Track / Overview

Extreme weather conditions and climatic changes highlight the urge for the decarbonisation of the energy sector. A potential strategy is the integration of (variable) renewable energy sources. However, aspects like the mismatch between availability of these sources and the demand on different time scales from hours to months generate severe challenges for the energy system as well as their safe operation.

This track brings into focus challenges of the energy transition and their solutions in real-world projects. Examples include the decarbonisation of heating and cooling in Switzerland within the next three decades. The potential of AI to help increasing the share of renewable energy in the electricity system, provide options for flexibility of demand without losing user comfort, and support the coupling of different energy carriers are also complex topics. In those, research and innovation driven by data science faces challenges at every stage in the value chain from data assimilation to the robust implementation of artificial intelligence systems.

We aim at bringing together perspectives and experiences of real-world applications of AI for the energy turnaround as well as experiences on crowdsourcing data science challenges, such as those pursued in hackathons. Furthermore, data engineering aspects such as standardization of data from the energy systems components, the role of actionable data (e.g. machine readable data), and approaches that preserve privacy will also be covered. Moving further down the value chain of AI solutions, we look for presentations of novel models or products that enable a collective reduction of energy consumption to support reduction of carbon footprint. 

Track / Schedule


Using Retrospective Modeling to Improve Long-Range National Energy Projections

With Evelina Trutnevyte

Data Modeling Tools for Thermal Grids

With Jonathan Chambers

Challenges of the Swiss Energy Transition for Network Operators

With Yamshid Farhat

Introduction Part 2

With Emanuele Fabbiani

Concrete Examples how Data Support the Energy Turnaround

With Matthias Eifert

Physics-inspired Deep Machine Learning and Reinforcement Learning with an Application to Building Control Problems

With Loris Di Natale

Using IRT for Prioritization of Building Retrofits

With Hui Ben


Introduction Part 3

Deep Reinforcement Learning for Energy-Efficient Control of Autonomous Evs

With Andrea Pozzi

Towards Better Estimates of Wind Power Potentials in the Alps

With Jérôme Dujardin

Genetic Algorithms for PV Power Simulation and Digital Twinning

With Dorian Guzman

Track / Speakers

Emanuele Fabbiani

Head of Data Science @ xtream

Andrea Pozzi

Assistant Professor, Catholic University of Sacred Heart

Hui Ben

Research Associate, University of Cambridge

Evelina Trutnevyte

Associate professor, University of Geneva

Loris Di Natale

Empa / EPFL

Matthias Eifert

Managing Director, Zukunftsregion Argovia

Yamshid Farhat

Head of Technology, Endaprime by BKW

Dorian Guzman


Jonathan Chambers

Maitre Assistant, UNIGE

Jérôme Dujardin

Postdoc, EPFL, SLF

Track / Co-organizers

Philipp Schütz

Professor, HSLU

Emanuele Fabbiani

Head of Data Science @ xtream

Braulio Barahona


Andreas Melillo

Senior Researcher, HSLU

Esther Linder

Senior scientist, HSLU

Richard Lüchinger

Researcher, HSLU

Patrick Meyer

Researcher, HSLU

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