.

Computational Materials Science, Journal Year: 2024, Volume and Issue: 247, P. 113491 - 113491

Published: Nov. 20, 2024

Language: Английский

Citations

3
Borides as promising M2AX phase materials with high elastic modulus using machine learning and optimization DOI Open Access

Ashwin Mhadeshwar,

Trupti Mohanty, Taylor D. Sparks

et al.

Journal of Materials Informatics, Journal Year: 2024, Volume and Issue: 4(3)

Published: Aug. 27, 2024

There is growing interest in novel MAX phase materials for various applications ranging from aircraft/spacecraft and defense to energy electronics due their unique combination of metallic ceramic properties. Traditional discovery has mostly relied on human intuition coupled with rigorous experiments; however, this approach been time-consuming inefficient. Over the last few decades, advances fundamental data-driven approaches such as first-principles modeling, informatics, machine learning optimization, an exponential rise computational power, have enabled faster more efficient discovery. Here, we present exploration high elastic modulus boride-based M2AX using a aforementioned methods. Specifically, ensemble gradient boosted models was developed predict informatics-based structural features by leveraging dataset Density Functional Theory (DFT)-predicted moduli 223 (carbides nitrides). Using Bayesian inverse modeling carried out maximize model-predicted identifying optimal features. Finally, model predictions 1,035 candidate were generated compare identify potential promising materials. We found that Ta2PB, Nb2PB, V2PB similar (371.7, 351.5, 347.4 GPa) carbide counterparts (364.7, 357.7, 373.5 GPa), our results support possibility borides can be viable tertiary element phases.

Language: Английский

Citations

2
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: March 27, 2024

Developing foundation models for materials science has attracted attention. However, there is a lack of work on inorganic due to the difficulty in comprehensive representation geometric concepts composing crystals, from 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 graphs, similar search, few-shot/imbalanced classification.

Language: Английский

Citations

1
Machine learning prediction of materials properties from chemical composition: Status and prospects DOI Open Access
Mohammed Alghadeer, Nyimas Aisyah, Mahmoud Hezam

et al.

Chemical Physics Reviews, Journal Year: 2024, Volume and Issue: 5(4)

Published: Dec. 1, 2024

In materials science, machine learning (ML) has become an essential and indispensable tool. ML emerged as a powerful tool in particularly for predicting material properties based on chemical composition. This review provides comprehensive overview of the current status future prospects using this domain, with special focus physics-guided (PGML). By integrating physical principles into models, PGML ensures that predictions are not only accurate but also interpretable, addressing critical need sciences. We discuss foundational concepts statistical PGML, outline general framework informatics, explore key aspects such data analysis, feature reduction, composition representation. Additionally, we survey latest advancements prediction geometric structures, electronic properties, other characteristics from formulas. The resource tables listing databases, tools, predictors, offering valuable reference researchers. As field rapidly expands, aims to guide efforts harnessing discovery development.

Language: Английский

Citations

1
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: March 28, 2024

Developing foundation models for materials science has attracted attention. However, there is a lack of work 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: March 29, 2024

Developing foundation models for materials science has attracted attention. However, there is a lack of work 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