1. A Deep Learning Earth System Model for Stable and Efficient Simulation of the Current Climate
- Author
-
Cresswell-Clay, Nathaniel, Liu, Bowen, Durran, Dale, Liu, Andy, Espinosa, Zachary I., Moreno, Raul, and Karlbauer, Matthias
- Subjects
Physics - Atmospheric and Oceanic Physics - Abstract
A key challenge for computationally intensive state-of-the-art Earth-system models is to distinguish global warming signals from interannual variability. Recently machine learning models have performed better than state-of-the-art numerical weather prediction models for medium-range forecasting. Here we introduce DLESyM, a parsimonious deep learning model that accurately simulates the Earth's current climate over 1000-year periods with negligible drift. DLESyM simulations equal or exceed key metrics of seasonal and interannual variability--such as tropical cyclone genesis and intensity, and mid-latitude blocking frequency--for historical simulations from four leading models from the 6th Climate Model Intercomparison Project. DLESyM, trained on both historical reanalysis data and satellite observations, is a key step toward an accurate highly efficient model of the coupled Earth system, empowering long-range sub-seasonal and seasonal forecasts., Comment: 24 Pages, 20 figures
- Published
- 2024