AUGUR, A flexible and efficient optimization algorithm for identification of optimal adsorption sites
This work addresses the challenge of computationally expensive adsorption site optimization for researchers in materials science and chemistry, offering a more efficient and flexible method.
The paper tackles the problem of identifying optimal adsorption sites for molecules by proposing AUGUR, a flexible optimization pipeline that combines graph neural networks and Gaussian processes for efficient, symmetry-aware prediction with uncertainty quantification. It achieves this with far fewer iterations than state-of-the-art approaches, enabling energy prediction for large, complex clusters using models trained on smaller systems.
In this paper, we propose a novel flexible optimization pipeline for determining the optimal adsorption sites, named AUGUR (Aware of Uncertainty Graph Unit Regression). Our model combines graph neural networks and Gaussian processes to create a flexible, efficient, symmetry-aware, translation, and rotation-invariant predictor with inbuilt uncertainty quantification. This predictor is then used as a surrogate for a data-efficient Bayesian Optimization scheme to determine the optimal adsorption positions. This pipeline determines the optimal position of large and complicated clusters with far fewer iterations than current state-of-the-art approaches. Further, it does not rely on hand-crafted features and can be seamlessly employed on any molecule without any alterations. Additionally, the pooling properties of graphs allow for the processing of molecules of different sizes by the same model. This allows the energy prediction of computationally demanding systems by a model trained on comparatively smaller and less expensive ones