Model Overview

Description

FourCastNet2 uses Spherical Fourier Neural Operator (SFNO) to predict a collection of surface and atmospheric variables such as wind speed, temperature and pressure and is applied to forecasting global atmospheric dynamics.

FourCastNet is a data-driven model that provides accurate short to medium-range global predictions at a time-step size of 6 hours with predictive stability for over a year of simulated time (1,460 steps), while retaining physically plausible dynamics.

This model is ready for commercial use.

Reference(s)

• Spherical Fourier Neural Operator Paper
  
• FourCastNet Paper
  
• Codebase
  
• The ERA5 global reanalysis
  

Model Architecture

Architecture Type: Neural Operator
Network Architecture: FourCastNet SFNO

Input

Input Type(s):

• Tensor (73 Surface & Atmospheric Variables)
• DateTime
  

Input Format(s): NumPy
Input Parameters:

• Four Dimensional (4D) (batch, variable, latitude, longitude)
  
• Input DateTime
  

Other Properties Related to Input:

• 0.25 degree latitude-longitude grid
• Input resolution: [721, 1440]
• Latitude Coordinates: [90, 89.75, 89.5, ..., -89.5, -89.75, -90]
• Longitude Coordinates: [0, 0.25, 0.5, ..., 359.25, 359.5, 359.75]
• Input weather variables: "u10m", "v10m", "u100m", "v100m", "t2m", "sp", "msl", "tcwv", "u50", "u100", "u150", "u200", "u250", "u300", "u400", "u500", "u600", "u700", "u850", "u925", "u1000", "v50", "v100", "v150", "v200", "v250", "v300", "v400", "v500", "v600", "v700", "v850", "v925", "v1000", "z50", "z100", "z150", "z200", "z250", "z300", "z400", "z500", "z600", "z700", "z850", "z925", "z1000", "t50", "t100", "t150", "t200", "t250", "t300", "t400", "t500", "t600", "t700", "t850", "t925", "t1000", "q50", "q100", "q150", "q200", "q250", "q300", "q400", "q500", "q600", "q700", "q850", "q925", "q1000"
  

Output

Output Type(s):

• Tensor (73 Surface & Atmospheric Variables)

Output Format(s): NumPy
Output Parameters:

• Four Dimensional (4D) (batch, variable, latitude, longitude)
  

Other Properties Related to Output:

• Time-delta of 6 hours from input array
• 0.25 degree latitude-longitude grid
• Output resolution: [721, 1440]
• Latitude Coordinates: [90, 89.75, 89.5, ..., -89.5, -89.75, -90]
• Longitude Coordinates: [0, 0.25, 0.5, ..., 359.25, 359.5, 359.75]
• Output weather variables: "u10m", "v10m", "u100m", "v100m", "t2m", "sp", "msl", "tcwv", "u50", "u100", "u150", "u200", "u250", "u300", "u400", "u500", "u600", "u700", "u850", "u925", "u1000", "v50", "v100", "v150", "v200", "v250", "v300", "v400", "v500", "v600", "v700", "v850", "v925", "v1000", "z50", "z100", "z150", "z200", "z250", "z300", "z400", "z500", "z600", "z700", "z850", "z925", "z1000", "t50", "t100", "t150", "t200", "t250", "t300", "t400", "t500", "t600", "t700", "t850", "t925", "t1000", "q50", "q100", "q150", "q200", "q250", "q300", "q400", "q500", "q600", "q700", "q850", "q925", "q1000"
  

Software Integration

Runtime Engine(s): Not Applicable
Supported Hardware Microarchitecture Compatibility:

• Ampere
  
• Hopper
  
• Turing
  

Supported Operating System(s):

• Linux
  

Model Version(s)

Model version: v1

Training, Testing, and Evaluation Datasets:

Training Dataset

Link: ERA5

Data Collection Method by dataset

• Automatic/Sensors
  

Labeling Method by dataset

• Automatic/Sensors
  

Properties (Quantity, Dataset Descriptions, Sensor(s)): ERA5 data for the years of 1979-2017. ERA5 provides hourly estimates of various atmospheric, land, and oceanic climate variables. The data covers the Earth on a 30km grid and resolves the atmosphere at 137 levels.

Evaluation Dataset

Link: ERA5

Data Collection Method by dataset

• Automatic/Sensors
  

Labeling Method by dataset

• Automatic/Sensors
  

Properties (Quantity, Dataset Descriptions, Sensor(s)): ERA5 data for the year of 2018. ERA5 provides hourly estimates of various atmospheric, land, and oceanic climate variables. The data covers the Earth on a 30km grid and resolves the atmosphere at 137 levels.

Inference:

Engine: Triton
Test Hardware:

• A100
  
• H100
  
• L40S
  
• RTX6000
  

Ethical Considerations:

NVIDIA believes Trustworthy AI is a shared responsibility and we have established policies and practices to enable development for a wide array of AI applications. When downloaded or used in accordance with our terms of service, developers should work with their supporting model team to ensure this model meets requirements for the relevant industry and use case and addresses unforeseen product misuse. For more detailed information on ethical considerations for this model, please see the Model Card++ Explainability, Bias, Safety & Security, and Privacy Subcards here. Please report security vulnerabilities or NVIDIA AI Concerns here.

License

This model is licensed under the NVIDIA AI Product Agreement. By pulling and using this model, you accept the terms and conditions of this license.

You are responsible for ensuring that your use of NVIDIA AI Foundation Models complies with all applicable laws.