| Autor: |
Duo Zhang, Hangrui Bi, Fu-Zhi Dai, Wanrun Jiang, Xinzijian Liu, Linfeng Zhang, Han Wang |
| Jazyk: |
angličtina |
| Rok vydání: |
2024 |
| Předmět: |
|
| Zdroj: |
npj Computational Materials, Vol 10, Iss 1, Pp 1-8 (2024) |
| Druh dokumentu: |
article |
| ISSN: |
2057-3960 |
| DOI: |
10.1038/s41524-024-01278-7 |
| Popis: |
Abstract Machine learning-assisted modeling of the inter-atomic potential energy surface (PES) is revolutionizing the field of molecular simulation. With the accumulation of high-quality electronic structure data, a model that can be pretrained on all available data and finetuned on downstream tasks with a small additional effort would bring the field to a new stage. Here we propose DPA-1, a Deep Potential model with a gated attention mechanism, which is highly effective for representing the conformation and chemical spaces of atomic systems and learning the PES. We tested DPA-1 on a number of systems and observed superior performance compared with existing benchmarks. When pretrained on large-scale datasets containing 56 elements, DPA-1 can be successfully applied to various downstream tasks with a great improvement of sample efficiency. Surprisingly, for different elements, the learned type embedding parameters form a s p i r a l in the latent space and have a natural correspondence with their positions on the periodic table, showing interesting interpretability of the pretrained DPA-1 model. |
| Databáze: |
Directory of Open Access Journals |
| Externí odkaz: |
|
Full text from SpringerLink