Data-Driven Approach to Design/Discover Intercalating Ions and Layered Materials for Metal-Ion Batteries

This study utilizes machine learning methods to find alternative 2D materials and intercalating ions beyond Li for metal-ion batteries with high power efficiencies. A dataset is constructed by performing first-principles density functional theory (DFT) simulations to estimate voltages by calculating the binding energies of 6 metal ions (Li, Na, K, Mg, Ca, and Al) at various adsorption sites on a set of 165 different 2D materials. A gradient boosting-based regression model is trained on the dataset to predict the binding energies with unprecedented accuracy. The generated dataset also provides insight into structural accommodations that can be expected upon ion intercalation on various 2D materials. Additionally, a binding energy and structural deformation-based classification model is developed to screen for novel anode materials compatible with various intercalating ions. Further, outlier analysis is performed to identify elemental factors leading to extremely high and low values for binding energies. Individual models trained on different classes of 2D materials further provide insights into differences in ion binding across materials classes. Using data-driven tools, the work provides crucial insights into the interplay between atomistic features that determine ion binding on 2D materials.