A generative model for inorganic materials design

Nature, Journal Year: 2025, Volume and Issue: 639(8055), P. 624 - 632

Published: Jan. 16, 2025

Language: Английский

---

Artificial Intelligence and Machine Learning in Tribology: Selected Case Studies and Overall Potential

Advanced Engineering Materials, Journal Year: 2025, Volume and Issue: unknown

Published: Jan. 15, 2025

Artificial intelligence (AI) and machine learning (ML) have been the subjects of increased interest in recent years due to their benefits across several fields. One sector that can benefit from these tools is tribology industry, with an emphasis on friction wear prediction. This industry hopes train utilize AI algorithms classify equipment life status forecast component failure, mainly using supervised unsupervised approaches. article examines some methods used accomplish this, such as condition monitoring for predictions material selection, lubrication performance, lubricant formulation. Furthermore, ML support determination tribological characteristics engineering systems, allowing a better fundamental understanding friction, wear, mechanisms. Moreover, study also finds continued use requires access findable, accessible, interoperable, reusable data ensure integrity prediction tools. The advances show considerable promise, providing more accurate extensible than traditional

Language: Английский

---

Accelerating the prediction of stable materials with machine learning

Nature Computational Science, Journal Year: 2023, Volume and Issue: 3(11), P. 934 - 945

Published: Nov. 9, 2023

Language: Английский

---

Machine learning in energy storage material discovery and performance prediction

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

Published: May 16, 2024

Language: Английский

---

Advances in materials informatics: a review

Journal of Materials Science, Journal Year: 2024, Volume and Issue: 59(7), P. 2602 - 2643

Published: Feb. 1, 2024

Language: Английский

---

Developments and applications of the OPTIMADE API for materials discovery, design, and data exchange

Digital Discovery, Journal Year: 2024, Volume and Issue: 3(8), P. 1509 - 1533

Published: Jan. 1, 2024

The Open Databases Integration for Materials Design (OPTIMADE) application programming interface (API) empowers users with holistic access to a growing federation of databases, enhancing the accessibility and discoverability materials chemical data. Since first release OPTIMADE specification (v1.0), API has undergone significant development, leading v1.2 release, underpinned multiple scientific studies. In this work, we highlight latest features format, accompanying software tools, provide an update on implementation in contributing databases. We end by providing several use cases that demonstrate utility research continue drive its ongoing development.

Language: Английский

---

Oxygen Vacancy Formation Energy in Metal Oxides: High-Throughput Computational Studies and Machine-Learning Predictions

Chemistry of Materials, Journal Year: 2023, Volume and Issue: 35(24), P. 10619 - 10634

Published: Dec. 4, 2023

The oxygen vacancy formation energy (ΔEvf) governs defect concentrations alongside the entropy and is a useful metric to perform materials selection for variety of applications. However, density functional theory (DFT) calculations ΔEvf come at greater computational cost than typical bulk available in databases due involvement multiple vacancy-containing supercells. As result, repositories direct remain relatively scarce, development machine-learning models capable delivering accurate predictions interest. In present work, we address both such points. We first report results new high-throughput DFT energies different unique sites over 1000 oxide materials, with large portion calculations, discussion, focusing on perovskite-type pyrochlore-type oxides. Together, 2500 form largest data set directly computed date, our knowledge. then utilize train random forest sets features, examining novel features introduced this work ones previously employed literature. demonstrate benefits including that contain information specific site account cation identity oxidation state achieve mean absolute error upon prediction ∼0.3 eV/O, which comparable accuracy observed comparison computations experimental results. Finally, exemplify predictive power developed search compounds solar-thermochemical water-splitting applications, finding 250 AA′BB′O6 double perovskite candidates.

Language: Английский

---

Stability and Equilibrium Structures of Unknown Ternary Metal Oxides Explored by Machine-Learned Potentials

Journal of the American Chemical Society, Journal Year: 2023, Volume and Issue: 145(35), P. 19378 - 19386

Published: Aug. 11, 2023

Ternary metal oxides are crucial components in a wide range of applications and have been extensively cataloged experimental materials databases. However, there still exist cation combinations with unknown stability structures their compounds oxide forms. In this study, we employ extensive crystal structure prediction methods, accelerated by machine-learned potentials, to investigate these untapped chemical spaces. We examine 181 ternary systems, encompassing most cations except for partially filled 3d or f shells, determine lowest-energy representative stoichiometry derived from prevalent oxidation states recommender systems. Consequently, discover 45 systems containing stable against decomposition into binary elemental phases, the majority which incorporate noble metals. Comparisons other theoretical databases highlight strengths limitations informatics-based material searches. With relatively modest computational resource requirement, contend that heuristic-based searches, as demonstrated offer promising approach future discovery endeavors.

Language: Английский

---

Accuracy of DFT computed oxygen-vacancy formation energies and high-throughput search of solar thermochemical water-splitting compounds

Physical Review Materials, Journal Year: 2023, Volume and Issue: 7(6)

Published: June 7, 2023

The computation of the oxygen vacancy formation energy using density functional theory is a critical factor in applications like solar thermochemical hydrogen production. However, when we calculate it structures that are dynamically unstable, results artificially reduced values and lack convergence with cell size. By comparing calculated experimental data, authors can clearly see importance stable for accurate calculations. This comparison also validates reliability Furthermore, high-throughput approach, perform such calculations to identify new candidates production among ABO${}_{3}$ perovskite materials, demonstrating striong influence B-site cations on energy.

Language: Английский

---

Machine-Learning-Assisted Understanding of Polymer Nanocomposites Composition–Property Relationship: A Case Study of NanoMine Database

Macromolecules, Journal Year: 2023, Volume and Issue: 56(11), P. 3945 - 3953

Published: May 23, 2023

The NanoMine database, one of two nodes in the MaterialsMine is a new materials data resource that collects annotated on polymer nanocomposites (PNCs). This work showcases potential and other resources to assist fundamental understanding therefore rational design. specific case study built around studying relationship between change glass transition temperature Tg (ΔTg) key descriptors nanofillers matrix PNCs. We sifted through from over 2000 experimental samples curated into NanoMine, trained decision tree classifier predict sign PNC ΔTg, multiple power regression metamodel ΔTg. successful model used including composition, nanoparticle volume fraction, interfacial surface energy. results demonstrate using aggregated gain insight predictive capability. Further analysis points importance additional parameters processing methodologies continuously adding sets increase sample pool size.

Language: Английский

---