A neural network potential with self-trained atomic fingerprints: a test with the mW water potential

Abstract

We present a neural network (NN) potential based on a new set of atomic fingerprints built upon two- and three-body contributions that probe distances and local orientational order respectively. Compared to existing NN potentials, the atomic fingerprints depend on a small set of tuneable parameters which are trained together with the neural network weights. To tackle the simultaneous training of the atomic fingerprint parameters and neural network weights we adopt an annealing protocol that progressively cycles the learning rate, significantly improving the accuracy of the NN potential. We test the performance of the network potential against the mW model of water, which is a classical three-body potential that well captures the anomalies of the liquid phase. Trained on just three state points, the NN potential is able to reproduce the mW model in a very wide range of densities and temperatures, from negative pressures to several GPa, capturing the transition from an open random tetrahedral network to a dense interpenetrated network. The NN potential also reproduces very well properties for which it was not explicitly trained, such as dynamical properties and the structure of the stable crystalline phases of mW.

14 pages, 11 figures

References in corpus (9)

• ANI-1: An extensible neural network potential with DFT accuracy at force field computational cost
• ANI-1: A data set of 20M off-equilibrium DFT calculations for organic molecules
• Machine learning force fields and coarse-grained variables in molecular dynamics: application to materials and biological systems
• Recursive evaluation and iterative contraction of $N$-body equivariant features
• Quantum-mechanical exploration of the phase diagram of water
• The physics of Empty Liquids: from Patchy particles to Water
• Roles of liquid structural ordering in glass transition, crystallization, and water's anomalies
• Machine-learning effective many-body potentials for anisotropic particles using orientation-dependent symmetry functions
• Modeling of many-body interactions between elastic spheres through symmetry functions