Model Accuracy and Data Heterogeneity Shape Uncertainty Quantification in Machine Learning Interatomic Potentials
This work addresses uncertainty quantification for researchers developing machine learning interatomic potentials, offering incremental improvements through a novel clustering method to handle data heterogeneity.
The study tackled the challenge of reliable uncertainty quantification in machine learning interatomic potentials by investigating ensemble learning and D-optimality, revealing that higher model accuracy improves uncertainty correlation with errors and novelty detection, while introducing clustering-enhanced local D-optimality substantially improves novelty detection in heterogeneous datasets.
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.