Accelerated Discovery of Ternary Gold Alloy Materials with Low Resistivity via an Interpretable Machine Learning Strategy

New ternary gold alloys with low resistivities (rho) were screened out via an interpretable machine learning strategy by using the support vector regression (SVR) model integrated with SHAP analysis. The correlation coefficient (R) and the root mean square error (RMSE) of test set were 0.876 and 0.302, respectively, indicating the strong generalization ability of the model. The average rho of top 10 candidates was 1.22x10(-7) Omega m, which was 41% lower than the known minimum of 2.08x10(-7) Omega m. The outputs of SVR model were analyzed with the critical SHAP values including first ionization energy of C-site (584 kJ.mol(-1)), electronegativity of C-site (1.72) and the second ionization energy of B-site (1135 kJ . mol(-1)), respectively. Moreover, an online web server was developed to share the model at http://materials-data-mining.com/onlineservers/wxdaualloy.

Automated summary

New ternary gold alloys with low resistivities were discovered using a interpretable machine learning strategy, with a strong generalization ability of the model. The outputs of the model were analyzed with critical SHAP values and an online web server was developed to share the model.