Constrained crystals deep convolutional generative adversarial network for the inverse design of crystal structures

Abstract

Autonomous materials discovery with desired properties is one of the ultimate goals for materials science, and the current studies have been focusing mostly on high-throughput screening based on density functional theory calculations and forward modelling of physical properties using machine learning. Applying the deep learning techniques, we have developed a generative model which can predict distinct stable crystal structures by optimizing the formation energy in the latent space. It is demonstrated that the optimization of physical properties can be integrated into the generative model as on-top screening or backwards propagator, both with their own advantages. Applying the generative models on the binary Bi-Se system reveals that distinct crystal structures can be obtained covering the whole composition range, and the phases on the convex hull can be reproduced after the generated structures are fully relaxed to the equilibrium. The method can be extended to multicomponent systems for multi-objective optimization, which paves the way to achieve the inverse design of materials with optimal properties.

23 pages, 3 figures

References in corpus (12)

• Auto-Encoding Variational Bayes
• Generative Adversarial Networks
• Automatic chemical design using a data-driven continuous representation of molecules
• CALYPSO: a method for crystal structure prediction
• Crystal Graph Convolutional Neural Networks for an Accurate and Interpretable Prediction of Material Properties
• Ab initio Random Structure Searching
• Comparing molecules and solids across structural and alchemical space
• Evolutionary search for novel superhard materials: Methodology and applications to forms of carbon and TiO2
• Data-driven learning of total and local energies in elemental boron
• Optimizing the Latent Space of Generative Networks
• Generative Models for Automatic Chemical Design
• Data-Driven Approach to Encoding and Decoding 3-D Crystal Structures

Cited by in corpus (14)

• Recent Advances and Applications of Deep Learning Methods in Materials Science
• An invertible crystallographic representation for general inverse design of inorganic crystals with targeted properties
• High-throughput discovery of novel cubic crystal materials using deep generative neural networks
• Data-driven discovery of novel 2D materials by deep generative models
• Crystal Diffusion Variational Autoencoder for Periodic Material Generation
• Deep learning generative model for crystal structure prediction
• Inverse Design of Next-generation Superconductors Using Data-driven Deep Generative Models
• Generative diffusion model for surface structure discovery
• Materials Discovery with Extreme Properties via Reinforcement Learning-Guided Combinatorial Chemistry
• Inorganic Crystal Structure Prototype Database based on Unsupervised Learning of Local Atomic Environments
• Self-Supervised Generative Models for Crystal Structures
• Dismai-Bench: Benchmarking and designing generative models using disordered materials and interfaces
• Neural Structure Fields with Application to Crystal Structure Autoencoders
• A generative machine learning model for designing metal hydrides applied to hydrogen storage