March 12, 2025 at 14:00 – 15:00 CET.

Overview of the webinar

AI has become almost synonymous with Generative AI. The world is booming around ChatGPT, LLama, DeepSeek, Dall-E, MidJourney and Runway. We’ve heard about the highlights of extra intelligence, replacement of labor force, but also of the enormous costs in energy and infrastructure that it brings. But what else is this AI bringing us? Where else could AI bring us benefits?

We look at three projects from our member RTOs using AI in different ways to improve forecasting, such as weather forecasting, climate change and biodiversity. How can AI models make these forecasts harder, better, stronger, faster? Can we improve the accuracy and energy usage? Come and join us to hear more from these smart researchers.

Agenda

• Weather modeling with AI at AIT (Kristofer Hasel
• Climate modeling with AI at RISE (Aleksis Pirinen)
• Biodiversity modeling with AI at TNO (Thanasis Trantas)
• Questions

Sign up here for the webinar

Speaker biographies

Kristofer Hasel (AIT) is a meteorologist with a focus on climatology and numerical weather and climate modeling. In his work and research projects, he has focused on the creation and analysis of urban climate scenarios considering population growth, the development of a statistical model for predicting climate indicators from data with monthly frequency, dynamical downscaling of global climate models to a resolution of down to 1 km, and the analysis and evaluation of climate model ensembles. During his studies, he worked as a student assistant at the meteorological institutes of the University of Natural Resources and Life Sciences, Vienna (BOKU-MET), and the University of Innsbruck (ACINN). After graduating, he began working as a doctoral candidate at the Austrian Institute of Technology (AIT) in November 2019. Since November 2023, he has been employed as a Junior Research Engineer at the Center for Energy, within the “Digital Resilient Cities” (DRC) business unit, focusing on regional climate modeling and risk assessment of extreme weather events, such as pluvial flooding caused by heavy rainfall.

Aleksis Pirinen (RISE) is a senior machine learning researcher at RISE Research Institutes of Sweden, where his research focuses on developing AI-based methods for environmental applications. He is a co-founder of Climate AI Nordics, a new Nordic research network focused on advancing AI for climate-related challenges. In addition, he is in the core team of an AI-themed working group within the intergovernmental Group on Earth Observations (GEO) and is also affiliated with the Swedish Centre for Impacts of Climate Extremes (CLIMES). Aleksis holds a PhD in computer vision from Lund University.

In his talk, Aleksis will present the new Nordic research network that he co-founded late last year – Climate AI Nordics (CAIN). The network gathers researchers dedicated to developing and utilizing AI technologies to address the urgent global challenge of climate change. CAIN’s researchers focus on creating and promoting AI solutions that support both climate change mitigation, reducing the severity of climate change, and adaptation, adjusting to the effects of climate change. We are already in a climate emergency which is causing biodiversity loss, extreme weather events, and human suffering, and this necessitates a multifaceted approach involving both policy change, limitations on activities contributing to climate change, and bolstering societal resilience against climate-related events. 

Athanasios Trantas, AI Research Scientists at TNO, specializes in developing large-scale AI systems with focus on advanced decision making. He holds a BSc in Mathematics and a MSc in Artificial Intelligence, with over 5 years of experience in building AI applications for hyperscale infrastructures across industries.

In his talk, Thanasis will introduce the concept of Biodiversity Foundation Model (BFM), a large-scale, multimodal AI model pre-trained on diverse biodiversity data modalities. The BFM aims to enhance biodiversity monitoring, prediction, and conservation efforts, while being flexible and robust to any kind of downstream task, from classification to prediction. Still, like any other advance AI model, BFM comes with a series of challenges. Each of these challenges require careful handling and a multi-disciplinary team with ecologist, computer scientists, AI and HPC experts to ensure its success.