Atlantic Meridional Overturning Circulation
The Atlantic Meridional Overturning Circulation (AMOC) is a crucial ocean current system impacting global climate, and current research focuses on understanding its stability and potential for abrupt collapse under climate change. Scientists employ machine learning techniques, including neural networks and rare-event algorithms, to analyze observational data and model simulations, aiming to improve predictions of AMOC behavior and quantify the probabilities of different transition scenarios. These efforts are vital for refining climate projections, particularly concerning regional impacts on Europe and North America, and for informing adaptation strategies to potential disruptions in the AMOC.
Papers
Machine-learning prediction of tipping with applications to the Atlantic Meridional Overturning Circulation
Shirin Panahi, Ling-Wei Kong, Mohammadamin Moradi, Zheng-Meng Zhai, Bryan Glaz, Mulugeta Haile, Ying-Cheng Lai
The Importance of Architecture Choice in Deep Learning for Climate Applications
Simon Dräger, Maike Sonnewald