Machine-learning-potential-driven prediction of high-entropy ceramics with ultra-high melting points

H Meng and YW Liu and HL Yu and L Zhuang and YH Chu, CELL REPORTS PHYSICAL SCIENCE, 6, 102449 (2025).

DOI: 10.1016/j.xcrp.2025.102449

Developing high-entropy ceramics (HECs) with ultra-high melting points (Tm) is crucial for their applications in ultra-high-temperature environments. Here, taking high-entropy diborides (HEBs) as an example, we develop a data-driven method to efficiently explore HEBs with ultra- high Tm via transferable machine-learning-potential-based molecular dynamics (MD). Specifically, a moment tensor potential (MTP) for both equimolar and non-equimolar HEBs is first constructed based on unary and binary diborides. The Tm of HEBs is then accurately simulated through MD simulations based on the constructed MTP, and 24 features are collected simultaneously to enable reliable machine learning training. Five descriptors with the gradient-boosting regression model are derived as the optimal combination for accurate Tm predictions in HEBs with genetic algorithms. Based on our established model, the Tm of 32,563 HEBs are eventually determined, achieving a maximum Tm of 3,765 K in (Ti0.1Zr0.1Hf0.6Ta0.2)B2. The work presents a feasible approach to developing HECs with ultrahigh Tm.

Return to Publications page