Global optimization in the discrete and variable-dimension conformational space: The case of crystal with the strongest atomic cohesion

Abstract

We introduce a computational method to optimize target physical properties in the full configuration space regarding atomic composition, chemical stoichiometry, and crystal structure. The approach combines the universal potential of the crystal graph neural network and Bayesian optimization. The proposed approach effectively obtains the crystal structure with the strongest atomic cohesion from all possible crystals. Several new crystals with high atomic cohesion are identified and confirmed by density functional theory for thermodynamic and dynamic stability. Our method introduces a novel approach to inverse materials design with additional functional properties for practical applications.

References in corpus (12)

• VASPKIT: A User-friendly Interface Facilitating High-throughput Computing and Analysis Using VASP Code
• CALYPSO: a method for crystal structure prediction
• A Universal Graph Deep Learning Interatomic Potential for the Periodic Table
• Towards Universal Neural Network Potential for Material Discovery Applicable to Arbitrary Combination of 45 Elements
• Machine Learning Energies of 2 M Elpasolite (ABC${}_2$D${}_6$) Crystals
• An invertible crystallographic representation for general inverse design of inorganic crystals with targeted properties
• A novel superhard tungsten nitride predicted by machine-learning accelerated crystal structure searching
• Towards Direct-Gap Silicon Phases by the Inverse Band Structure Design Approach
• Unified Graph Neural Network Force-field for the Periodic Table
• Machine Learning and Evolutionary Prediction of Superhard B-C-N Compounds
• Inverse Design of Next-generation Superconductors Using Data-driven Deep Generative Models
• Understanding the fragile-to-strong transition in silica from microscopic dynamics