A Physics-Informed Active Learning Framework for Accelerated Materials Discovery

The lack of efficient discovery tools for advanced functional materials is a major bottleneck to enabling future-generation energy, health, and sustainability technologies. One main factor contributing to this inefficiency is the large combinatorial space of materials which is very sparsely observed. Searches of this large combinatorial space are often biased by expert knowledge and clustered close to material configurations that are known to perform well. Moreover, experimental characterization or first principles quantum mechanical calculations of all possible materials are extremely expensive leading to small available data sets. In this talk, we introduce an active learning approach, PAL 2.0, that uses Bayesian optimization to significantly accelerate materials discovery. PAL 2.0 operates in a closed-loop framework, integrating physics-based Gaussian process models with experimental validation. Here we showcase the application of PAL 2.0 for the closed-loop discovery of multi-principal element alloys (MPEAs). MPEAs are often sought after due to their exceptional mechanical properties, such as high hardness, strength, and thermal stability, which make them highly desirable for various applications. However, a significant challenge in the discovery and design of MPEAs lies in the vast and complex compositional space, which is both high-dimensional and sparsely explored. Our PAL 2.0 methodology enables the model to intelligently navigate the compositional space, making informed decisions about the most promising alloy candidates to synthesize and test. Using the PAL 2.0 closed-loop approach, we successfully synthesized 13 new MPEA compositions through a rapid arc-melting process. Among these, we identified two alloys with exceptionally high Vickers hardness values of 1269 and 1263, far exceeding the hardness values of alloys in the initial training data set. Our study demonstrates the power of PAL 2.0 as a fast, efficient, and scalable tool for the discovery of materials with optimal properties. This work not only accelerates the development of high-performance MPEAs but also offers a pathway for exploring other complex, high-dimensional material spaces, paving the way for future advancements in materials science.