Transferring climate change knowledge

arXiv:2309.14780v3 Announce Type: replace-cross
Abstract: Accurate and precise 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 …

abstract arxiv change climate climate change complexity cs.ai cs.lg earth knowledge linear non-linear physics.ao-ph reduce transfer transfer learning type