Model Accuracy and Data Heterogeneity Shape Uncertainty Quantification in Machine Learning Interatomic Potentials
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911093200257024 |
|---|---|
| author | Shuang, Fei Wei, Zixiong Liu, Kai Gao, Wei Dey, Poulumi |
| author_facet | Shuang, Fei Wei, Zixiong Liu, Kai Gao, Wei Dey, Poulumi |
| contents | Machine learning interatomic potentials (MLIPs) enable accurate atomistic modelling, but reliable uncertainty quantification (UQ) remains elusive. In this study, we investigate two UQ strategies, ensemble learning and D-optimality, within the atomic cluster expansion framework. It is revealed that higher model accuracy strengthens the correlation between predicted uncertainties and actual errors and improves novelty detection, with D-optimality yielding more conservative estimates. Both methods deliver well calibrated uncertainties on homogeneous training sets, yet they underpredict errors and exhibit reduced novelty sensitivity on heterogeneous datasets. To address this limitation, we introduce clustering-enhanced local D-optimality, which partitions configuration space into clusters during training and applies D-optimality within each cluster. This approach substantially improves the detection of novel atomic environments in heterogeneous datasets. Our findings clarify the roles of model fidelity and data heterogeneity in UQ performance and provide a practical route to robust active learning and adaptive sampling strategies for MLIP development. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_03405 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Model Accuracy and Data Heterogeneity Shape Uncertainty Quantification in Machine Learning Interatomic Potentials Shuang, Fei Wei, Zixiong Liu, Kai Gao, Wei Dey, Poulumi Materials Science Machine Learning Machine learning interatomic potentials (MLIPs) enable accurate atomistic modelling, but reliable uncertainty quantification (UQ) remains elusive. In this study, we investigate two UQ strategies, ensemble learning and D-optimality, within the atomic cluster expansion framework. It is revealed that higher model accuracy strengthens the correlation between predicted uncertainties and actual errors and improves novelty detection, with D-optimality yielding more conservative estimates. Both methods deliver well calibrated uncertainties on homogeneous training sets, yet they underpredict errors and exhibit reduced novelty sensitivity on heterogeneous datasets. To address this limitation, we introduce clustering-enhanced local D-optimality, which partitions configuration space into clusters during training and applies D-optimality within each cluster. This approach substantially improves the detection of novel atomic environments in heterogeneous datasets. Our findings clarify the roles of model fidelity and data heterogeneity in UQ performance and provide a practical route to robust active learning and adaptive sampling strategies for MLIP development. |
| title | Model Accuracy and Data Heterogeneity Shape Uncertainty Quantification in Machine Learning Interatomic Potentials |
| topic | Materials Science Machine Learning |
| url | https://arxiv.org/abs/2508.03405 |