Efficient Estimation of Material Property Curves and Surfaces via Active Learning

TL;DR

This paper compares active learning strategies for efficiently estimating material property curves and surfaces, demonstrating that directed exploration guided by maximum variance generally converges faster, with performance depending on data and noise conditions.

Contribution

It evaluates various active learning strategies for material property estimation, highlighting the effectiveness of maximum variance exploration and discussing utility function choices based on data characteristics.

Findings

Maximum variance exploration converges faster in several cases.

Trade-off methods with exploitation can perform equally well or better.

Performance depends on data distribution, noise, and experimental budget.

Abstract

The relationship between material properties and independent variables such as temperature, external field or time, is usually represented by a curve or surface in a multi-dimensional space. Determining such a curve or surface requires a series of experiments or calculations which are often time and cost consuming. A general strategy uses an appropriate utility function to sample the space to recommend the next optimal experiment or calculation within an active learning loop. However, knowing what the optimal sampling strategy to use to minimize the number of experiments is an outstanding problem. We compare a number of strategies based on directed exploration on several materials problems of varying complexity using a Kriging based model. These include one dimensional curves such as the fatigue life curve for 304L stainless steel and the Liquidus line of the Fe-C phase diagram, surfaces such as the Hartmann 3 function in 3D space and the fitted intermolecular potential for Ar-SH, and a four dimensional data set of experimental measurements for BaTiO3 based ceramics. We also consider the effects of experimental noise on the Hartmann 3 function. We find that directed exploration guided by maximum variance provides better performance overall, converging faster across several data sets. However, for certain problems, the trade-off methods incorporating exploitation can perform at least as well, if not better than maximum variance. Thus, we discuss how the choice of the utility function depends on the distribution of the data, the model performance and uncertainties, additive noise as well as the budget.