Report
Uncertainty-biased molecular dynamics for learning uniformly accurate interatomic potentials
| العنوان: | Uncertainty-biased molecular dynamics for learning uniformly accurate interatomic potentials |
|---|---|
| المؤلفون: | Zaverkin, Viktor, Holzmüller, David, Christiansen, Henrik, Errica, Federico, Alesiani, Francesco, Takamoto, Makoto, Niepert, Mathias, Kästner, Johannes |
| المصدر: | npj Comput. Mater. 10, 83 (2024) |
| سنة النشر: | 2023 |
| المجموعة: | Condensed Matter Physics (Other) Statistics |
| مصطلحات موضوعية: | Physics - Computational Physics, Condensed Matter - Materials Science, Statistics - Machine Learning |
| الوصف: | Efficiently creating a concise but comprehensive data set for training machine-learned interatomic potentials (MLIPs) is an under-explored problem. Active learning, which uses biased or unbiased molecular dynamics (MD) to generate candidate pools, aims to address this objective. Existing biased and unbiased MD-simulation methods, however, are prone to miss either rare events or extrapolative regions -- areas of the configurational space where unreliable predictions are made. This work demonstrates that MD, when biased by the MLIP's energy uncertainty, simultaneously captures extrapolative regions and rare events, which is crucial for developing uniformly accurate MLIPs. Furthermore, exploiting automatic differentiation, we enhance bias-forces-driven MD with the concept of bias stress. We employ calibrated gradient-based uncertainties to yield MLIPs with similar or, sometimes, better accuracy than ensemble-based methods at a lower computational cost. Finally, we apply uncertainty-biased MD to alanine dipeptide and MIL-53(Al), generating MLIPs that represent both configurational spaces more accurately than models trained with conventional MD. |
| نوع الوثيقة: | Working Paper |
| DOI: | 10.1038/s41524-024-01254-1 |
| URL الوصول: | http://arxiv.org/abs/2312.01416 |
| رقم الانضمام: | edsarx.2312.01416 |
| قاعدة البيانات: | arXiv |
| DOI: | 10.1038/s41524-024-01254-1 |
|---|