Machine learning for nonadiabatic molecular dynamics: best practices and recent progress Exploring molecular excited states holds immense significance across organic chemistry, chemical biology, and materials science. Understanding the photophysical properties of molecular chromophores is...

Check out our new collaborative paper on machine learning for nonadiabatic molecular dynamics published in @chemicalscience.rsc.org. It provides an overview of the current state-of-the-art and best practices. Thx to
@jwestermayr.bsky.social @stevenalopez.bsky.social @rcrespootero.bsky.social ...

Statistics makes a difference: Machine learning adsorption dynamics of functionalized cyclooctine on Si(001) at DFT accuracy The interpretation of experiments on reactive semiconductor surfaces requires statistically significant sampling of molecular dynamics, but conventional ab initio methods are limited due to prohibitiv...

I am super glad to announce! - Our first paper using machine learning for surface chemistry is out on arxiv! arxiv.org/abs/2509.14828

Thanks to all for the fantastic work!
@rhyanbarrett.bsky.social ,
@jwestermayr.bsky.social l,
@ralftonner.bsky.social al, and especially patrickmelix.bsky.social!

Had a great time at the NuMeriQS SFB retreat: joined a Q&A career session & had great discussion. Big thanks to Tom Frömbgen!

This week is packed: our Saxon Academy of Sciences symposium Mo/Tue, then off to the STC with 6 contributions (incl. a talk by @swesely.bsky.social). Exciting times ahead 🚀

Reposting welcome!

At #PsiK2025 today? Don’t miss Daniel’s talk “Towards time-dependent property predictions with deep equivariant neural networks” at 18:00 in Session B2a (Room C) - work with Tom Frömbgen, Barbara Kirchner & Martin Brehm!

#ML #CompChem #TheoretialChemistry
@dbitterlich.bsky.social

In case you are at #psik25 make sure to visit @dbitterlich.bsky.social talking about time-dependency in #ML predictions for vibrational spectroscopy! Now at 6pm in room C! First talk during his PhD - Could not be prouder to work with such talented people. #compchem

@unileipzig.bsky.social

Big congrats to @alexanderfeige.bsky.social for winning a poster prize at the international school for crystallography using machine learning for electron diffraction! ☺️🎉 in collaboration with @stockholm-uni.bsky.social

A schematic of the functioning of a ML/QM hybrid framework

When you combine #machinelearning and #compchem, you need to start worrying at the QM details within your ML architecture. We use our indirect Hamiltonian framework and pySCFAD to explore the enormous design space arxiv.org/abs/2504.01187

Picture of Robin

Hey, I’m Robin, a PhD student in ML and chemistry at Leipzig University. I joined the Westermayr group in 2024. My work focuses on the application of generative machine learning for the targeted design of molecular systems.
@robincurth.bsky.social
#CompChem #ML #TheoreticalChemistry

📢 Excited to share another great work by @rhyanbarrett.bsky.social on machine learning (MACE) for extended systems in both, ground and excited states ☀️ 🎉 For this work, we made use of the multipole expansion and integrated it into the MACE framework & tested transferability arxiv.org/abs/2502.21045

Incorporating Long-Range Interactions via the Multipole Expansion into Ground and Excited-State Molecular Simulations Simulating long-range interactions remains a significant challenge for molecular machine learning potentials due to the need to accurately capture interactions over large spatial regions. In this work...

I am pleased to announce a preprint of another one of my papers on arxiv with Johannes Dietschreit and Julia Westermayr on: Incorporating Long-Range Interactions via the Multipole Expansion into Ground and Excited-State Molecular Simulation: arxiv.org/abs/2502.21045

thanks, should be fixed now :)

Particularly happy to share this preprint with Christoph Ortner by @rhyanbarrett.bsky.social, where we introduce X-MACE: MACE for excited states 🔆- towards transferability, enabling the transfer from the ground state to excited states. Check it out: arxiv.org/abs/2502.12870

Sophia during her talk

Fahim during his talk

Internship successfully defended! Congrats to our students Sophia and Fahim! 🎉
Their research topics were "ML for Time Series Classification" and "Large Language Models for the Prediction of Reaction Yields". #CompChem #ML #TheoreticalChemisty #WestermayrGroup

Picture of Rhyan

Hi, I’m Rhyan, a PhD student in ML & chemistry at Uni Leipzig and the first PhD in the Westermayr group (since 2022). I combine quantum mechanics & ML to model excitation energies, spectra, and design functional organic molecules. @rhyanbarrett.bsky.social #CompChem #ML #TheoreticalChemistry

Giulia during her introduction talk

We are happy to welcome Giulia Giugliano from the NanoBio Interface Lab in Bologna to our group! 🎉 She is joining us for a 6-month research stay, and we look forward to collaborating and exchanging ideas.

#CompChem #ML #TheoreticalChemistry #Welcome

We’re excited to announce that the Westermayr Group is now on Bluesky! 🎉

In the next few weeks, we will present an overview of each group member and their research area, stay tuned for updates!

@jwestermayr.bsky.social
#TheoreticalChemistry #MachineLearning #CompChem #WestermayrGroup