FourCastNeXt is an optimization of FourCastNet - a global machine learning weather forecasting model - that performs with a comparable level of accuracy and can be trained using around 5% of the original FourCastNet computational requirements. This technical report presents strategies for model optimization that maintain similar performance as measured by the root-mean-square error (RMSE) of the modelled variables. By providing a model with very low comparative training costs, FourCastNeXt makes Neural Earth System Modelling much more accessible to researchers looking to conduct training experiments and ablation studies. FourCastNeXt training and inference code are available at https://github.com/nci/FourCastNeXt
@article{arxiv.2401.05584,
title = {FourCastNeXt: Optimizing FourCastNet Training for Limited Compute},
author = {Edison Guo and Maruf Ahmed and Yue Sun and Rui Yang and Harrison Cook and Tennessee Leeuwenburg and Ben Evans},
journal= {arXiv preprint arXiv:2401.05584},
year = {2024}
}
Comments
Major revision. All prior content (text, figures, table) has been updated. Additionally, new text, tables and figures have been added. Updated title. Updated author list