FourCastNeXt: Optimizing FourCastNet Training for Limited Compute
This incremental optimization makes Neural Earth System Modelling more accessible for researchers conducting training experiments and ablation studies by lowering computational barriers.
The paper tackled the high computational cost of training FourCastNet, a global machine learning weather forecasting model, by developing FourCastNeXt, which achieves comparable accuracy while reducing training compute requirements by about 95% (to around 5% of the original).
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