Saved in:
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2512.09169 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909005943668736 |
|---|---|
| author | Cavignac, Théo Schmidt, Jonathan De Breuck, Pierre-Paul Loew, Antoine Cerqueira, Tiago F. T. Wang, Hai-Chen Bochkarev, Anton Lysogorskiy, Yury Romero, Aldo H. Drautz, Ralf Botti, Silvana Marques, Miguel A. L. |
| author_facet | Cavignac, Théo Schmidt, Jonathan De Breuck, Pierre-Paul Loew, Antoine Cerqueira, Tiago F. T. Wang, Hai-Chen Bochkarev, Anton Lysogorskiy, Yury Romero, Aldo H. Drautz, Ralf Botti, Silvana Marques, Miguel A. L. |
| contents | We present a novel multi-stage workflow for computational materials discovery that achieves a 99% success rate in identifying compounds within 100 meV/atom of thermodynamic stability, with a threefold improvement over previous approaches. By combining the Matra-Genoa generative model, Orb-v2 universal machine learning interatomic potential, and ALIGNN graph neural network for energy prediction, we generated 119 million candidate structures and added 1.3 million DFT-validated compounds to the ALEXANDRIA database, including 74 thousand new stable materials. The expanded ALEXANDRIA database now contains 5.8 million structures with 175 thousand compounds on the convex hull. Predicted structural disorder rates (37-43%) match experimental databases, unlike other recent AI-generated datasets. Analysis reveals fundamental patterns in space group distributions, coordination environments, and phase stability networks, including sub-linear scaling of convex hull connectivity. We release the complete dataset, including sAlex25 with 14 million out-of-equilibrium structures containing forces and stresses for training universal force fields. We demonstrate that fine-tuning a GRACE model on this data improves benchmark accuracy. All data, models, and workflows are freely available under Creative Commons licenses. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_09169 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | AI-Driven Expansion and Application of the Alexandria Database Cavignac, Théo Schmidt, Jonathan De Breuck, Pierre-Paul Loew, Antoine Cerqueira, Tiago F. T. Wang, Hai-Chen Bochkarev, Anton Lysogorskiy, Yury Romero, Aldo H. Drautz, Ralf Botti, Silvana Marques, Miguel A. L. Materials Science Artificial Intelligence We present a novel multi-stage workflow for computational materials discovery that achieves a 99% success rate in identifying compounds within 100 meV/atom of thermodynamic stability, with a threefold improvement over previous approaches. By combining the Matra-Genoa generative model, Orb-v2 universal machine learning interatomic potential, and ALIGNN graph neural network for energy prediction, we generated 119 million candidate structures and added 1.3 million DFT-validated compounds to the ALEXANDRIA database, including 74 thousand new stable materials. The expanded ALEXANDRIA database now contains 5.8 million structures with 175 thousand compounds on the convex hull. Predicted structural disorder rates (37-43%) match experimental databases, unlike other recent AI-generated datasets. Analysis reveals fundamental patterns in space group distributions, coordination environments, and phase stability networks, including sub-linear scaling of convex hull connectivity. We release the complete dataset, including sAlex25 with 14 million out-of-equilibrium structures containing forces and stresses for training universal force fields. We demonstrate that fine-tuning a GRACE model on this data improves benchmark accuracy. All data, models, and workflows are freely available under Creative Commons licenses. |
| title | AI-Driven Expansion and Application of the Alexandria Database |
| topic | Materials Science Artificial Intelligence |
| url | https://arxiv.org/abs/2512.09169 |