AUGUR, A flexible and efficient optimization algorithm for identification of optimal adsorption sites
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866917785333923840 |
|---|---|
| author | Kouroudis, Ioannis Poonam Misciaci, Neel Mayr, Felix Müller, Leon Gu, Zhaosu Gagliardi, Alessio |
| author_facet | Kouroudis, Ioannis Poonam Misciaci, Neel Mayr, Felix Müller, Leon Gu, Zhaosu Gagliardi, Alessio |
| contents | 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 |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_16204 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | AUGUR, A flexible and efficient optimization algorithm for identification of optimal adsorption sites Kouroudis, Ioannis Poonam Misciaci, Neel Mayr, Felix Müller, Leon Gu, Zhaosu Gagliardi, Alessio Chemical Physics Machine Learning 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 |
| title | AUGUR, A flexible and efficient optimization algorithm for identification of optimal adsorption sites |
| topic | Chemical Physics Machine Learning |
| url | https://arxiv.org/abs/2409.16204 |