Salvato in:
Dettagli Bibliografici
Autori principali: Guo, Edison, Ahmed, Maruf, Sun, Yue, Yang, Rui, Cook, Harrison, Leeuwenburg, Tennessee, Evans, Ben
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:https://arxiv.org/abs/2401.05584
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866911806547558400
author Guo, Edison
Ahmed, Maruf
Sun, Yue
Yang, Rui
Cook, Harrison
Leeuwenburg, Tennessee
Evans, Ben
author_facet Guo, Edison
Ahmed, Maruf
Sun, Yue
Yang, Rui
Cook, Harrison
Leeuwenburg, Tennessee
Evans, Ben
contents 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
format Preprint
id arxiv_https___arxiv_org_abs_2401_05584
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle FourCastNeXt: Optimizing FourCastNet Training for Limited Compute
Guo, Edison
Ahmed, Maruf
Sun, Yue
Yang, Rui
Cook, Harrison
Leeuwenburg, Tennessee
Evans, Ben
Computer Vision and Pattern Recognition
Artificial Intelligence
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
title FourCastNeXt: Optimizing FourCastNet Training for Limited Compute
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2401.05584