Yinping Zeng

Abstract Machine learning is widely used to accelerate materials design, but its performance remains limited in small-data scenarios, reducing effectiveness in guiding novel materials development. Here, we developed a novel representation transfer framework based on the Calculation of Phase Diagrams (CALPHAD) method to address the challenge. By integrating CALPHAD with feature engineering, the thermodynamics-informed descriptors related to strength and ductility were constructed and selected.

CONFLICT OF INTEREST STATEMENT The authors declare no conflicts of interest. Supporting Information REFERENCES 1, , . Principles of modern chemistry. Boston, MA: Cengage Learning; 2016. 2. Scientific and technological challenges of industrial glass melting. Solid State Ionics. 1998; 105(1-4): 265–270. https://doi.org/10.1016/S0167-2738(97)00478-5 3, , . Lateral hardness and the scratch resistance of glasses in the Na2O–CaO–SiO2 system. J Non-Cryst Solids. 2018; 492: 94–101.