OneScience/FourCastNet

FourCastNet

Model Introduction

FourCastNet (Fourier Forecasting Neural Network) is a global weather forecast model based on AFNO (Adaptive Fourier Neural Operator), jointly developed by NVIDIA and multiple top-tier academic institutions.

Paper: FourCastNet: A Global Data-driven High-resolution Weather Forecasting Model

https://arxiv.org/abs/2202.11214

Model Description

FourCastNet is a global high-resolution weather forecast model based on the Adaptive Fourier Neural Operator, suitable for short-to-medium-range global weather forecast research.

Use Cases

Scenario	Description
Global Weather Forecast Research	Train a FourCastNet-style AFNO forecast model using annual ERA5 HDF5 data.
Local Quick Validation	Use synthetic data to verify data loading, training entry points, inference, and result scripts.
ModelScope / OneCode Execution	Download as a standalone model package, install dependencies, and run scripts directly.
Multi-GPU Training	Launch multi-process training via torchrun.

Usage Guide

1. OneCode Usage

Experience intelligent one-click AI4S programming through the OneCode online environment:

Click to Experience Intelligent One-Click AI4S Programming

2. Manual Installation and Usage

Hardware Requirements

• A GPU or DCU is recommended.
• CPU can be used for import and small-scale connectivity verification; full training and inference will be slow.
• DCU users must install DTK in advance. DTK 25.04.2 or above, or the OneScience recommended version matching your cluster, is recommended.

Download the Model Package

modelscope download --model OneScience/FourCastNet --local_dir ./FourCastNet
cd FourCastNet

Install the Runtime Environment

DCU Environment

# Please activate DTK and CONDA first
conda create -n onescience311 python=3.11 -y
conda activate onescience311
# uv installation is supported
pip install onescience[earth-dcu] -i http://mirrors.onescience.ai:3141/pypi/simple/  --trusted-host mirrors.onescience.ai

GPU Environment

# Please activate CONDA first
conda create -n onescience311 python=3.11 -y libstdcxx-ng=12 libgcc-ng=12 gcc_linux-64=12 gxx_linux-64=12
conda activate onescience311
# uv installation is supported
pip install onescience[earth-gpu] -i http://mirrors.onescience.ai:3141/pypi/simple/  --trusted-host mirrors.onescience.ai

Training Data Introduction

The OneScience community provides ERA5 data for training (due to file size limits, the current repository contains a slice of the full dataset). Users can download it with the command below and confirm that the data path in conf/config.yaml is set correctly:

modelscope download --dataset OneScience/ERA5 --local_dir ./data

Training

Single GPU:

python scripts/train.py

Multi-GPU:

torchrun --nproc_per_node=8 --nnodes=1 --rdzv_id=1000 --rdzv_backend=c10d --max_restarts=0 --master_addr="localhost" --master_port=29500 scripts/train.py

Training outputs:

data/checkpoints/model_bak.pth
data/checkpoints/trloss.npy
data/checkpoints/valoss.npy

Training Weights

This repository provides weights trained on ERA5 reanalysis data in the weights/ folder. The weight files will be uploaded soon and are expected to be available in the near future.

Inference

Inference reads data/checkpoints/model_bak.pth by default:

python scripts/inference.py

Prediction results are output to:

result/output/

Evaluation and Visualization

python scripts/result.py

Output contents include:

• result/rmse.npy
• result/acc.npy
• result/loss.png
• Forecast comparison plots for specified dates and variables

OneScience Official Information

Platform	OneScience Main Repository	Skills Repository
Gitee	https://gitee.com/onescience-ai/onescience	https://gitee.com/onescience-ai/oneskills
GitHub	https://github.com/onescience-ai/OneScience	https://github.com/onescience-ai/oneskills

Citation & License

• This repository is an independent reproduction of FourCastNet, with the architecture design adapted from the original paper by Pathak et al. (2022).