Magnetic iron-cobalt silicides discovered using machine-learning

Liao, Timothy; Xia, Weiyi; Sakurai, Masahiro; Wang, Renhai; Zhang, Chao; Sun, Huaijun; Ho, Kai‐Ming; Wang, Cai‐Zhuang; Chelikowsky, James R.

doi:10.1103/physrevmaterials.7.034410

Cited by 4 publications

(5 citation statements)

References 54 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…One significant advance of the integrated deep machine learning approach presented in this paper over that used in ref. 25 and 36 is that interatomic potential trained by artificial neural network (ANN) has been incorporated into our ML framework. The accuracy of the ANN-ML interatomic potentials for complex materials was also demonstrated.…”

Section: Discussionmentioning

confidence: 99%

“…Because of the incorporation of the ANN-ML interatomic potential, only a few tens or a few hundred structures (instead of several thousand structures with the approach in ref. 25 and 36) need to be final checked by first-principles calculations. Thus, the pace of the novel compound discovery can be sped up 100–1000 times without losing the accuracy of first-principles predictions.…”

Section: Discussionmentioning

confidence: 99%

“…While the g-CGCNN model has been shown to be very useful for accelerating the discovery of novel complex ternary compounds, [25][26][27] the accuracy and efficiency of the CGCNN model can be signicantly improved further if the model is retrained using the data specically targeting the materials being studied. 25,36 For La-Si-P ternary system, we retrained the CGCNN using 228 284 structures and formation energies from the dataset that was prepared to train an ANN-ML interatomic potential for the La-Si-P system (see below and ESI †). We refer to this later CGCNN model as a specic CGCMM (s-CGCNN) model.…”

Section: Accelerated Discovery Of La-si-p Ternary Compoundsmentioning

confidence: 99%

See 2 more Smart Citations

Accelerating materials discovery using integrated deep machine learning approaches

Xia,

Tang,

Sun

et al. 2023

J. Mater. Chem. A

Self Cite

View full text Add to dashboard Cite

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Section: Accelerated Discovery Of La-si-p Ternary Compoundsmentioning

confidence: 99%

See 1 more Smart Citation

Accelerating materials discovery using integrated deep machine learning approaches

Xia,

Tang,

Sun

et al. 2023

J. Mater. Chem. A

Self Cite

View full text Add to dashboard Cite

show abstract

“…Fortunately, mankind has developed artificial intelligence as a means of coping with the enormous information abundance. Methodologies have been proposed for the application of machine learning to chemical/material systems [337][338][339][340][341] and the concept of materials informatics [342][343][344]. For the preparation and use of nanospaces (nanopores, etc.…”

Section: Summary and Perspectivesmentioning

confidence: 99%

Confined Space Nanoarchitectonics for Dynamic Functions and Molecular Machines

Ariga

2024

Micromachines

View full text Add to dashboard Cite

Nanotechnology has advanced the techniques for elucidating phenomena at the atomic, molecular, and nano-level. As a post nanotechnology concept, nanoarchitectonics has emerged to create functional materials from unit structures. Consider the material function when nanoarchitectonics enables the design of materials whose internal structure is controlled at the nanometer level. Material function is determined by two elements. These are the functional unit that forms the core of the function and the environment (matrix) that surrounds it. This review paper discusses the nanoarchitectonics of confined space, which is a field for controlling functional materials and molecular machines. The first few sections introduce some of the various dynamic functions in confined spaces, considering molecular space, materials space, and biospace. In the latter two sections, examples of research on the behavior of molecular machines, such as molecular motors, in confined spaces are discussed. In particular, surface space and internal nanospace are taken up as typical examples of confined space. What these examples show is that not only the central functional unit, but also the surrounding spatial configuration is necessary for higher functional expression. Nanoarchitectonics will play important roles in the architecture of such a total system.

show abstract

“…The design of such materials has been addressed by us and other authors. ,− These works used either high-throughput DFT calculations or ML-assisted screening to identify candidate materials, followed by validation with DFT calculations. So far, generative models have not been employed to address the problem, primarily due to the paucity of materials data for AE.…”

mentioning

confidence: 99%

MagGen: A Graph-Aided Deep Generative Model for Inverse Design of Permanent Magnets

Mal,

Seal,

Sen

2024

J. Phys. Chem. Lett.

View full text Add to dashboard Cite

A deep generative model based on a variational autoencoder (VAE), conditioned simultaneously by two target properties, is developed to inverse design stable magnetic materials. The structure of the physics-informed, property embedded latent space of the model is analyzed using graph theory. An impressive ∼96% of the generated materials are found to satisfy the target properties as per predictions from the target-learning branches. This is a huge improvement over approaches that do not condition the VAE latent space by target properties or that do not consider the connectivity of the parent materials from which the new materials are generated. This impressive feat is achieved by using a simple real-space-only representation that can be directly read from material cif files. Model predictions are finally validated by density functional theory calculations on a randomly chosen subset of materials. The performance of the present model is comparable or superior to that of models reported earlier. This model (MagGen) is applied to the problem of designing rare earth-free permanent magnets with promising results.

show abstract

Magnetic iron-cobalt silicides discovered using machine-learning

Cited by 4 publications

References 54 publications

Accelerating materials discovery using integrated deep machine learning approaches

Accelerating materials discovery using integrated deep machine learning approaches

Confined Space Nanoarchitectonics for Dynamic Functions and Molecular Machines

MagGen: A Graph-Aided Deep Generative Model for Inverse Design of Permanent Magnets

Contact Info

Product

Resources

About