Multi-task learning for molecular electronic structure approaching coupled-cluster accuracy

TL;DR

This paper introduces a machine learning model trained on high-accuracy CCSD(T) data that surpasses traditional DFT methods in predicting molecular electronic properties, demonstrating strong generalization to complex systems.

Contribution

A unified ML approach trained on CCSD(T) data that achieves higher accuracy and efficiency than DFT for molecular electronic structure predictions.

Findings

Outperforms DFT in accuracy and computational cost

Effective on aromatic compounds and semiconducting polymers

Generalizes well to complex systems

Abstract

Machine learning (ML) plays an important role in quantum chemistry, providing fast-to-evaluate predictive models for various properties of molecules. However, most existing ML models for molecular electronic properties use density functional theory (DFT) databases as ground truth in training, and their prediction accuracy cannot surpass that of DFT. In this work, we developed a unified ML method for electronic structures of organic molecules using the gold-standard CCSD(T) calculations as training data. Tested on hydrocarbon molecules, our model outperforms DFT with the widely-used hybrid and double hybrid functionals in computational costs and prediction accuracy of various quantum chemical properties. As case studies, we apply the model to aromatic compounds and semiconducting polymers on both ground state and excited state properties, demonstrating its accuracy and generalization capability to complex systems that are hard to calculate using CCSD(T)-level methods.