Gradient-based grand canonical optimization enabled by graph neural networks with fractional atomic existence
This work addresses materials science challenges by enabling more efficient structure optimization, though it appears incremental as it builds on existing graph neural network methods.
The authors tackled the problem of optimizing atomic structures by extending graph neural networks with a continuous variable for fractional atomic existence, enabling gradient-based grand canonical optimization, and demonstrated its capabilities on a Cu(110) surface oxide.
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.