Machine learning-guided synthesis of advanced inorganic materials

Tang, Bijun; Lu, Yong; Zhou, Jiadong; Chouhan, Tushar; Wang, Han; Golani, Prafful; Xu, Manzhang; Xu, Quan; Guan, Cuntai; Liu, Zheng

doi:10.1016/j.mattod.2020.06.010

Cited by 100 publications

(92 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In recent years, machine learning algorithms have irrupted as an alternative tool to model the properties and structure of materials [1][2][3][4][5][6][7][8][9][10][11]. These algorithms have allowed scientists to work with large particle systems at shorter times and lower computational costs with respect to the recurred quantum methods [12][13][14][15].…”

Section: Introductionmentioning

confidence: 99%

Crystal-Site-Based Artificial Neural Networks for Material Classification

2021

View full text Add to dashboard Cite

In materials science, crystal structures are the cornerstone in the structure–property paradigm. The description of crystal compounds may be ascribed to the number of different atomic chemical environments, which are related to the Wyckoff sites. Hence, a set of features related to the different atomic environments in a crystal compound can be constructed as input data for artificial neural networks (ANNs). In this article, we show the performance of a series of ANNs developed using crystal-site-based features. These ANNs were developed to classify compounds into halite, garnet, fluorite, hexagonal perovskite, ilmenite, layered perovskite, -o-tp- perovskite, perovskite, and spinel structures. Using crystal-site-based features, the ANNs were able to classify the crystal compounds with a 93.72% average precision. Furthermore, the ANNs were able to retrieve missing compounds with one of these archetypical structure types from a database. Finally, we showed that the developed ANNs were also suitable for a multitask learning paradigm, since the extracted information in the hidden layers linearly correlated with lattice parameters of the crystal structures.

show abstract

Section: Introductionmentioning

confidence: 99%

Crystal-Site-Based Artificial Neural Networks for Material Classification

2021

View full text Add to dashboard Cite

show abstract

“…However, providing a general metric to identify the probability of successful synthesis of hypothetical crystals is a challenging task because of the broad range of parameters controlling the synthesis process, including processing rates and routes, thermodynamic handles, synthesis techniques, and synthesis scales. While materials synthesis is traditionally guided by the expert-interpreted knowledge of various synthesis conditions 1,2 , recent computational methods and machine learning approaches provide prospects for predictive capability and guidelines for the synthesis of future materials [3][4][5][6][7][8][9][10][11][12] . However, there remains a lack of general and accurate predictive models for synthesizability across various crystal structure types and chemical compositions.…”

mentioning

confidence: 99%

“…Only a few studies have employed machine learning to address the issue of synthesizability of crystalline materials [8][9][10][11][12][14][15][16][17][18][19] . In one of the earliest studies by Hautier et al 15,16 developed a probabilistic model built on an experimental crystal structure database to quantify the likelihood of substitution of certain ions in a compound leading to another compound with the same crystal structure.…”

mentioning

confidence: 99%

“…They utilized their model to predict the likelihood of successful experimental synthesis of hypothetical materials. Some recent studies utilize expert-knowledge-based parameters instead of structural or chemical features to predict synthesis success [9][10][11][12] . For example, Kim et al 10 analyzed the literature text via natural language processing methods to determine the significant parameters involved in the synthesis of titania nanotubes by hydrothermal methods, and Raccuglia et al 9 used failed hydrothermal synthesis experimental data to predict the crystallization of vanadium selenites.…”

mentioning

confidence: 99%

“…For example, Kim et al 10 analyzed the literature text via natural language processing methods to determine the significant parameters involved in the synthesis of titania nanotubes by hydrothermal methods, and Raccuglia et al 9 used failed hydrothermal synthesis experimental data to predict the crystallization of vanadium selenites. Tang et al 12 utilized machine learning to optimize synthesis conditions in order to enhance process-related properties in inorganic crystalline solids.…”

mentioning

confidence: 99%

See 2 more Smart Citations

Predicting synthesizability of crystalline materials via deep learning

2021

View full text Add to dashboard Cite

Predicting the synthesizability of hypothetical crystals is challenging because of the wide range of parameters that govern materials synthesis. Yet, exploring the exponentially large space of novel crystals for any future application demands an accurate predictive capability for synthesis likelihood to avoid a haphazard trial-and-error. Typically, benchmarks of synthesizability are defined based on the energy of crystal structures. Here, we take an alternative approach to select features of synthesizability from the latent information embedded in crystalline materials. We represent the atomic structure of crystalline materials by three-dimensional pixel-wise images that are color-coded by their chemical attributes. The image representation of crystals enables the use of a convolutional encoder to learn the features of synthesizability hidden in structural and chemical arrangements of crystalline materials. Based on the presented model, we can accurately classify materials into synthesizable crystals versus crystal anomalies across a broad range of crystal structure types and chemical compositions. We illustrate the usefulness of the model by predicting the synthesizability of hypothetical crystals for battery electrode and thermoelectric applications.

show abstract