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 Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Predicting UV-visible absorption spectra is essential to understandingphotochemical processes and designing energy materials. Quantum chemicalmethods can deliver accurate calculations of UV-visible absorption spectra, butthey are computationally expensive, especially for large systems or when onecomputes line shapes from thermal averages. Here, we present an approach topredicting UV-visible absorption spectra of solvated aromatic molecules byquantum chemistry (QC) and machine learning (ML). We show that a ML model,trained on the high-level QC calculation of the excitation energy of a set ofaromatic molecules, can accurately predict the line shape of the lowest-energyUV-visible absorption band of several related molecules with less than 0.1 eVdeviation with respect to reference experimental spectra. Applying lineardecomposition analysis on the excitation energies, we unveil that our ML modelsprobe vertical excitations of these aromatic molecules primarily by learningthe atomic environment of their phenyl rings, which align with the physicalorigin of the $\pi\rightarrow\pi^\star$ electronic transition. Our studyprovides an effective workflow that combines ML with quantum chemical methodsto accelerate the calculations of UV-visible absorption spectra for variousmolecular systems.

UV-Visible Absorption Spectra of Solvated Molecules by Quantum Chemical Machine Learning