Researchers led by Philipp Hess have developed a novel consistency model that transforms coarse Earth system model simulations into detailed, high-resolution precipitation fields in one step. This method corrects spatial biases and outperforms traditional diffusion techniques. It’s a breakthrough tool to enhance climate projections for better planning.

Copy link
Facebook X LinkedIn WhatsApp
Share post via...


Read full article
Fast, scale-adaptive and uncertainty-aware downscaling of Earth system model fields with generative machine learning