Learning atoms for materials discovery

Zhou, Quan; Tang, Peizhe; Liu, Shenxiu; Pan, Jinbo; Yan, Qimin; Zhang, Shou Cheng

doi:10.1073/pnas.1801181115

Cited by 177 publications

(155 citation statements)

References 29 publications

Supporting

Mentioning

151

Contrasting

Unclassified

Order By: Relevance

“…PCA is a method of feature extraction and dimensionality reduction, and it is widely used in previous studies to visualize the high-dimensional features. [39][40][41] As seen in Fig. 4b, alkali metals (group I), alkali earth metals (group II), halogens (group VII), and rare gases (group VIII) are clustered in different regions.…”

Section: Discussionmentioning

confidence: 99%

Atom table convolutional neural networks for an accurate prediction of compounds properties

Zeng

Zhao

et al. 2019

npj Comput Mater

View full text Add to dashboard Cite

Machine learning techniques are widely used in materials science. However, most of the machine learning models require a lot of prior knowledge to manually construct feature vectors. Here, we develop an atom table convolutional neural networks that only requires the component information to directly learn the experimental properties from the features constructed by itself. For band gap and formation energy prediction, the accuracy of our model exceeds the standard DFT calculations. Besides, through dataenhanced technology, our model not only accurately predicts superconducting transition temperatures, but also distinguishes superconductors and non-superconductors. Utilizing the trained model, we have screened 20 compounds that are potential superconductors with high superconducting transition temperature from the existing database. In addition, from the learned features, we extract the properties of the elements and reproduce the chemical trends. This framework is valuable for high throughput screening and helpful to understand the underlying physics.

show abstract

Section: Discussionmentioning

confidence: 99%

Atom table convolutional neural networks for an accurate prediction of compounds properties

Zeng

Zhao

et al. 2019

npj Comput Mater

View full text Add to dashboard Cite

show abstract

“…The atomic vector (Atom2Vec) was first proposed by Quan et al [38] of Stanford University. Below, we briefly describe the workflow of Atom2Vec.…”

Section: Atomic Vector Generation Methodsmentioning

confidence: 99%

“…The existence of the element's environmental and order dependencies often greatly affects the properties of materials. Based on this, this paper proposes a method that uses atomic vectors [38,39] to describe materials and uses an HNN model that combines a convolutional neural network CNN and long short-term memory neural network (LSTM) to predict Tc. The HNN model uses CNN to extract the short-dependence feature relationships between atoms, and the LSTM…”

mentioning

confidence: 99%

Critical Temperature Prediction of Superconductors Based on Atomic Vectors and Deep Learning

Dan

et al. 2020

Symmetry

View full text Add to dashboard Cite

In this paper, a hybrid neural network (HNN) that combines a convolutional neural network (CNN) and long short-term memory neural network (LSTM) is proposed to extract the high-level characteristics of materials for critical temperature (Tc) prediction of superconductors. Firstly, by obtaining 73,452 inorganic compounds from the Materials Project (MP) database and building an atomic environment matrix, we obtained a vector representation (atomic vector) of 87 atoms by singular value decomposition (SVD) of the atomic environment matrix. Then, the obtained atom vector was used to implement the coded representation of the superconductors in the order of the atoms in the chemical formula of the superconductor. The experimental results of the HNN model trained with 12,413 superconductors were compared with three benchmark neural network algorithms and multiple machine learning algorithms using two commonly used material characterization methods. The experimental results show that the HNN method proposed in this paper can effectively extract the characteristic relationships between the atoms of superconductors, and it has high accuracy in predicting the Tc.Symmetry 2020, 12, 262 2 of 13 same time, the prediction of the Tc of superconductors, especially high-temperature superconductors, is not very accurate. The solution of these problems depends on the discovery of superconductors or similar materials and an understanding of the physical properties of these materials. Although this was the focus of research for the past 30 years, the prediction of Tc of superconductors is still very difficult.Advances in computers, as well as the development and continuous improvement of first-principles computational quantum chemistry theories and statistical (or machine learning) methods, greatly influenced research activities related to material discovery and design [12]. Material design for high-throughput (HT) calculations made progress in determining the structure of thousands of inorganic solids [13,14]. Since 1970, density functional theory (DFT) is widely used in the calculation of solid-state physics. In most cases, compared with other methods for solving multi-body problems in quantum mechanics, DFT using local density approximation gives very satisfactory results, and solid-state computing is less expensive than experiments. DFT is the leading method for the calculation of electronic structures in various fields; however, these methods are currently not suitable for high-level calculations due to the high-cost calculation. When using standard exchanges and correlation functions such as Perdew-Berke-Ernzerhof (PBE) [15] which is currently the most widely used exchange-related functional form in the calculation of solid structures, there are cases where the system is underestimated compared to the experimental values.In addition to prediction models based on physical principles/theories, the machine learning [16-21] approach for Tc prediction is a data-driven prediction model, which exploits the relationship between material ...

show abstract

“…Unsupervised learning has a promising application in material search. Zhang and coworkers build an Atom2Vec model using unsupervised learning . The basic properties of atoms can learn by themselves from the extensive database of known compounds and materials with the help of this model.…”

Section: Discussionmentioning

confidence: 99%

Simulation and design of energy materials accelerated by machine learning

Wang

2019

WIREs Comput Mol Sci

View full text Add to dashboard Cite

In the light of mature mathematical algorithms and material database construction, a basic research framework of machine learning (ML) method integrated with computational chemistry toolkits exhibits great potentials and advantages in the field of material researches. In this review, we introduce a work flow of ML in energy materials and demonstrate its recent applications in accelerating the material exploration, especially significant progresses in designing novel catalysts, organic and inorganic battery materials and metal-organic framework materials. As a rising research direction, we also identify the prospects and challenges of ML. More automated and intelligent workflows will be widely used in energy material design with the development of ML. Our review provides a guideline to study and design energy materials in the framework of ML. DatabasesDescription URL AFLOWLIBStructure and property repository from high-throughput ab initio calculations of inorganic materials http://afowlib.org Materials Project Computed properties of known and hypothetical materials carried out using a standard calculation scheme https://materialsproject.org GDB Databases of hypothetical small organic molecules http://gdb.unibe.ch/downloads ZINC Commercially available organic molecules in 2D and 3D formats https://zinc15.docking.org NREL Materials Database Computed properties of materials for renewable energy applications https://materials.nrel.gov Harvard Clean Energy Project Computed properties of candidate organic solar absorber materials https://cepdb.molecularspace.org TEDesignLab Experimental and computed properties to aid the design of new thermoelectric materials

show abstract

Learning atoms for materials discovery

Cited by 177 publications

References 29 publications

Atom table convolutional neural networks for an accurate prediction of compounds properties

Atom table convolutional neural networks for an accurate prediction of compounds properties

Critical Temperature Prediction of Superconductors Based on Atomic Vectors and Deep Learning

Simulation and design of energy materials accelerated by machine learning

Contact Info

Product

Resources

About