Uncertainty estimation for molecular dynamics and sampling

Abstract

Machine learning models have emerged as a very effective strategy to sidestep time-consuming electronic-structure calculations, enabling accurate simulations of greater size, time scale and complexity. Given the interpolative nature of these models, the reliability of predictions depends on the position in phase space, and it is crucial to obtain an estimate of the error that derives from the finite number of reference structures included during the training of the model. When using a machine-learning potential to sample a finite-temperature ensemble, the uncertainty on individual configurations translates into an error on thermodynamic averages, and provides an indication for the loss of accuracy when the simulation enters a previously unexplored region. Here we discuss how uncertainty quantification can be used, together with a baseline energy model, or a more robust although less accurate interatomic potential, to obtain more resilient simulations and to support active-learning strategies. Furthermore, we introduce an on-the-fly reweighing scheme that makes it possible to estimate the uncertainty in the thermodynamic averages extracted from long trajectories. We present examples covering different types of structural and thermodynamic properties, and systems as diverse as water and liquid gallium.

17 pages, 9 figures

References in corpus (35)

• Quantum ESPRESSO: a modular and open-source software project for quantum simulations of materials
• Canonical sampling through velocity-rescaling
• Advanced capabilities for materials modelling with Quantum ESPRESSO
• Gaussian Approximation Potentials: the accuracy of quantum mechanics, without the electrons
• Fast and Accurate Modeling of Molecular Atomization Energies with Machine Learning
• ANI-1: An extensible neural network potential with DFT accuracy at force field computational cost
• PLUMED: a portable plugin for free-energy calculations with molecular dynamics
• Accurate determination of crystal structures based on averaged local bond order parameters
• Big Data meets Quantum Chemistry Approximations: The $\Delta$-Machine Learning Approach
• Less is more: sampling chemical space with active learning
• Machine Learning Unifies the Modelling of Materials and Molecules
• By-passing the Kohn-Sham equations with machine learning
• Towards Exact Molecular Dynamics Simulations with Machine-Learned Force Fields
• Phase transitions of hybrid perovskites simulated by machine-learning force fields trained on-the-fly with Bayesian inference
• How van der Waals interactions determine the unique properties of water
• i-PI 2.0: A Universal Force Engine for Advanced Molecular Simulations
• Ab initio thermodynamics of liquid and solid water
• Chemical Shifts in Molecular Solids by Machine Learning
• A Transferable Machine-Learning Model of the Electron Density
• A neural network interatomic potential for the phase change material GeTe
• Colored-noise thermostats à la carte
• Committee neural network potentials control generalization errors and enable active learning
• Evidence for supercritical behavior of high-pressure liquid hydrogen
• Fast and Accurate Uncertainty Estimation in Chemical Machine Learning
• Constructing first-principles phase diagrams of amorphous LixSi using machine-learning-assisted sampling with an evolutionary algorithm
• Learning the electronic density of states in condensed matter
• Using Gaussian Process Regression to Simulate the Vibrational Raman Spectra of Molecular Crystals
• Computing Gibbs free energy differences by interface pinning
• Accurate molecular dynamics and nuclear quantum effects at low cost by multiple steps in real and imaginary time: using density functional theory to accelerate wavefunction methods
• Inexpensive modelling of quantum dynamics using path integral generalized Langevin equation thermostats
• Quantifying Chemical Structure and Atomic Energies in Amorphous Silicon Networks
• The inefficiency of re-weighted sampling and the curse of system size in high order path integration
• On Machine Learning Force Fields for Metallic Nanoparticles
• Simulating solvation and acidity in complex mixtures with first-principles accuracy: the case of CH${}_3$SO${}_3$H and H${}_2$O${}_2$ in phenol
• Enabling robust offline active learning for machine learning potentials using simple physics-based priors

Cited by in corpus (29)

• Thermodynamics and dielectric response of ${\text{BaTiO}}_3$ by data-driven modeling
• Differentiable sampling of molecular geometries with uncertainty-based adversarial attacks
• A complete description of thermodynamic stabilities of molecular crystals
• i-PI 3.0: a flexible and efficient framework for advanced atomistic simulations
• Universal QM/MM Approaches for General Nanoscale Applications
• Accurate machine learning force fields via experimental and simulation data fusion
• Lifelong Machine Learning Potentials
• Predicting Properties of Periodic Systems from Cluster Data: A Case Study of Liquid Water
• Exploring the robust extrapolation of high-dimensional machine learning potentials
• The importance of nuclear quantum effects for NMR crystallography
• Prediction uncertainty validation for computational chemists
• Modeling the Ga/As binary system across temperaturesand compositions from first principles
• chemtrain: Learning Deep Potential Models via Automatic Differentiation and Statistical Physics
• Prediction rigidities for data-driven chemistry
• Machine learning potentials for complex aqueous systems made simple
• A Riemannian Stochastic Representation for Quantifying Model Uncertainties in Molecular Dynamics Simulations
• Machine Learning Enhanced Calculation of Quantum-Classical Binding Free Energies
• Uncertainty Quantification in Atomistic Simulations of Silicon using Interatomic Potentials
• Building Robust Machine Learning Models for Small Chemical Science Data: The Case of Shear Viscosity
• Flow Matching for Accelerated Simulation of Atomic Transport in Crystalline Materials
• Apax: A Flexible and Performant Framework For The Development of Machine-Learned Interatomic Potentials
• Multi-head committees enable direct uncertainty prediction for atomistic foundation models
• Lifelong Machine Learning Potentials for Chemical Reaction Network Explorations
• Accurate Machine Learning Interatomic Potentials for Polyacene Molecular Crystals: Application to Single Molecule Host-Guest Systems
• Structure and thermodynamics of defects in Na-feldspar from a neural network potential
• Adaptive Equilibration of Molecular Dynamics Simulations
• Learning atomic forces from uncertainty-calibrated adversarial attacks
• Uncertainty in AI-driven Monte Carlo simulations
• Integer linear programming for unsupervised training set selection in molecular machine learning