A Deep-Learning Potential for Crystalline and Amorphous Li-Si Alloys
N Xu and Y Shi and Y He and Q Shao, JOURNAL OF PHYSICAL CHEMISTRY C, 124, 16278-16288 (2020).
This work investigates the ability of the deeplearning potential (DP) to describe structural, dynamic and energetic properties of crystalline and amorphous Li-Si alloys. Li-Si systems play an important role in the development of high-energy lithium ion batteries. One challenge in simulating Li-Si systems is to balance the proper description of complex Li-Si interactions and the system size. Molecular simulations implemented with DP provide a promising alternative to achieve this balance and enable us to investigate the fine details of Li-Si systems that the classical force fields cannot offer. We develop a DP for Li-Si systems with Li/Si ratio ranging from 0 to 4.2 based on a vast data set generated using the quantum mechanical calculations in an active learning procedure. Then we investigate the structural and dynamic properties of several crystalline and amorphous Li-Si systems using this developed DP. The DP can predict bulk densities, the radial distribution functions, and diffusivity of Li in amorphous Li-Si systems with an accuracy close to quantum mechanical calculations with the benefit of 20 times faster speed than the ab initio molecular dynamics simulations. Several issues related to the development of DP are also discussed.
Return to Publications page