Researchers in Waterloo Region are doing amazing work when it comes to the renewable energy. From minerals to exploring machine learning impact on renewable energy technologies Waterloo researchers are focused on finding solutions. Join us to explore some of the great things happening right in your backyard at the University of Waterloo.
The event is free.
Meet our speakers
Chris Yakymchuk
University of Waterloo - Earth & Environmental Sciences
Associate Professor
Minerals at the heart of the Green Energy Transition
Minerals represent the raw materials that we remove from the Earth and process to provide the metals needed for manufacturing of everyday and advanced technology. Your phone, your vehicle, your Kitchenaid mixer, wind turbines – all of these originate as various minerals in our Earth. Many of these minerals are considered 'critical' by the Canadian government, which means that they are essential for our everyday lives but there is a risk to supply. I will explore why our transition to green energy requires these minerals and the issues we have in obtaining them in a sustainable and responsible manner.
Teaser: An iPhone's battery contains lithium, cobalt, and graphite. Do you know where these raw materials come from? The answer may surprise you.
Conrard Giresse Tetsassi Feugmo
University of Waterloo - Chemistry
Assistant Professor
Physics-Informed Machine Learning in Electrochemistry
Machine learning is transforming how we make sense of complex chemical and electrochemical systems. Yet, despite its success, conventional data-driven models often overlook the deep physical and chemical understanding that scientists have built over decades. In this talk, I’ll introduce a new physics-informed approach that blends electrochemical theory—like the Butler–Volmer and Nernst equations—directly into the architecture of neural networks. By teaching AI the fundamental laws of electrochemistry, we can interpret entire electrochemical measurements more holistically, uncover key reaction parameters, and even reimagine traditional analyses such as Tafel plots. This merging of physical insight with modern machine learning not only enhances model transparency and reliability but also accelerates the discovery of high-performance materials for renewable energy technologies, such as batteries and fuel cells.