Equation of state of fluid methane from first principles with machine learning potentials

Abstract

The predictive simulation of molecular liquids requires models that are not only accurate, but computationally efficient enough to handle the large systems and long time scales required for reliable prediction of macroscopic properties. We present a new approach to the systematic approximation of the first-principles potential energy surface (PES) of molecular liquids using the GAP (Gaussian Approximation Potential) framework. The approach allows us to create potentials at several different levels of accuracy in reproducing the true PES, which allows us to test the level of quantum chemistry that is necessary to accurately predict its macroscopic properties. We test the approach by building potentials for liquid methane (CH${}_4$), which is difficult to model from first principles because its behavior is dominated by weak dispersion interactions with a significant many-body component. We find that an accurate, consistent prediction of its bulk density across a wide range of temperature and pressure requires not only many-body dispersion, but also quantum nuclear effects to be modeled accurately.

References in corpus (31)

• Gaussian Approximation Potentials: the accuracy of quantum mechanics, without the electrons
• On representing chemical environments
• ANI-1: An extensible neural network potential with DFT accuracy at force field computational cost
• Comparing molecules and solids across structural and alchemical space
• Machine Learning Unifies the Modelling of Materials and Molecules
• Machine-learning based interatomic potential for amorphous carbon
• Long-range correlation energy calculated from coupled atomic response functions
• Machine Learning of Molecular Electronic Properties in Chemical Compound Space
• How van der Waals interactions determine the unique properties of water
• Nuclear quantum effects enter the mainstream
• Efficient stochastic thermostatting of path integral molecular dynamics
• Alchemical and structural distribution based representation for improved QML
• Achieving DFT accuracy with a machine-learning interatomic potential: thermomechanics and defects in bcc ferromagnetic iron
• Nuclear quantum effects in solids using a colored-noise thermostat
• i-PI: A Python interface for ab initio path integral molecular dynamics simulations
• Colored-noise thermostats à la carte
• Efficient first-principles calculation of the quantum kinetic energy and momentum distribution of nuclei
• Data-driven learning of total and local energies in elemental boron
• Accurate molecular polarizabilities with coupled-cluster theory and machine learning
• Langevin Dynamics in Constant Pressure Extended Systems
• Growth Mechanism and Origin of High $s{p}^3$ Content in Tetrahedral Amorphous Carbon
• Non-covalent interactions across organic and biological subsets of chemical space: Physics-based potentials parametrized from machine learning
• Machine learning of molecular properties: locality and active learning
• Feature Optimization for Atomistic Machine Learning Yields A Data-Driven Construction of the Periodic Table of the Elements
• Transferable atomic multipole machine learning models for small organic molecules
• Guest Editorial: Special Topic on Data-enabled Theoretical Chemistry
• Accurate representation of formation energies of crystalline alloys with many components
• High Order Path Integrals Made Easy
• New angles on standard force fields: towards a general approach for treating atomic-level anisotropy
• Analytical nuclear gradients for the range-separated many-body dispersion model of noncovalent interactions
• Modeling the structural and thermal properties of loaded metal-organic frameworks. An interplay of quantum and anharmonic fluctuations

Cited by in corpus (20)

• Big-Data Science in Porous Materials: Materials Genomics and Machine Learning
• Physics-inspired structural representations for molecules and materials
• Machine learning for electronically excited states of molecules
• Machine learning force fields and coarse-grained variables in molecular dynamics: application to materials and biological systems
• Fast and Accurate Uncertainty Estimation in Chemical Machine Learning
• Predicting molecular dipole moments by combining atomic partial charges and atomic dipoles
• Thermodynamics and dielectric response of ${\text{BaTiO}}_3$ by data-driven modeling
• BIGDML: Towards Exact Machine Learning Force Fields for Materials
• Gaussian Process-Based Refinement of Dispersion Corrections
• Diamond formation from hydrocarbon mixtures in planets
• Atomic Permutationally Invariant Polynomials for Fitting Molecular Force Fields
• Efficient implementation of atom-density representations
• Modeling the structural and thermal properties of loaded metal-organic frameworks. An interplay of quantum and anharmonic fluctuations
• Measuring transferability issues in machine-learning force fields: The example of Gold-Iron interactions with linearized potentials
• Infrared spectra of neutral polycyclic aromatic hydrocarbons by machine learning
• Mean-Field Density Matrix Decompositions
• Selective Excitation of IR-Inactive Modes via Vibrational Polaritons: Insights from Atomistic Simulations
• Accelerating Stochastic Quantum Chemistry
• Machine learning at the atomic-scale
• Physical machine learning outperforms "human learning" in Quantum Chemistry