Sign up to receive the calendar invites with MS Teams links.

Join us online for the ADIA Lab Climate Data Science Best Paper Award Finalists Seminar Series! Following a competitive selection process, we have chosen five outstanding finalists to present their papers in virtual seminars over the coming weeks.

Seminar 1: Transferring Climate Change Physical Knowledge

Authors: Francesco Immorlano, Veronika Eyring, Thomas le Monnier de Gouville, Gabriele Accarino, Donatello Elia, Stephan Mandt, Giovanni Aloisio, Pierre Gentine

Precise and reliable climate projections are required for climate adaptation and mitigation, but Earth system models still exhibit great uncertainties. Several approaches have been developed to reduce the spread of climate projections and feedbacks, yet those methods cannot capture the non-linear complexity inherent in the climate system. Using a Transfer Learning approach, we show that Machine Learning can be used to optimally leverage and merge the knowledge gained from Earth system models simulations and historical observations to reduce the spread of global surface air temperature fields projected in the 21st century. We reach an uncertainty reduction of more than 50% with respect to state-of-the-art approaches, while giving evidence that our novel method provides improved regional temperature patterns together with narrower projections uncertainty, urgently required for climate adaptation.

When you sign-up, you will recieve links to watch all 5 seminars online. Feel free to attend all sessions or just the ones that interest you most — we look forward to seeing you there!