Interatomic machine learning potentials for aluminium: application to solidification phenomena

In studying solidification process by simulations on the atomic scale, the modeling of crystal nucleation or amorphisation requires the construction of interatomic interactions that are able to reproduce the properties of both the solid and the liquid states. Taking into account rare nucleation events or structural relaxation under deep undercooling conditions requires much larger length scales and longer time scales than those achievable by \textit{ab initio} molecular dynamics (AIMD). This problem is addressed by means of classical MD simulations using a well established high dimensional neural network potential trained on a relevant set of configurations generated by AIMD. Our dataset contains various crystalline structures and liquid states at different pressures, including their time fluctuations in a wide range of temperatures considering only their energy labels. Applied to elemental aluminium, the resulting potential is shown to be efficient to reproduce the basic structural, dynamics and thermodynamic quantities in the liquid and undercooled states without the need to include neither explicitly the forces nor all kind of configurations in the training procedure. The early stage of crystallization is further investigated on a much larger scale with one million atoms, allowing us to unravel features of the homogeneous nucleation mechanisms in the fcc phase at ambient pressure as well as in the bcc phase at high pressure with unprecedented accuracy close to the \textit{ab initio} one. In both case, a single step nucleation process is observed.