FourCastNet: A Global Data-driven High-resolution Weather Model using Adaptive Fourier Neural Operators

02/22/2022
by   Jaideep Pathak, et al.
64

FourCastNet, short for Fourier Forecasting Neural Network, is a global data-driven weather forecasting model that provides accurate short to medium-range global predictions at 0.25^∘ resolution. FourCastNet accurately forecasts high-resolution, fast-timescale variables such as the surface wind speed, precipitation, and atmospheric water vapor. It has important implications for planning wind energy resources, predicting extreme weather events such as tropical cyclones, extra-tropical cyclones, and atmospheric rivers. FourCastNet matches the forecasting accuracy of the ECMWF Integrated Forecasting System (IFS), a state-of-the-art Numerical Weather Prediction (NWP) model, at short lead times for large-scale variables, while outperforming IFS for variables with complex fine-scale structure, including precipitation. FourCastNet generates a week-long forecast in less than 2 seconds, orders of magnitude faster than IFS. The speed of FourCastNet enables the creation of rapid and inexpensive large-ensemble forecasts with thousands of ensemble-members for improving probabilistic forecasting. We discuss how data-driven deep learning models such as FourCastNet are a valuable addition to the meteorology toolkit to aid and augment NWP models.

READ FULL TEXT

page 3

page 10

page 12

page 13

page 16

page 25

research
08/08/2022

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

Extreme weather amplified by climate change is causing increasingly deva...
research
06/05/2023

SwinRDM: Integrate SwinRNN with Diffusion Model towards High-Resolution and High-Quality Weather Forecasting

Data-driven medium-range weather forecasting has attracted much attentio...
research
11/03/2022

Pangu-Weather: A 3D High-Resolution Model for Fast and Accurate Global Weather Forecast

In this paper, we present Pangu-Weather, a deep learning based system fo...
research
10/21/2022

DL-Corrector-Remapper: A grid-free bias-correction deep learning methodology for data-driven high-resolution global weather forecasting

Data-driven models, such as FourCastNet (FCN), have shown exemplary perf...
research
05/26/2022

SwinVRNN: A Data-Driven Ensemble Forecasting Model via Learned Distribution Perturbation

Data-driven approaches for medium-range weather forecasting are recently...
research
07/29/2023

Rapid Flood Inundation Forecast Using Fourier Neural Operator

Flood inundation forecast provides critical information for emergency pl...
research
08/18/2020

A Comparative Study of Convolutional Neural Network Models for Wind Field Downscaling

We analyze the applicability of convolutional neural network (CNN) archi...

Please sign up or login with your details

Forgot password? Click here to reset