Tell machine learning potentials what they are needed for: Simulation-oriented training exemplified for glycine
arXiv:2403.11216 · doi:10.1021/acs.jpclett.4c00746
Abstract
Machine learning potentials (MLPs) are widely applied as an efficient alternative way to represent potential energy surfaces (PES) in many chemical simulations. The MLPs are often evaluated with the root-mean-square errors on the test set drawn from the same distribution as the training data. Here, we systematically investigate the relationship between such test errors and the simulation accuracy with MLPs on an example of a full-dimensional, global PES for the glycine amino acid. Our results show that the errors in the test set do not unambiguously reflect the MLP performance in different simulation tasks such as relative conformer energies, barriers, vibrational levels, and zero-point vibrational energies. We also offer an easily accessible solution for improving the MLP quality in a simulation-oriented manner, yielding the most precise relative conformer energies and barriers. This solution also passed the stringent test by the diffusion Monte Carlo simulations.
References in corpus (23)
- 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
- Machine Learning of Accurate Energy-Conserving Molecular Force Fields
- A Performance and Cost Assessment of Machine Learning Interatomic Potentials
- Less is more: sampling chemical space with active learning
- Physics-inspired structural representations for molecules and materials
- Active Learning of Uniformly Accurate Inter-atomic Potentials for Materials Simulation
- Machine Learning Molecular Dynamics for the Simulation of Infrared Spectra
- Neural Network Based in Silico Simulation of Combustion Reactions
- sGDML: Constructing Accurate and Data Efficient Molecular Force Fields Using Machine Learning
- On the Completeness of Atomic Structure Representations
- Structure-based Sampling and Self-correcting Machine Learning for Accurate Calculations of Potential Energy Surfaces and Vibrational Levels
- Strategies for the Construction of Machine-Learning Potentials for Accurate and Efficient Atomic-Scale Simulations
- Accelerated Computation of Free Energy Profile at ab Initio Quantum Mechanical/Molecular Mechanics Accuracy via a Semi-Empirical Reference Potential. I. Weighted Thermodynamics Perturbation
- Differentiable sampling of molecular geometries with uncertainty-based adversarial attacks
- MLatom 3: Platform for machine learning-enhanced computational chemistry simulations and workflows
- Permutationally invariant polynomial regression for energies and gradients, using reverse differentiation, achieves orders of magnitude speed-up with high precision compared to other machine learning methods
- Challenges for Machine Learning Force Fields in Reproducing Potential Energy Surfaces of Flexible Molecules
- The MD17 Datasets from the Perspective of Datasets for Gas-Phase "Small" Molecule Potentials
- The Phase Space Mechanism for Selectivity in a Symmetric Potential Energy Surface with a Post-Transition-State Bifurcation
- Energy-conserving molecular dynamics is not energy conserving
- No Headache for PIPs: A PIP Potential for Aspirin Outperforms Other Machine-Learned Potentials