Evidential Deep Learning for Interatomic Potentials
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_ | 1866915244353257472 |
|---|---|
| author | Xu, Han Cui, Taoyong Tang, Chenyu Ma, Jinzhe Zhou, Dongzhan Li, Yuqiang Gao, Xiang Gong, Xingao Ouyang, Wanli Zhang, Shufei Su, Mao |
| author_facet | Xu, Han Cui, Taoyong Tang, Chenyu Ma, Jinzhe Zhou, Dongzhan Li, Yuqiang Gao, Xiang Gong, Xingao Ouyang, Wanli Zhang, Shufei Su, Mao |
| contents | Machine learning interatomic potentials (MLIPs) have been widely used to facilitate large-scale molecular simulations with accuracy comparable to ab initio methods. In practice, MLIP-based molecular simulations often encounter the issue of collapse due to reduced prediction accuracy for out-of-distribution (OOD) data. Addressing this issue requires enriching the training dataset through active learning, where uncertainty serves as a critical indicator for identifying and collecting OOD data. However, existing uncertainty quantification (UQ) methods tend to involve either expensive computations or compromise prediction accuracy. In this work, we introduce evidential deep learning for interatomic potentials (eIP) with a physics-inspired design. Our experiments indicate that eIP provides reliable UQ results without significant computational overhead or decreased prediction accuracy, consistently outperforming other UQ methods across a variety of datasets. Furthermore, we demonstrate the applications of eIP in exploring diverse atomic configurations, using examples including water and universal potentials. These results highlight the potential of eIP as a robust and efficient alternative for UQ in molecular simulations. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_13994 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Evidential Deep Learning for Interatomic Potentials Xu, Han Cui, Taoyong Tang, Chenyu Ma, Jinzhe Zhou, Dongzhan Li, Yuqiang Gao, Xiang Gong, Xingao Ouyang, Wanli Zhang, Shufei Su, Mao Computational Physics Machine learning interatomic potentials (MLIPs) have been widely used to facilitate large-scale molecular simulations with accuracy comparable to ab initio methods. In practice, MLIP-based molecular simulations often encounter the issue of collapse due to reduced prediction accuracy for out-of-distribution (OOD) data. Addressing this issue requires enriching the training dataset through active learning, where uncertainty serves as a critical indicator for identifying and collecting OOD data. However, existing uncertainty quantification (UQ) methods tend to involve either expensive computations or compromise prediction accuracy. In this work, we introduce evidential deep learning for interatomic potentials (eIP) with a physics-inspired design. Our experiments indicate that eIP provides reliable UQ results without significant computational overhead or decreased prediction accuracy, consistently outperforming other UQ methods across a variety of datasets. Furthermore, we demonstrate the applications of eIP in exploring diverse atomic configurations, using examples including water and universal potentials. These results highlight the potential of eIP as a robust and efficient alternative for UQ in molecular simulations. |
| title | Evidential Deep Learning for Interatomic Potentials |
| topic | Computational Physics |
| url | https://arxiv.org/abs/2407.13994 |