Gradient-based grand canonical optimization enabled by graph neural networks with fractional atomic existence

Abstract

Machine learning interatomic potentials have become an indispensable tool for materials science, enabling the study of larger systems and longer timescales. State-of-the-art models are generally graph neural networks that employ message passing to iteratively update atomic embeddings that are ultimately used for predicting properties. In this work we extend the message passing formalism with the inclusion of a continuous variable that accounts for fractional atomic existence. This allows us to calculate the gradient of the Gibbs free energy with respect to both the Cartesian coordinates of atoms and their existence. Using this we propose a gradient-based grand canonical optimization method and document its capabilities for a Cu(110) surface oxide.

References in corpus (25)

• Gaussian Approximation Potentials: the accuracy of quantum mechanics, without the electrons
• Crystal Graph Convolutional Neural Networks for an Accurate and Interpretable Prediction of Material Properties
• E(3)-Equivariant Graph Neural Networks for Data-Efficient and Accurate Interatomic Potentials
• Two-dimensional materials from high-throughput computational exfoliation of experimentally known compounds
• Ab initio Random Structure Searching
• PhysNet: A Neural Network for Predicting Energies, Forces, Dipole Moments and Partial Charges
• GPAW: An open Python package for electronic-structure calculations
• Scalable Parallel Algorithm for Graph Neural Network Interatomic Potentials in Molecular Dynamics Simulations
• Efficient global structure optimization with a machine learned surrogate model
• Efficient Bayesian Inference of Atomistic Structure in Complex Functional Materials
• Data-driven discovery of novel 2D materials by deep generative models
• Accelerating CALYPSO Structure Prediction by Data-driven Learning of Potential Energy Surface
• IrO2 Surface Complexions Identified Through Machine Learning and Surface Investigations
• Uncertainty-biased molecular dynamics for learning uniformly accurate interatomic potentials
• Global optimization of atomic structures with gradient-enhanced Gaussian process regression
• Machine Learning and Data-Driven Methods in Computational Surface and Interface Science
• Hyperspatial optimisation of structures
• Generative diffusion model for surface structure discovery
• Atomic structure optimization with machine-learning enabled interpolation between chemical elements
• Generating candidates in global optimization algorithms using complementary energy landscapes
• Cascading symmetry constraint during machine learning-enabled structural search for sulfur induced Cu(111)-$(\sqrt{43}\times \sqrt{43})$ surface reconstruction
• Machine-learning enabled optimization of atomic structures using atoms with fractional existence
• $\Delta$-model correction of Foundation Model based on the models own understanding
• Accelerating structure search using atomistic graph-based classifiers
• RAFFLE: Active learning accelerated interface structure prediction