The IGAC-iCACGP ECR SSC committee would like to thank everyone who attended for helping us make the first-ever online Early Career Researched science-focused conference.
Workshop Host: The WCRP Academy
The World Climate Research Programme (WCRP) Academy is the capacity-building and training arm of the WCRP. Its mission is to equip the next generation of climate scientists with the knowledge and skills needed to tackle the world’s most pressing climate challenges. By providing access to online training, educational resources, and networking opportunities, the WCRP Academy fosters a global community of researchers and future leaders in climate science, ensuring they are prepared to advance our understanding of the Earth system.
The Use of AI for Atmospheric and Climate Science
Machine learning (ML) is reshaping Earth and climate sciences, offering powerful tools to make use of the rapidly expanding streams of observational and model data. This session introduces the essentials of ML, what it is, how it contrasts with traditional numerical modeling, and the main categories of ML methods. A case study on sea-ice motion illustrates the practical value of ML, demonstrating how neural networks capture complex, non-linear relationships that go beyond simple regression. Participants will also see how ML models are trained, work with interactive examples, and access resources to start applying these methods in their own research.
Presenter Bio: Dr. Lauren Hoffman
Dr. Lauren Hoffman is a Postdoctoral Research Fellow at the Université catholique de Louvain in Belgium. Her research focuses on the intersection of climate dynamics and machine learning, with a particular emphasis on improving the prediction of Arctic sea ice. She develops innovative machine learning models that leverage satellite observations to forecast sea ice conditions, aiming to enhance the skill of both short-term and seasonal predictions. Dr. Hoffman earned her PhD from the Massachusetts Institute of Technology (MIT), where her work centered on understanding the sources of sea ice predictability.