$\Delta$-Machine Learning for Potential Energy Surfaces: A PIP approach to bring a DFT-based PES to CCSD(T) Level of Theory

Abstract

``$\Delta$-machine learning" refers to a machine learning approach to bring a property such as a potential energy surface (PES) based on low-level (LL) density functional theory (DFT) energies and gradients to close to a coupled cluster (CC) level of accuracy. Here we present such an approach that uses the permutationally invariant polynomial (PIP) method to fit high-dimensional PESs. The approach is represented by a simple equation, in obvious notation $V_{LL\to CC}=V_{LL}+\Delta V_{CC-LL}$, and demonstrated for \ce{CH4}, \ce{H3O+}, and $trans$ and $cis$-$N$-methyl acetamide (NMA), \ce{CH3CONHCH3}. For these molecules, the LL PES, $V_{LL}$, is a PIP fit to DFT/B3LYP/6-31+G(d) energies and gradients, and $\Delta V_{CC-LL}$ is a precise PIP fit obtained using a low-order PIP basis set and based on a relatively small number of CCSD(T) energies. For \ce{CH4} these are new calculations adopting an aug-cc-pVDZ basis, for \ce{H3O+} previous CCSD(T)-F12/aug-cc-pVQZ energies are used, while for NMA new CCSD(T)-F12/aug-cc-pVDZ calculations are performed. With as few as 200 CCSD(T) energies, the new PESs are in excellent agreement with benchmark CCSD(T) results for the small molecules, and for 12-atom NMA training is done with 4696 CCSD(T) energies.

References in corpus (1)

• Molecular Force Fields with Gradient-Domain Machine Learning: Construction and Application to Dynamics of Small Molecules with Coupled Cluster Forces

Cited by in corpus (21)

• Machine Learning in Nuclear Physics
• Perspective on integrating machine learning into computational chemistry and materials science
• 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
• Phase Transitions of Zirconia: Machine-Learned Force Fields Beyond Density Functional Theory
• 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
• The long road to calibrated prediction uncertainty in computational chemistry
• Towards DMC accuracy across chemical space with scalable $\Delta$-QML
• Multi-Fidelity Machine Learning for Excited State Energies of Molecules
• $\Delta$-Machine Learning to Elevate DFT-based Potentials and a Force Field to the CCSD(T) Level Illustrated for Ethanol
• 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
• Optimized Multifidelity Machine Learning for Quantum Chemistry
• Augmentation of Universal Potentials for Broad Applications
• Enabling rapid and accurate construction of CCSD(T)-level potential energy surface of large molecules using molecular tailoring approach
• Deep learning methods for the computation of vibrational wavefunctions
• Topical Review: Extracting Molecular Frame Photoionization Dynamics from Experimental Data
• MOLPIPx: an end-to-end differentiable package for permutationally invariant polynomials in Python and Rust
• Transfer Learned Potential Energy Surfaces: Accurate Anharmonic Vibrational Dynamics and Dissociation Energies for the Formic Acid Monomer and Dimer
• Analogy between Boltzmann machines and Feynman path integrals
• Active Δ-learning with universal potentials for global structure optimization