Rational design of chemically complex metallic glasses by hybrid modeling guided machine learning

Abstract The compositional design of metallic glasses (MGs) is a long-standing issue in materials science and engineering. However, traditional experimental approaches based on empirical rules are time consuming with low efficiency. In this work, we successfully developed hybrid machine learning (ML) model to address fundamental database containing ~5000 different compositions (either bulk or ribbon) reported since 1960s. Unlike the prior works relying parameters for featurization data, designed modeling guided data descriptors line recent theoretical models amorphization chemically complex alloys development classification-regression ML algorithms. Our was validated both numerically experimentally. Most importantly, it enabled discovery MGs through ML-aided deep search multitude quaternary scenery alloy compositions. computational framework herein established expected accelerate MG expand their applications by probing multi-dimensional space that has never been explored before.