Approaches for Uncertainty Quantification of AI-predicted Material Properties: A Comparison
This work addresses the need for reliable uncertainty quantification in material science predictions, offering incremental improvements by comparing existing methods for a domain-specific application.
The paper tackled the problem of quantifying uncertainty in AI-predicted material properties by comparing three easy-to-implement methods—Quantile, direct machine learning of intervals, and Ensemble—across ten material properties, finding that these approaches provide practical ways to estimate prediction intervals.
The development of large databases of material properties, together with the availability of powerful computers, has allowed machine learning (ML) modeling to become a widely used tool for predicting material performances. While confidence intervals are commonly reported for such ML models, prediction intervals, i.e., the uncertainty on each prediction, are not as frequently available. Here, we investigate three easy-to-implement approaches to determine such individual uncertainty, comparing them across ten ML quantities spanning energetics, mechanical, electronic, optical, and spectral properties. Specifically, we focused on the Quantile approach, the direct machine learning of the prediction intervals and Ensemble methods.