FourCastNet: Accelerating Global High-Resolution Weather Forecasting using Adaptive Fourier Neural Operators
-
1.
California Institute of Technology
Abstract
Extreme weather amplified by climate change is causing increasingly devastating impacts across the globe. The current use of physics-based numerical weather prediction (NWP) limits accuracy due to high computational cost and strict time-to-solution limits. We report that a data-driven deep learning Earth system emulator, FourCastNet, can predict global weather and generate medium-range forecasts five orders-of-magnitude faster than NWP while approaching state-of-the-art accuracy. FourCast-Net is optimized and scales efficiently on three supercomputing systems: Selene, Perlmutter, and JUWELS Booster up to 3,808 NVIDIA A100 GPUs, attaining 140.8 petaFLOPS in mixed precision (11.9%of peak at that scale). The time-to-solution for training FourCastNet measured on JUWELS Booster on 3,072GPUs is 67.4minutes, resulting in an 80,000times faster time-to-solution relative to state-of-the-art NWP, in inference. FourCastNet produces accurate instantaneous weather predictions for a week in advance, enables enormous ensembles that better capture weather extremes, and supports higher global forecast resolutions.
Additional Information
This research used resources from the National Energy Research Scientific Computing Center (NERSC), a U.S. Department of Energy Office of Science User Facility located at Lawrence Berkeley National Laboratory, operated under Contract No. DE-AC02-05CH11231. The authors also gratefully acknowledge the Gauss Centre for Supercomputing e.V. (www.gauss-centre.eu) for funding this project by providing computing time on the GCS Supercomputer JUWELS [25] at Jülich Supercomputing Centre (JSC). We thank Peter Dueben (ECMWF), Peter Bauer (ECMWF), Bjorn Stevens (MPI-M), Pedram Hassanzadeh (Rice U.), Ashesh Chattopadhyay (Rice U.), and Torsten Hoefler (ETHZ) for many valuable discussions that have shaped this research. We are grateful for the support of staff at the Jülich Supercomputing Centre, NERSC, and the NVIDIA Selene team for their assistance with the runs on their supercomputing systems.Additional details
- Eprint ID
- 118539
- Resolver ID
- CaltechAUTHORS:20221221-004638167
- DE-AC02-05CH11231
- Department of Energy (DOE)
- Gauss Centre for Supercomputing
- Created
-
2022-12-22Created from EPrint's datestamp field
- Updated
-
2023-06-02Created from EPrint's last_modified field