# Predicting molecular dipole moments by combining atomic partial charges and atomic dipoles

arXiv: https://arxiv.org/abs/2003.12437 · HTML: https://mlsanity.com/paper/2003.12437/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Mar 2020.

## Built on by (most cited first, 18 of 18)

- [Equivariant message passing for the prediction of tensorial properties and molecular spectra](https://mlsanity.com/paper/2102.03150/) (2021)
- [Smooth, exact rotational symmetrization for deep learning on point clouds](https://mlsanity.com/paper/2305.19302/) (2023)
- [Informing Geometric Deep Learning with Electronic Interactions to Accelerate Quantum Chemistry](https://mlsanity.com/paper/2105.14655/) (2021)
- [SchNetPack 2.0: A neural network toolbox for atomistic machine learning](https://mlsanity.com/paper/2212.05517/) (2022)
- [A Universal Framework for Accurate and Efficient Geometric Deep Learning of Molecular Systems](https://mlsanity.com/paper/2311.11228/) (2023)
- [Wigner kernels: body-ordered equivariant machine learning without a basis](https://mlsanity.com/paper/2303.04124/) (2023)
- [Efficient and Accurate Physics-aware Multiplex Graph Neural Networks for 3D Small Molecules and Macromolecule Complexes](https://mlsanity.com/paper/2206.02789/) (2022)
- [Electronic-structure properties from atom-centered predictions of the electron density](https://mlsanity.com/paper/2206.14087/) (2022)
- [Accurate Molecular-Orbital-Based Machine Learning Energies via Unsupervised Clustering of Chemical Space](https://mlsanity.com/paper/2204.09831/) (2022)
- [Synthetic data enable experiments in atomistic machine learning](https://mlsanity.com/paper/2211.16443/) (2022)
- [Molecular Dipole Moment Learning via Rotationally Equivariant Gaussian Process Regression with Derivatives in Molecular-orbital-based Machine Learning](https://mlsanity.com/paper/2205.15510/) (2022)
- [Molecular-orbital-based Machine Learning for Open-shell and Multi-reference Systems with Kernel Addition Gaussian Process Regression](https://mlsanity.com/paper/2207.08317/) (2022)
- [Predicting hot-electron free energies from ground-state data](https://mlsanity.com/paper/2205.05591/) (2022)
- [Edge Direction-invariant Graph Neural Networks for Molecular Dipole Moments Prediction](https://mlsanity.com/paper/2206.12867/) (2022)
- [Benchmarking Data Efficiency in Delta-ML and Multifidelity Models for Quantum Chemistry](https://mlsanity.com/paper/2410.11391/) (2024)
- [Vibrational Fingerprints of Strained Polymers: A Spectroscopic Pathway to Mechanical State Prediction](https://mlsanity.com/paper/2509.16266/) (2025)
- [QT-Net: Rethinking Evaluation of AI Models in Atomic Chemical Space](https://mlsanity.com/paper/2605.10458/) (2026)
- [Coupled-cluster molecular properties across the main group that extrapolate beyond training size](https://mlsanity.com/paper/2608.18346/) (2026)

## Abstract (arXiv)

The molecular dipole moment (boldsymbolμ) is a central quantity in chemistry. It is essential in predicting infrared and sum-frequency generation spectra, as well as induction and long-range electrostatic interactions. Furthermore, it can be extracted directly from high-level quantum mechanical calculations, making it an ideal target for machine learning (ML). In this work, we choose to represent this quantity with a physically inspired ML model that captures two distinct physical effects: local atomic polarization is captured within the symmetry-adapted Gaussian process regression (SA-GPR) framework, which assigns a (vector) dipole moment to each atom, while movement of charge across the entire molecule is captured by assigning a partial (scalar) charge to each atom. The resulting "MuML" models are fitted together to reproduce molecular boldsymbolμ computed using high-level coupled-cluster theory (CCSD) and density functional theory (DFT) on the QM7b dataset. The combined model shows excellent transferability when applied to a showcase dataset of larger and more complex molecules, approaching the accuracy of DFT at a small fraction of the computational cost. We also demonstrate that the uncertainty in the predictions can be estimated reliably using a calibrated committee model. The ultimate performance of the models depends, however, on the details of the system at hand, with the scalar model being clearly superior when describing large molecules whose dipole is almost entirely generated by charge separation. These observations point to the importance of simultaneously accounting for the local and non-local effects that contribute to boldsymbolμ; further, they define a challenging task to benchmark future models, particularly those aimed at the description of condensed phases.