Workshop

Boosting Computational Catalysis with Machine Learning
Current Challenges, Limitations, and Opportunities

May 27, 2025, 11:00–18:30

Meridian Hall, Collegium Helveticum

Convened by

Konstantinos Vogiatzis
Senior Fellow 2024–2025

Markus Reiher
Associate Fellow

Details: Intended for an interested professional audience, with limited places available. Attendance is free of charge.

This workshop aims to bring together experts in computational catalysis and machine learning to exchange ideas, discuss current challenges, and explore opportunities for advancing the field. The workshop will be recorded, as we plan to synthesize its key outcomes into a perspective article outlining a roadmap for future developments. All participants who contribute to the discussion will have the opportunity to be included as co-authors of the paper, should they wish to be involved.

Program

11:00	Opening & welcome remarks By Konstantinos Vogiatzis, Markus Reiher, and the Collegium’s directorate
	Session 1
11:15	The Comprehensive Digital Effort Behind the Computational Discovery of Molecular Catalysts Clémence Corminboeuf École Polytechnique Fédérale de Lausanne, CH
12:00	Generative ML for De Novo Catalyst Design Philippe Schwaller École Polytechnique Fédérale de Lausanne, CH
12:45	Lunch break
	Session 2
13:45	Bi-functional Catalyst Design for CO₂ Hydrogenation Reactions Ainara Nova Flores University of Oslo, NO
14:30	Gaussian-Moment Neural Networks Provide Transferable and Uniformly Accurate Interatomic Potentials Johannes Kästner University of Stuttgart, DE
15:15	Coffee break
	Session 3
15:30	Machine Learning Methods for Gas-Phase Chemical Reactivity Markus Meuwly University of Basel, CH
16:15	Structure- And Mechanism-Focused Machine Learning for Catalysis Kjell Jorner ETH Zurich, CH
17:00	Coffee break
17:15	Boosting Computational Catalysis with Machine Learning Panel discussion
18:15	Business meeting
18:30	Closing remarks

Want to be the first to know about upcoming events?

Discover more

craiyon_151810_atomic_simulation_using_quantum_monte_carlog_method_showing_electron_electron_correla

Capturing the Strong Correlation of Electrons with Machine Learning and Quantum Chemistry

Konstantinos Vogiatzis

Fellow Project

AI x Quantum Materials

Artem Mishchenko

Fellow Project

Bubbles, Droplets, Membranes, and Interfaces
Materials Science Meets Visual Arts

April 3–21, 2023

Exhibition

Acapulco
Seeing (through) Images from Large-Scale Vision Datasets

Bruno Moreschi

Fellow Project

Human-AI-Robot Collaboration for Accelerated Energy Transition
Self-Driving Chemistry Lab

Milad Abolhasani

Fellow Project

Program

Opening & welcome remarks

Session 1

The Comprehensive Digital Effort Behind the Computational Discovery of Molecular Catalysts

Generative ML for De Novo Catalyst Design

Lunch break

Session 2

Bi-functional Catalyst Design for CO2 Hydrogenation Reactions

Gaussian-Moment Neural Networks Provide Transferable and Uniformly Accurate Interatomic Potentials

Coffee break

Session 3

Machine Learning Methods for Gas-Phase Chemical Reactivity

Structure- And Mechanism-Focused Machine Learning for Catalysis

Coffee break

Boosting Computational Catalysis with Machine LearningPanel discussion

Business meeting

Closing remarks

Discover more

Capturing the Strong Correlation of Electrons with Machine Learning and Quantum Chemistry

AI x Quantum Materials

Bubbles, Droplets, Membranes, and Interfaces Materials Science Meets Visual Arts

Acapulco Seeing (through) Images from Large-Scale Vision Datasets

Human-AI-Robot Collaboration for Accelerated Energy Transition Self-Driving Chemistry Lab

Bi-functional Catalyst Design for CO₂ Hydrogenation Reactions

Boosting Computational Catalysis with Machine Learning
Panel discussion

Bubbles, Droplets, Membranes, and Interfaces
Materials Science Meets Visual Arts

Acapulco
Seeing (through) Images from Large-Scale Vision Datasets

Human-AI-Robot Collaboration for Accelerated Energy Transition
Self-Driving Chemistry Lab