Compositional design and phase formation capability of high-entropy rare-earth disilicates from machine learning and decision fusion

Abstract A key strategy for designing environmental barrier coatings is to incorporate multiple rare-earth (RE) components into β- and γ-RE 2 Si 2 O 7 to achieve multifunctional performance optimization. However, the polymorphic phase presents significant challenges for the design of multicomponent RE disilicates. Here, employing decision fusion, a machine learning (ML) method is crafted to identify multicomponent RE disilicates, showcasing notable accuracy in prediction. The well-trained ML models evaluated the phase formation capability of 117 (RE1 0.25 RE2 0.25 Yb 0.25 Lu 0.25 ) 2 Si 2 O 7 and (RE1 1/6 RE2 1/6 RE3 1/6 Gd 1/6 Yb 1/6 Lu 1/6 ) 2 Si 2 O 7, which are unreported in experiments and validated by first-principles calculations. Utilizing model visualization, essential factors governing the formation of (RE1 0.25 RE2 0.25 Yb 0.25 Lu 0.25 ) 2 Si 2 O 7 are pinpointed, including the average radius of RE 3+ and variations in different RE 3+ combinations. On the other hand, (RE1 1/6 RE2 1/6 RE3 1/6 Gd 1/6 Yb 1/6 Lu 1/6 ) 2 Si 2 O 7 must take into account the average mass and the electronegativity deviation of RE 3+ . This work combines material-oriented ML methods with formation mechanisms of multicomponent RE disilicates, enabling the efficient design of superior materials with exceptional properties for the application of environmental barrier coatings.