Hybrid Machine Learning-Enabled Potential Energy Model for Atomistic Simulation of Lithium Intercalation into Graphite from Plating to Overlithiation.

Graphite is one of the most widely used negative electrode materials for lithium ion batteries (LIBs). However, because of the rapid growth of demands pursuing higher energy density and charging rates, comprehensive insights into the lithium intercalation and plating processes are critical for further boosting the potential of graphite electrodes. Herein, by utilizing the dihedral-angle-corrected registry-dependent potential (DRIP) (Wen et al., , , 235404), the Ziegler-Biersack-Littmark (ZBL) potential (Ziegler and Biersack, ; 1985, pp 93-129), and the machine learning-based spectral neighbor analysis (SNAP) potential (Thompson et al., , , 316-330), we have successfully trained a hybrid machine learning-enabled potential energy model capable of simulating a wide spectrum of lithium intercalation scenario from plating to overlithiation. Our extensive atomistic simulations reveal the trapping of intercalated lithium atoms close to the graphite edges due to high hopping barriers, resulting in lithium plating. Furthermore, we report a stable dense graphite intercalation compound (GIC) LiC with a theoretical capacity of 558 mAh/g, wherein lithium atoms occupy alternating upper/lower graphene hollow sites with a nearest Li-Li distance of 2.8 Å. Surprisingly, following the same lithium insertion manner would allow the nearest Li-Li distance to be retained until the capacity reaches 845.2 mAh/g, corresponding to a GIC of LiC. Hence, the present study demonstrates that the hybrid machine learning approach could further extend the scope of machine learning energy models, allowing us to investigate the lithium intercalation into graphite over a wide range of intercalation capacity to unveil the underlying mechanisms of lithium plating, diffusion, and discovery of new dense GICs for advanced LIBs with high charging rates and high energy densities.