English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

The molecular dipole moment ($\boldsymbol{\mu}$) is a central quantity inchemistry. It is essential in predicting infrared and sum-frequency generationspectra, as well as induction and long-range electrostatic interactions.Furthermore, it can be extracted directly from high-level quantum mechanicalcalculations, making it an ideal target for machine learning (ML). In thiswork, we choose to represent this quantity with a physically inspired ML modelthat captures two distinct physical effects: local atomic polarization iscaptured within the symmetry-adapted Gaussian process regression (SA-GPR)framework, which assigns a (vector) dipole moment to each atom, while movementof charge across the entire molecule is captured by assigning a partial(scalar) charge to each atom. The resulting "MuML" models are fitted togetherto reproduce molecular $\boldsymbol{\mu}$ computed using high-levelcoupled-cluster theory (CCSD) and density functional theory (DFT) on the QM7bdataset. The combined model shows excellent transferability when applied to ashowcase dataset of larger and more complex molecules, approaching the accuracyof DFT at a small fraction of the computational cost. We also demonstrate thatthe uncertainty in the predictions can be estimated reliably using a calibratedcommittee model. The ultimate performance of the models depends, however, onthe details of the system at hand, with the scalar model being clearly superiorwhen describing large molecules whose dipole is almost entirely generated bycharge separation. These observations point to the importance of simultaneouslyaccounting for the local and non-local effects that contribute to$\boldsymbol{\mu}$; further, they define a challenging task to benchmark futuremodels, particularly those aimed at the description of condensed phases.

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