Exploring effective charge in electromigration using machine learning

The effective charge of an element is a parameter characterizing the electromigration effect, which can determine the reliability of interconnection in electronic technologies. In this work, machine learning approaches were employed to model the effective charge (z^∗) as a linear function of physically meaningful elemental properties. Average fivefold (leave-out-alloy-group) cross-validation yielded root-mean-square-error divided by whole data set standard deviation (RMSE/σ) values of 0.37 ± 0.01 (0.22 ± 0.18), respectively, and R² values of 0.86. Extrapolation to z∗ of totally new alloys showed limited but potentially useful predictive ability. The model was used in predicting z∗ for technologically relevant host-impurity pairs.