Transferability in Machine Learning for Electronic Structure via the Molecular Orbital Basis

TL;DR

This paper introduces a machine learning approach that predicts electronic correlation energies from Hartree-Fock data, emphasizing transferability across diverse chemical systems without relying on atom-specific features.

Contribution

The method predicts correlation energies using molecular orbital properties, enhancing transferability and compactness compared to traditional atom-based features.

Findings

Accurately predicts MP2 and CCSD energies across various systems.

Maintains accuracy even for molecules with unseen atom types.

Demonstrates transferability within and across chemical families.

Abstract

We present a machine learning (ML) method for predicting electronic structure correlation energies using Hartree-Fock input.The total correlation energy is expressed in terms of individual and pair contributions from occupied molecular orbitals, and Gaussian process regression is used to predict these contributions from a feature set that is based on molecular orbital properties, such as Fock, Coulomb, and exchange matrix elements. With the aim of maximizing transferability across chemical systems and compactness of the feature set, we avoid the usual specification of ML features in terms of atom- or geometry-specific information, such atom/element-types, bond-types, or local molecular structure. ML predictions of MP2 and CCSD energies are presented for a range of systems, demonstrating that the method maintains accuracy while providing transferability both within and across chemical families; this includes predictions for molecules with atom-types and elements that are not included in the training set. The method holds promise both in its current form and as a proof-of-principle for the use of ML in the design of generalized density-matrix functionals.