| Abstract Scope |
In this talk, we propose a novel microstructure-sensitive Bayesian optimization (BO) framework designed to enhance the efficiency of materials discovery by explicitly incorporating microstructural information. Traditional materials design approaches often focus exclusively on direct chemistry-process-property relationships, overlooking the critical role of microstructures. To address this limitation, our framework integrates microstructural descriptors as latent variables, enabling the construction of a comprehensive process-structure-property mapping that improves both predictive accuracy and optimization outcomes. To demonstrate this framework, we deploy it to investigate the chemistry-processing-structure-property space in FCC High Entropy Alloys (HEAs), in which we explicitly exploit recrystallization and the corresponding modification of polycrystalline microstructure to tune multiple mechanical properties at once. Our framework uses high-throughput CALPHAD and DFT simulations as well as synthesis, processing, and characterization/testing, and accelerated design is demonstrated through three iterative discovery cycles. |