_version_ 1866914072324210688
author Daub, Eric G.
Dunstan, Tom
Bennett, Thusal
Burnand, Matthew
Chappell, James
Coca-Castro, Alejandro
Eftekhari, Noushin
Hosking, J. Scott
Janmaijaya, Manvendra
Lillis, Jon
Salvador-Jasin, David
Simpson, Nathan
Strickson, Oliver T
Chan, Ryan Sze-Yin
Elmasri, Mohamad
France, Lydia Allegranza
Madge, Sam
Owen, Aled
Robinson, James
Scaife, Adam A.
Walters, David
Yatsyshin, Peter
McCaie, Theo
Bokeria, Levan
Brown, Hannah
Dodds, Tom
Llewellyn-Jones, David
Moreton, Sophia
Potter, Tom
Stenson, Iain
van Zeeland, Louisa
Bett-Williams, Karina
Dale, Kirstine Ida
author_facet Daub, Eric G.
Dunstan, Tom
Bennett, Thusal
Burnand, Matthew
Chappell, James
Coca-Castro, Alejandro
Eftekhari, Noushin
Hosking, J. Scott
Janmaijaya, Manvendra
Lillis, Jon
Salvador-Jasin, David
Simpson, Nathan
Strickson, Oliver T
Chan, Ryan Sze-Yin
Elmasri, Mohamad
France, Lydia Allegranza
Madge, Sam
Owen, Aled
Robinson, James
Scaife, Adam A.
Walters, David
Yatsyshin, Peter
McCaie, Theo
Bokeria, Levan
Brown, Hannah
Dodds, Tom
Llewellyn-Jones, David
Moreton, Sophia
Potter, Tom
Stenson, Iain
van Zeeland, Louisa
Bett-Williams, Karina
Dale, Kirstine Ida
contents We present FastNet version 1.0, a data-driven medium range numerical weather prediction (NWP) model based on a Graph Neural Network architecture, developed jointly between the Alan Turing Institute and the Met Office. FastNet uses an encode-process-decode structure to produce deterministic global weather predictions out to 10 days. The architecture is independent of spatial resolution and we have trained models at 1$^{\circ}$ and 0.25$^{\circ}$ resolution, with a six hour time step. FastNet uses a multi-level mesh in the processor, which is able to capture both short-range and long-range patterns in the spatial structure of the atmosphere. The model is pre-trained on ECMWF's ERA5 reanalysis data and then fine-tuned on additional autoregressive rollout steps, which improves accuracy over longer time horizons. We evaluate the model performance at 1.5$^{\circ}$ resolution using 2022 as a hold-out year and compare with the Met Office Global Model, finding that FastNet surpasses the skill of the current Met Office Global Model NWP system using a variety of evaluation metrics on a number of atmospheric variables. Our results show that both our 1$^{\circ}$ and 0.25$^{\circ}$ FastNet models outperform the current Global Model and produce results with predictive skill approaching those of other data-driven models trained on 0.25$^{\circ}$ ERA5.
format Preprint
id arxiv_https___arxiv_org_abs_2509_17658
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Technical overview and architecture of the FastNet Machine Learning weather prediction model, version 1.0
Daub, Eric G.
Dunstan, Tom
Bennett, Thusal
Burnand, Matthew
Chappell, James
Coca-Castro, Alejandro
Eftekhari, Noushin
Hosking, J. Scott
Janmaijaya, Manvendra
Lillis, Jon
Salvador-Jasin, David
Simpson, Nathan
Strickson, Oliver T
Chan, Ryan Sze-Yin
Elmasri, Mohamad
France, Lydia Allegranza
Madge, Sam
Owen, Aled
Robinson, James
Scaife, Adam A.
Walters, David
Yatsyshin, Peter
McCaie, Theo
Bokeria, Levan
Brown, Hannah
Dodds, Tom
Llewellyn-Jones, David
Moreton, Sophia
Potter, Tom
Stenson, Iain
van Zeeland, Louisa
Bett-Williams, Karina
Dale, Kirstine Ida
Atmospheric and Oceanic Physics
We present FastNet version 1.0, a data-driven medium range numerical weather prediction (NWP) model based on a Graph Neural Network architecture, developed jointly between the Alan Turing Institute and the Met Office. FastNet uses an encode-process-decode structure to produce deterministic global weather predictions out to 10 days. The architecture is independent of spatial resolution and we have trained models at 1$^{\circ}$ and 0.25$^{\circ}$ resolution, with a six hour time step. FastNet uses a multi-level mesh in the processor, which is able to capture both short-range and long-range patterns in the spatial structure of the atmosphere. The model is pre-trained on ECMWF's ERA5 reanalysis data and then fine-tuned on additional autoregressive rollout steps, which improves accuracy over longer time horizons. We evaluate the model performance at 1.5$^{\circ}$ resolution using 2022 as a hold-out year and compare with the Met Office Global Model, finding that FastNet surpasses the skill of the current Met Office Global Model NWP system using a variety of evaluation metrics on a number of atmospheric variables. Our results show that both our 1$^{\circ}$ and 0.25$^{\circ}$ FastNet models outperform the current Global Model and produce results with predictive skill approaching those of other data-driven models trained on 0.25$^{\circ}$ ERA5.
title Technical overview and architecture of the FastNet Machine Learning weather prediction model, version 1.0
topic Atmospheric and Oceanic Physics
url https://arxiv.org/abs/2509.17658