PhD Student

Julia Westermayr
University of Vienna
Institute of Theoretical Chemistry
Währinger Str. 17
1090 Vienna
Austria

julia.westermayr@univie.ac.at
+43 1 4277 52766

Focus Area

The focus of my work is the development of artificial neural network potentials and their implementation into our own ab-initio molecular dynamics program SHARC (Surface Hopping including ARbitrary Couplings). By running molecular dynamics with the SHARC program, we are currently investigating the first step of the underlying mechanism of dityrosine crosslinking.

Awards & Prizes

2019 Best Poster Award ISTCP-X
University of Vienna Uni:docs Fellowship

News

18.07.2022 Bank Austria Anerkennungspreise für Julia Westermayr und Cornelia von Baeckmann

Publications

16.

COLUMBUS — an Efficient and General Program Package for Ground and Excited State Computations Including Spin-Orbit Couplings and Dynamics

15.

Excited-state Nonadiabatic Dynamics in Explicit Solvent Using Machine Learned Interatomic Potentials

Digital Discovery

DOI: 10.1039/D5DD00044K

M. Tiefenbacher, B. Bachmair, C. Cheng-Giuseppe, J. Westermayr, P. Marquetand, J. Dietschreit, L. González
Excited-state Nonadiabatic Dynamics in Explicit Solvent Using Machine Learned Interatomic Potentials
arXiv, (2025), DOI: 10.48550/arXiv.2501.16974

14.

Incorporating Long-Range Interactions via the Multipole Expansion into Ground and Excited-State Molecular Simulations

arXiv:2502.21045 [physics.comp-ph]

DOI: 10.48550/arXiv.2502.21045

13.

SpaiNN: Equivariant Message Passing for Excited-State Nonadiabatic Molecular Dynamics

Chem. Sci.

DOI: 10.1039/D4SC04164J

12.

Focus on Learning Excited-state Properties in General

Learning Excited-state Properties. In Quantum Chemistry in the Age of Machine Learning.

DOI: 10.1016/B978-0-323-90049-2.00004-4

11.

Arene Variation of Highly Cytotoxic Tridentate Naphthoquinone-Based Ruthenium (II) Complexes and In-Depth In Vitro Studies

Pharmaceutics

DOI: 10.3390/pharmaceutics14112466

10.

Deep Learning Study of Tyrosine Reveals that Roaming can Lead to Photodamage

Nat. Chem.

DOI: 10.1038/s41557-022-00950-z

BuRNN: Buffer Region Neural Network Approach for Polarizable-Embedding Neural Network/Molecular Mechanics Simulations

J. Chem. Phys.

DOI: 10.1021/acs.jpclett.2c00654

B. Lier, P. Poliak, P. Marquetand, J. Westermayr, C. Oostenbrink
BuRNN: Buffer Region Neural Network Approach for Polarizable-Embedding Neural Network/Molecular Mechanics Simulations
arXiv:2112.11395 [physics.chem-ph], (2021), DOI: 10.48550/arXiv.2112.11395

Tridentate 3-Substituted Naphthoquinone Ruthenium Arene Complexes: Synthesis, Characterization, Aqueous Behavior, and Theoretical and Biological Studies

Inorg. Chem.

DOI: 10.1021/acs.inorgchem.1c01083

Machine learning for electronically excited states of molecules

Chem. Rev.

DOI: 10.1021/acs.chemrev.0c00749

J. Westermayr, P. Marquetand
Machine learning for electronically excited states of molecules
arXiv:2007.05320 [physics.chem-ph], (2020)

Deep learning for UV absorption spectra with SchNarc: First steps toward transferability in chemical compound space

J. Chem. Phys.

DOI: 10.1063/5.0021915

J. Westermayr, P. Marquetand
Deep learning for UV absorption spectra with SchNarc: First steps toward transferability in chemical compound space
arXiv:2007.07684 [physics.chem-ph], (2020)

Machine learning and excited-state molecular dynamics

Mach. Learn.: Sci. Technol.

DOI: 10.1088/2632-2153/ab9c3e

J. Westermayr, P. Marquetand
Machine learning and excited-state molecular dynamics
arXiv:2005.14139 [physics.chem-ph], (2020)

Combining SchNet and SHARC: The SchNarc machine learning approach for excited-state dynamics

J. Phys. Chem. Lett.

DOI: 10.1021/acs.jpclett.0c00527

J. Westermayr, M. Gastegger, P. Marquetand
Combining SchNet and SHARC: The SchNarc machine learning approach for excited-state dynamics
arXiv:2002.07264 [physics.chem-ph], (2020)

Neural networks and kernel ridge regression for excited states dynamics of CH₂NH⁺₂: From single-state to multi-state representations and multi-property machine learning models

Mach. Learn.: Sci. Technol.

DOI: 10.1088/2632-2153/ab88d0

J. Westermayr, F. A. Faber, A. S. Christensen, O. A. von Lilienfeld, P. Marquetand
Neural networks and kernel ridge regression for excited states dynamics of CH₂NH₂⁺: From single-state to multi-state representations and multi-property machine learning models
arXiv:1912.08484 [physics.chem-ph], (2020)

Machine Learning for Nonadiabatic Molecular Dynamics In: Hugh Cartwright (ed) Machine Learning in Chemistry: The Impact of Artificial Intelligence

Theoretical and Computational Chemistry Series, Royal Society of Chemistry

DOI: 10.1039/9781839160233-00076

Machine Learning Enables Long Time Scale Molecular Photodynamics Simulations

Chem. Sci.

DOI: 10.1039/C9SC01742A

Cover Image:
Machine Learning Enables Long Time Scale Molecular Photodynamics Simulations
Chem. Sci. 10, 8273-8273, (2019), DOI: 10.1039/C9SC90196E

J. Westermayr, M. Gastegger, M. Menger, S. Mai, L. González, P. Marquetand
Machine Learning Enables Long Time Scale Molecular Photodynamics Simulations
arXiv:1811.09112 [physics.chem-ph], (2018)