Molecular Dynamics with NeQUIP

#=========================================================================

This tutorial introduces a Machine Learning Interatomic Potential (MLP) model called NequIP.

This is the tutorial for 22-water cluster in a 40 ų periodic box. The steps to build MLP requires following stages:

1. Data generation          [00.data]
2. Training                 [01.train]
3. Molecular Dynamics       [02.lmp]

For data generation, we will use the Quantum Espresso package.

Here, I will not explain that, how to generate the initial configuration. However, there are several ways to do that. The easiest way is to perform a classical MD simulation and then take the (M) random configurations and perform the ab-initio calculations to get the potential energy and corresponding forces (in this case, we will be using Quantum Espresso).

The initial 500 configurations (input and output) are stored in the QE_In_File and QE_Out_File folders inside the 00.data directory. (You can re-run the inputs if you want).

The underlying concept and details are given in this article [https://www.nature.com/articles/s41467-022-29939-5].