Generative adversarial networks (GAN) based efficient sampling of chemical composition space for inverse design of inorganic materials

@article{Dan2020GenerativeAN,
  title={Generative adversarial networks (GAN) based efficient sampling of chemical composition space for inverse design of inorganic materials},
  author={Yabo Dan and Y. Zhao and Xiang Li and Shaobo Li and M. Hu and J. Hu},
  journal={npj Computational Materials},
  year={2020},
  volume={6},
  pages={1-7}
}
A major challenge in materials design is how to efficiently search the vast chemical design space to find the materials with desired properties. One effective strategy is to develop sampling algorithms that can exploit both explicit chemical knowledge and implicit composition rules embodied in the large materials database. Here, we propose a generative machine learning model (MatGAN) based on a generative adversarial network (GAN) for efficient generation of new hypothetical inorganic materials… Expand
Learning Representations of Inorganic Materials from Generative Adversarial Networks
TLDR
An adversarial method to learn the composition of atoms using the Generative Adversarial Network (GAN) and generates hypothetical materials with the same distribution as known materials, and these hypotheses can be used as a source for new material discovery. Expand
ACTIVE LEARNING BASED GENERATIVE DESIGN FOR DISCOVERY OF WIDE BAND GAP MATERIALS
Active learning has been increasingly applied to screening functional materials from existing materials databases with desired properties. However, the number of known materials deposited in theExpand
Active learning based generative design for the discovery of wide bandgap materials
TLDR
An active generative inverse design method that combines active learning with a deep variational autoencoder neural network and a generative adversarial deep neural network model to discover new materials with a target property in the whole chemical design space is presented. Expand
High-Throughput Discovery of Novel Cubic Crystal Materials Using Deep Generative Neural Networks.
TLDR
The authors show that the proposed CubicGAN model is able to not only rediscover most of the currently known cubic materials but also generate hypothetical materials of new structure prototypes, enabling the discovery of new functional materials via screening. Expand
Deep learning enabled inorganic material generator.
TLDR
The DING architecture proposed in this paper can be extended to other properties based on which the chemical space can be efficiently explored for interesting materials/molecules. Expand
Computational discovery of new 2D materials using deep learning generative models
TLDR
A template-based element substitution structure prediction approach is developed to predict the crystal structures of a subset of the newly predicted hypothetical formulas, which allows us to confirm their structure stability using DFT calculations. Expand
Machine-learning-assisted search for functional materials over extended chemical space
Materials discovery is a grand challenge for modern materials science. In particular, inverse materials design is aimed at the accelerated search for materials with human-defined target properties.Expand
Interpretable discovery of new semiconductors with machine learning
TLDR
An evolutionary algorithm powered search which uses machine-learned surrogate models trained on highthroughput hybrid functional DFT data benchmarked against experimental bandgaps: Deep Adaptive Regressive Weighted Intelligent Network (DARWIN). Expand
Mlatticeabc: Generic Lattice Constant Prediction of Crystal Materials Using Machine Learning
TLDR
MLatticeABC, a random forest machine learning model with a new descriptor set for lattice unit cell edge length (a, b, c) prediction which achieves an R2 score of 0.973, is reported, which could be used by just inputting the molecular formula of the crystal material to get the lattice constants. Expand
BASED C RYSTAL STRUCTURE PREDICTION USING GLOBAL OPTIMIZATION
Crystal structure prediction is now playing an increasingly important role in discovery of new materials. Global optimization methods such as genetic algorithms (GA) and particle swarm optimizationExpand
...
1
2
3
...

References

SHOWING 1-10 OF 45 REFERENCES
Study of Deep Generative Models for Inorganic Chemical Compositions
TLDR
This work uses a conditional VAE (CondVAE) and a conditional GAN (CondGAN) and shows that CondGAN using the bag-of-atom representation with physical descriptors generates better compositions than other generative models. Expand
CrystalGAN: Learning to Discover Crystallographic Structures with Generative Adversarial Networks
TLDR
This work proposes a novel GAN called CrystalGAN which generates new chemically stable crystallographic structures with increased domain complexity, and introduces an original architecture, the corresponding loss functions, and it is shown that the CrystalGAN generates very reasonable data. Expand
Conditional molecular design with deep generative models
TLDR
A conditional molecular design method that facilitates generating new molecules with desired properties is presented, built as a semisupervised variational autoencoder trained on a set of existing molecules with only a partial annotation. Expand
Inverse molecular design using machine learning: Generative models for matter engineering
TLDR
Methods for achieving inverse design, which aims to discover tailored materials from the starting point of a particular desired functionality, are reviewed. Expand
ElemNet: Deep Learning the Chemistry of Materials From Only Elemental Composition
TLDR
The design and implementation of a deep neural network model referred to as ElemNet is presented; it automatically captures the physical and chemical interactions and similarities between different elements using artificial intelligence which allows it to predict the materials properties with better accuracy and speed. Expand
Inverse Design of Solid-State Materials via a Continuous Representation
TLDR
This work presents a framework for learning a continuous representation of materials and building a model for new discovery using latent space representation, and suggests computational efficiency of generative models that can explore chemical compositional space effectively by learning the distributions of known materials for crystal structure prediction. Expand
Advances and challenges in deep generative models for de novo molecule generation
TLDR
A concise and insightful discussion of recent advances in applying deep generative models for de novo molecule generation is presented, with particularly emphasizing the most important challenges for successful application of deepGenerative models in this specific area. Expand
InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets
TLDR
Experiments show that InfoGAN learns interpretable representations that are competitive with representations learned by existing fully supervised methods. Expand
Screening billions of candidates for solid lithium-ion conductors: A transfer learning approach for small data.
TLDR
A novel method is proposed for transferring physical insights from physical equations onto more generic descriptors, allowing us to screen billions of unknown compositions for Li-ion conductivity, a scale which was previously unfeasible. Expand
Wasserstein Generative Adversarial Networks
TLDR
This work introduces a new algorithm named WGAN, an alternative to traditional GAN training that can improve the stability of learning, get rid of problems like mode collapse, and provide meaningful learning curves useful for debugging and hyperparameter searches. Expand
...
1
2
3
4
5
...