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

Abstract

Predicting UV-visible absorption spectra is essential to understanding photochemical processes and designing energy materials. Quantum chemical methods can deliver accurate calculations of UV-visible absorption spectra, but they are computationally expensive, especially for large systems or when one computes line shapes from thermal averages. Here, we present an approach to predicting UV-visible absorption spectra of solvated aromatic molecules by quantum 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 of aromatic molecules, can accurately predict the line shape of the lowest-energy UV-visible absorption band of several related molecules with less than 0.1 eV deviation with respect to reference experimental spectra. Applying linear decomposition analysis on the excitation energies, we unveil that our ML models probe vertical excitations of these aromatic molecules primarily by learning the atomic environment of their phenyl rings, which align with the physical origin of the $\pi \to {\pi }^{\star }$ electronic transition. Our study provides an effective workflow that combines ML with quantum chemical methods to accelerate the calculations of UV-visible absorption spectra for various molecular systems.

arXiv comment8 Figures

References in corpus (28)

• Scikit-learn: Machine Learning in Python
• Canonical sampling through velocity-rescaling
• Separable Dual Space Gaussian Pseudo-potentials
• Gaussian Approximation Potentials: the accuracy of quantum mechanics, without the electrons
• On representing chemical environments
• Fast and Accurate Modeling of Molecular Atomization Energies with Machine Learning
• A Spectral Analysis Method for Automated Generation of Quantum-Accurate Interatomic Potentials
• A Performance and Cost Assessment of Machine Learning Interatomic Potentials
• Machine Learning Unifies the Modelling of Materials and Molecules
• Machine Learning of Molecular Electronic Properties in Chemical Compound Space
• Physics-inspired structural representations for molecules and materials
• Efficient stochastic thermostatting of path integral molecular dynamics
• Automatic Selection of Atomic Fingerprints and Reference Configurations for Machine-Learning Potentials
• Electronic Spectra from TDDFT and Machine Learning in Chemical Space
• Combining SchNet and SHARC: The SchNarc machine learning approach for excited-state dynamics
• Accurate molecular polarizabilities with coupled-cluster theory and machine learning
• Perspective on integrating machine learning into computational chemistry and materials science
• On the Completeness of Atomic Structure Representations
• The Quest For Highly Accurate Excitation Energies: A Computational Perspective
• QUESTDB: a database of highly-accurate excitation energies for the electronic structure community
• Deep neural network for the dielectric response of insulators
• Quantum-Accurate Spectral Neighbor Analysis Potential Models for Ni-Mo Binary Alloys and FCC Metals
• Combining the Ensemble and Franck-Condon Approaches for Spectral Shapes of Molecules in Solution
• Deep Learning for UV Absorption Spectra with SchNarc: First Steps Towards Transferability in Chemical Compound Space
• Explicit Multi-element Extension of the Spectral Neighbor Analysis Potential for Chemically Complex Systems
• Physically inspired deep learning of molecular excitations and photoemission spectra
• Equivariant representations for molecular Hamiltonians and N-center atomic-scale properties
• Multimodel Approach to the Optical Properties of Molecular Dyes in Solution

Cited by in corpus (2)

• Multi-Fidelity Machine Learning for Excited State Energies of Molecules
• Two-dimensional electronic spectroscopy in the condensed phase using equivariant transformer accelerated molecular dynamics simulations