BoltzmaNN: Predicting effective pair potentials and equations of state using neural networks

Abstract

Neural networks (NNs) are employed to predict equations of state from a given isotropic pair potential using the virial expansion of the pressure. The NNs are trained with data from molecular dynamics simulations of monoatomic gases and liquids, sampled in the $NVT$ ensemble at various densities. We find that the NNs provide much more accurate results compared to the analytic low-density limit estimate of the second virial coefficient. Further, we design and train NNs for computing (effective) pair potentials from radial pair distribution functions, $g(r)$, a task which is often performed for inverse design and coarse-graining. Providing the NNs with additional information on the forces greatly improves the accuracy of the predictions, since more correlations are taken into account; the predicted potentials become smoother, are significantly closer to the target potentials, and are more transferable as a result.

References in corpus (13)

• Strong scaling of general-purpose molecular dynamics simulations on GPUs
• Equilibrium cluster phases and low-density arrested disordered states: The role of short-range attraction and long-range repulsion
• Extended corresponding-states behavior for particles with variable range attractions
• Accurate effective pair potentials for polymer solutions
• Beware of density dependent pair potentials
• Non-covalent interactions across organic and biological subsets of chemical space: Physics-based potentials parametrized from machine learning
• Optimized Interactions for Targeted Self-Assembly: Application to Honeycomb Lattice
• Inverse methods for design of soft materials
• Computer Assembly of Cluster-Forming Amphiphilic Dendrimers
• Perspective: Inverse methods for material design
• Inverse Design for Self Assembly via On-the-Fly Optimization
• Accurate structure-based coarse-graining leads to consistent barrier-crossing dynamics
• The Role of Pressure in Inverse Design for Assembly

Cited by in corpus (1)

• Machine Learning of consistent thermodynamic models using automatic differentiation