Track / Overview

Many problems in different engineering disciplines share similar challenges from the methodological perspective. They are typically characterized by high-dimensional state and parameter spaces, nonlinear dynamics and heterogeneous multi-modal and partly high-frequency state and condition observations, together with possibly noisy and limited data. The physics- based models are usually computationally very expensive and may not be fully representative of the underlying processes, since those may not even be completely understood. The applications typically also require interpretability, extrapolation ability and the quantification of the underlying uncertainties of the predictions/estimations. In many cases, the collected data is not fully representative of all possible conditions and is lacking labels that are required for training. While the problems in different disciplines in sciences and engineering appear very different, innovative AI algorithms that span across domains enable fast, efficient and robust solutions to these problems.

In this track, we aim to showcase the potential of AI methods for engineering applications, discuss the current state of research and outstanding issues, and point out the most promising research directions. By gathering well-known speakers and young researchers from different engineering disciplines, we will be able to recognize similarities and differences in the research needs of the various areas and promote exchange and discussion on common grounds.

Track / Schedule

Learned Models for Physical Simulation and Design

With Kimberly Stachenfeld

Forward and Inverse Design with Machine Learning for Solid Mechanics

With Miguel A. Bessa

Panel Discussion

With Miguel A. Bessa & Kimberly Stachenfeld


Physics Informed Neural Networks for Thermal Analysis of LPBF Process

With Ehsan Hosseini

Discovering Hyperelastic Material Models through Sparse Regression with an Application to Human Brain Tissue

With Huitian Yu

Physics-informed neural networks for traffic assignment optimization

With Ji-Eun Byun

Bridging the Sim2real Gap for Long Term Battery Discharge Predictions with Time Series Transformer

With Luca Biggio & Tommaso Bendinelli

Modeling and Prediction of Non-Linearizable Phenomena via Dynamics-Based Machine Learning

With Mattia Cenedese

Application of Reinforcement Learning (RL) for Marine Route Optimization to Minimize CO2 Emissions

With Mohammad Hossein Moradi

Data-Centric Machine Learning in Natural Hazards Engineering

With Nenad Bijelic

Boosting Model Robustness by Leveraging Data Augmentations, Stability Training, and Noise Injections

With Soon Hoe Lim

Learning Physics-Consistent Particle Interactions

With Zhichao Han

Digitization of Industrial Diagrams Using Machine Learning & Computer Vision

With Jo-Anne Ting


Simulating Physics Using Constraint-Based Graph Networks

With Yulia Rubanova

Towards Model-Based Reinforcement Learning on Real Robots

With Georg Martius

Panel Discussion

With Georg Martius & Yulia Rubanova

Track / Speakers

Soon Hoe Lim

WINQ Fellow and incoming Assistant Professor, Nordita

Georg Martius

Dr, Max Planck Institute for Intelligent Systems

Miguel A. Bessa

Associate Professor, TU Delft

Yulia Rubanova

Research Scientist, Deepmind

Kimberly Stachenfeld

Senior Research Scientist

Zhichao Han

PhD student, ETH

Ehsan Hosseini

Group leader, Empa + lecturer, ETH Zürich

Jo-Anne Ting

CEO & President, DataSeer

Mohammad Hossein Moradi

Research assistant, KIT

Ji-Eun Byun

Postoctoral Researcher, Technical University of Munich (Germany)

Mattia Cenedese

Postdoctoral Fellow, ETH Zürich

Nenad Bijelic

Postdoctoral researcher, EPFL

Huitian Yu


Luca Biggio

PhD candidate, ETHZ

Tommaso Bendinelli

R&D Engineer, CSEM

Track / Co-organizers

Olga Fink

Professor, EPFL

David Kammer

Assistant Professor, ETH Zurich

Laura De Lorenzis

Professor, ETH Zürich

AMLD EPFL 2022 / Tracks & talks

AMLD Keynote Session – Monday morning

Marcel Salathé, Lenka Zdeborová, Carmela Troncoso, Chiara Enderle, Patrick Barbey, Thomas Wolf, Gunther Jansen, Laure Willemin, Simon Hefti, Arthur Gassner

10:00-12:00 March 28Auditorium A

AI & Physics

Francesca Mignacco, Gert-Jan Both, Michael Unser, Thomas Asikis, Dalila Salamani, Pietro Rotondo, Tom Beucler, Giulio Biroli

12:30-18:00 March 285BC

AI & Pharma

Asif Jan, Jonas Richiardi, Patrick Schwab, Naghmeh Ghazaleh, Alexander Büsser, Carlos Ciller, Caibin Sheng, Silvia Zaoli, Félix Balazard, Giulia Capestro, Marianna Rapsomaniki, Martijn van Attekum

13:30-17:30 March 281BC

AMLD / Global partners