Machine learning supported annealing for prediction of grand canonical crystal structures

2024/08/07 by Yannick Couzinié, Couzinie, Yannick, Yuya Seki +11 · 8 citations
Materials Science · #Computational Physics (physics.comp-ph) #FOS: Physical sciences #Machine Learning in Materials Science #Materials Science (cond-mat.mtrl-sci)

paper · pdf · doi:10.48550/arxiv.2408.03556

openalex publication_date 2024/08/07 · openalex created_date 2024/11/02 · openalex updated_date 2026/07/28

Abstract

This study investigates the application of Factorization Machines with Quantum Annealing (FMQA) to address the crystal structure problem (CSP) in materials science. FMQA is a black-box optimization algorithm that combines machine learning with annealing machines to find samples to a black-box function that minimize a given loss. The CSP involves determining the optimal arrangement of atoms in a material based on its chemical composition, a critical challenge in materials science. We explore FMQA's ability to efficiently sample optimal crystal configurations by setting the loss function to the energy of the crystal configuration as given by a predefined interatomic potential. Further we investigate how well the energies of the various metastable configurations, or local minima of the potential, are learned by the algorithm. Our investigation reveals FMQA's potential in quick ground state sampling and in recovering relational order between local minima.

Cited by

• Efficient Grand Canonical Global Optimization with On-the-fly-trained Machine-learning Interatomic Potentials
• Extending Sample Persistence Variable Reduction for Constrained Combinatorial Optimization Problems
• Frustration-Enhanced Quantum Annealing Correction Models with Additional Inter-replica Interactions
• Subsampling Factorization Machine Annealing
• Optimization Performance of Factorization Machine with Annealing under Limited Training Data
• Gradient-based grand canonical optimization enabled by graph neural networks with fractional atomic existence
• Black-box optimization using factorization and Ising machines
• Real-Time Black-Box Optimization for Dynamic Discrete Environments Using Embedded Ising Machines

Related

• From Quantum Annealing to Alloy Discovery: Towards Accelerated Design of High-Entropy Alloys
• A machine learning potential-based generative algorithm for on-lattice crystal structure prediction
• Machine-Learning Accelerated Annealing with Fitting-Search Style for Multi-alloy Structure Predictions
• Machine learning based approach for solving atomic structures of nanomaterials combining pair distribution functions with density functional theory
• Self-Optimizing Machine Learning Potential Assisted Automated Workflow for Highly Efficient Complex Systems Material Design