Speeding up high-throughput characterization of materials libraries by active learning: autonomous electrical resistance measurements

TL;DR

This paper presents an autonomous active learning algorithm that significantly accelerates high-throughput electrical resistance measurements in materials discovery, reducing measurement time by up to 90% while maintaining high accuracy.

Contribution

The authors develop a Gaussian process-based active learning method for autonomous electrical resistance measurements, enabling efficient exploration of complex materials libraries with outlier handling and dynamic stopping.

Findings

Measurement time reduced by 70-90%.

High accuracy (>90%) maintained despite reduced measurements.

Validated across ten diverse materials libraries.

Abstract

High-throughput experimentation enables efficient search space exploration for the discovery and optimization of new materials. However, large search spaces of, e.g., compositionally complex materials, require decreasing characterization times significantly. Here, an autonomous measurement algorithm was developed, which leverages active learning based on a Gaussian process model capable of iteratively scanning a materials library based on the highest uncertainty. The algorithm is applied to a four-point probe electrical resistance measurement device, frequently used to obtain indications for regions of interest in materials libraries. Ten materials libraries with different complexities of composition and property trends are analyzed to validate the model. By stopping the process before the entire library is characterized and predicting the remaining measurement areas, the measurement efficiency can be improved drastically. As robustness is essential for autonomous measurements, intrinsic outlier handling is built into the model and a dynamic stopping criterion based on the mean predicted covariance is proposed. A measurement time reduction of about 70-90% was observed while still ensuring an accuracy of above 90%.