CaltechAUTHORS
  A Caltech Library Service

FourCastNet: Accelerating Global High-Resolution Weather Forecasting using Adaptive Fourier Neural Operators

Kurth, Thorsten and Subramanian, Shashank and Harrington, Peter and Pathak, Jaideep and Mardani, Morteza and Hall, David and Miele, Andrea and Kashinath, Karthik and Anandkumar, Animashree (2022) FourCastNet: Accelerating Global High-Resolution Weather Forecasting using Adaptive Fourier Neural Operators. . (Unpublished) https://resolver.caltech.edu/CaltechAUTHORS:20221221-004638167

Full text is not posted in this repository. Consult Related URLs below.

Use this Persistent URL to link to this item: https://resolver.caltech.edu/CaltechAUTHORS:20221221-004638167

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.


Item Type:Report or Paper (Discussion Paper)
Related URLs:
URLURL TypeDescription
http://arxiv.org/abs/2208.05419arXivDiscussion Paper
ORCID:
AuthorORCID
Kurth, Thorsten0000-0003-0832-6198
Pathak, Jaideep0000-0002-3095-0256
Mardani, Morteza0000-0002-3788-137X
Kashinath, Karthik0000-0002-9311-5215
Anandkumar, Animashree0000-0002-6974-6797
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.
Funders:
Funding AgencyGrant Number
Department of Energy (DOE)DE-AC02-05CH11231
Gauss Centre for SupercomputingUNSPECIFIED
DOI:10.48550/arXiv.2208.05419
Record Number:CaltechAUTHORS:20221221-004638167
Persistent URL:https://resolver.caltech.edu/CaltechAUTHORS:20221221-004638167
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:118539
Collection:CaltechAUTHORS
Deposited By: George Porter
Deposited On:22 Dec 2022 18:36
Last Modified:02 Jun 2023 01:29

Repository Staff Only: item control page