AI for Climate Sciences
What would it actually take to build an AI climate scientist?
Climate research already relies on large-scale simulations, physical models, and vast observational datasets. Dr Torsten Hoefler will explore how modern machine learning fits into these workflows in practice, sharing where AI has delivered real gains such as accelerating simulations and making sense of noisy data, and where it continues to struggle with generalization, uncertainty, and physical consistency.
Rather than positioning AI as a replacement for scientists, he will share how AI can realistically support and extend scientific workflows under real computational and modeling constraints. Through examples from current research, learn how to separate meaningful progress from hype and understand what is still missing before AI can contribute to deeper scientific reasoning in climate science.
More About the Speaker
Dr Torsten Hoefler directs the Scalable Parallel Computing Laboratory at ETH Zurich. A member of Academia Europaea and Fellow of ACM and IEEE, he focuses on 'Performance-centric System Design', including scalable networks, parallel programming, and performance modeling. Hoefler is the youngest recipient of the IEEE Sidney Fernbach Award and has won the ACM Gordon Bell Prize, ISC Jack Dongarra award, and ETH Zurich's Latsis prize. His work, supported by ERC starting and consolidator grants, has earned multiple best paper awards at top conferences. Hoefler has contributed to MPI standards and continues to shape high-performance computing and AI.
More About the Series
Praxis is a focused technical sharing series built around researcher-driven discussions on advanced AI and applied research topics.
Get involved: Learn more about Lorong AI | Speaker Sign-up | WhatsApp Community | LinkedIn | X