• Corpus ID: 231639222

Elucidating atmospheric brown carbon -- Supplanting chemical intuition with exhaustive enumeration and machine learning

  title={Elucidating atmospheric brown carbon -- Supplanting chemical intuition with exhaustive enumeration and machine learning},
  author={Enrico Tapavicza and Guido Falk von Rudorff and David O. De Haan and M. Contin and Christian George and Matthieu Riva and O. Anatole von Lilienfeld},
To unravel the structures of constitutional C 12 H 12 O 7 isomers, identified as light-absorbing photooxidation products of syringol in atmospheric chamber experiments, we apply a combined graph-based molecule generator and machine learning workflow. To accomplish this in a bias-free manner, molecular graphs of the entire chemical subspace of C 12 H 12 O 7 were generated, under only the assumption that the isomers contain two C 6 -rings; this led to 260 million molecular graphs, of which 120… 

Figures from this paper



Alchemical and structural distribution based representation for universal quantum machine learning.

We introduce a representation of any atom in any chemical environment for the automatized generation of universal kernel ridge regression-based quantum machine learning (QML) models of electronic

Electronic spectra from TDDFT and machine learning in chemical space.

This work applies machine learning models trained on deviations of reference second-order approximate coupled-cluster singles and doubles spectra from TDDFT counterparts, or even from DFT gap to low-lying singlet-singlet vertical electronic spectra of over 20 000 synthetically feasible small organic molecules with up to eight CONF atoms.

Machine Learning for Absorption Cross Sections

It is demonstrated for two examples, benzene and a 9-dicyanomethylene derivative of acridine, that ML-NEA can produce statistically converged cross sections even for very challenging cases and even with as few as several hundreds of training points.

Machine Learning for Electronically Excited States of Molecules

This review focuses on not only how machine learning is employed to speed up excited-state simulations but also how this branch of artificial intelligence can be used to advance this exciting research field in all its aspects.

Assessing Excited State Methods by Adiabatic Excitation Energies.

We compile a 109-membered benchmark set of adiabatic excitation energies (AEEs) from high-resolution gas-phase experiments. Our data set includes a variety of organic chromophores with up to 46

Fast and accurate modeling of molecular atomization energies with machine learning.

A machine learning model is introduced to predict atomization energies of a diverse set of organic molecules, based on nuclear charges and atomic positions only, and applicability is demonstrated for the prediction of molecular atomization potential energy curves.

First-Principles Prediction of Wavelength-Dependent Product Quantum Yields.

We present a method to predict wavelength-dependent product quantum yields (PQYs) for photochemical reactions and applied it to Z/E-isomerization and several ring-closing reactions of

Nitrogen-Containing, Light-Absorbing Oligomers Produced in Aerosol Particles Exposed to Methylglyoxal, Photolysis, and Cloud Cycling.

Chemical analysis of brown carbon aerosol particles collected from cloud cycling/photolysis chamber experiments, where gaseous methylglyoxal and methylamine interacted with glycine, ammonium, or methYlammonium sulfate seed particles, suggests that daytime methyl Glyoxal oligomer formation is dominated by radical addition mechanisms involving CH3CO*.

The role of tachysterol in vitamin D photosynthesis - a non-adiabatic molecular dynamics study.

This study confirms the previously formed hypothesis that cEc rotamers are more prone to prev vitamin D formation than other isomers and reinforces a recent hypothesis that tachysterol constitutes a source of previtamin D when only low energy ultraviolet light is available, as the case in winter or in the morning and evening hours of the day.

A Mountaineering Strategy to Excited States: Highly-Accurate Energies and Benchmarks for Medium Size Molecules.

Following our previous work focussing on compounds containing up to 3 non-hydrogen atoms [J. Chem. Theory Comput. 14 (2018) 4360-4379], we present here highly-accurate vertical transition energies