Transfer-Learned Potential Energy Surfaces: Towards Microsecond-Scale Molecular Dynamics Simulations in the Gas Phase at CCSD(T) Quality

Abstract

The rise of machine learning has greatly influenced the field of computational chemistry, and that of atomistic molecular dynamics simulations in particular. One of its most exciting prospects is the development of accurate, full-dimensional potential energy surfaces (PESs) for molecules and clusters, which, however, often require thousands to tens of thousands of ab initio data points restricting the community to medium sized molecules and/or lower levels of theory (e.g. DFT). Transfer learning, which improves a global PES from a lower to a higher level of theory, offers a data efficient alternative requiring only a fraction of the high level data (on the order of 100 are found to be sufficient for malonaldehyde). The present work demonstrates that even with Hartree-Fock theory and a double-zeta basis set as the lower level model, transfer learning yields CCSD(T)-level quality for H-transfer barrier energies, harmonic frequencies and H-transfer tunneling splittings. Most importantly, finite-temperature molecular dynamics simulations on the sub-microsecond time scale in the gas phase are possible and the infrared spectra determined from the transfer learned PESs are in good agreement with experiment. It is concluded that routine, long-time atomistic simulations on PESs fulfilling CCSD(T)-standards become possible.

References in corpus (14)

• Neural Message Passing for Quantum Chemistry
• SchNet - a deep learning architecture for molecules and materials
• PhysNet: A Neural Network for Predicting Energies, Forces, Dipole Moments and Partial Charges
• Big Data meets Quantum Chemistry Approximations: The $\Delta$-Machine Learning Approach
• Combining Machine Learning and Computational Chemistry for Predictive Insights Into Chemical Systems
• Neural Network Potentials for Chemistry: Concepts, Applications and Prospects
• Breaking the Coupled Cluster Barrier for Machine Learned Potentials of Large Molecules: The Case of 15-atom Acetylacetone
• Full- and reduced-dimensionality instanton calculations of the tunnelling splitting in the formic acid dimer
• Reactive Dynamics and Spectroscopy of Hydrogen Transfer from Neural Network-Based Reactive Potential Energy Surfaces
• Challenges for Machine Learning Force Fields in Reproducing Potential Energy Surfaces of Flexible Molecules
• Retro*: Learning Retrosynthetic Planning with Neural Guided A* Search
• A $\Delta$-Machine Learning Approach for Force Fields, Illustrated by a CCSD(T) 4-body Correction to the MB-pol Water Potential
• Quantum calculations on a new CCSD(T) machine-learned PES reveal the leaky nature of gas-phase $trans$ and $gauche$ ethanol conformers
• Molecular-Level Understanding of the Ro-vibrational Spectra of N${}_2$O in Gaseous, Supercritical and Liquid SF${}_6$ and Xe

Cited by in corpus (3)

• PhysNet Meets CHARMM: A Framework for Routine Machine Learning / Molecular Mechanics Simulations
• $\Delta$-Machine Learning to Elevate DFT-based Potentials and a Force Field to the CCSD(T) Level Illustrated for Ethanol
• A Bond-Based Machine Learning Model for Molecular Polarizabilities and A Priori Raman Spectra