README.md

metadata

license: mit

Global Data-driven High-resolution Weather Model

This is a global data-driven high-resolution weather model implemented and open sourced by High-Flyer AI. It is the first AI weather model, which can compare with the ECMWF Integrated Forecasting System (IFS).

Typhoon track comparison:

Water vapour comparison:

Requirements

• hfai
• torch >=1.8

Training

The raw data is from the public dataset, ERA5 , which is integrated into the dataset warehouse, hfai.datasets.

submit these tasks to Yinghuo HPC:

1. pretrain backbone.pt

    hfai python train/pretrain.py -- -n 8 -p 30
   

2. finetune backbone.pt

    hfai python train/fine_tune.py -- -n 8 -p 30
   

3. train precipitation.pt

    hfai python train/precipitation.py -- -n 8 -p 30
   

Citation

@article{pathak2022fourcastnet,
  title={Fourcastnet: A global data-driven high-resolution weather model using adaptive fourier neural operators},
  author={Pathak, Jaideep and Subramanian, Shashank and Harrington, Peter and Raja, Sanjeev and Chattopadhyay, Ashesh and Mardani, Morteza and Kurth, Thorsten and Hall, David and Li, Zongyi and Azizzadenesheli, Kamyar and others},
  journal={arXiv preprint arXiv:2202.11214},
  year={2022}
}