An update to ECMWF's machine-learned weather forecast model AIFS

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Moldovan, Gabriel, Pinnington, Ewan, Nemesio, Ana Prieto, Lang, Simon, Bouallègue, Zied Ben, Dramsch, Jesper, Alexe, Mihai, Cruz, Mario Santa, Hahner, Sara, Cook, Harrison, Theissen, Helen, Clare, Mariana, O'Brien, Cathal, Polster, Jan, Magnusson, Linus, Mertes, Gert, Pinault, Florian, Raoult, Baudouin, de Rosnay, Patricia, Forbes, Richard, Chantry, Matthew
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866909802418929664
author Moldovan, Gabriel
Pinnington, Ewan
Nemesio, Ana Prieto
Lang, Simon
Bouallègue, Zied Ben
Dramsch, Jesper
Alexe, Mihai
Cruz, Mario Santa
Hahner, Sara
Cook, Harrison
Theissen, Helen
Clare, Mariana
O'Brien, Cathal
Polster, Jan
Magnusson, Linus
Mertes, Gert
Pinault, Florian
Raoult, Baudouin
de Rosnay, Patricia
Forbes, Richard
Chantry, Matthew
author_facet Moldovan, Gabriel
Pinnington, Ewan
Nemesio, Ana Prieto
Lang, Simon
Bouallègue, Zied Ben
Dramsch, Jesper
Alexe, Mihai
Cruz, Mario Santa
Hahner, Sara
Cook, Harrison
Theissen, Helen
Clare, Mariana
O'Brien, Cathal
Polster, Jan
Magnusson, Linus
Mertes, Gert
Pinault, Florian
Raoult, Baudouin
de Rosnay, Patricia
Forbes, Richard
Chantry, Matthew
contents We present an update to ECMWF's machine-learned weather forecasting model AIFS Single with several key improvements. The model now incorporates physical consistency constraints through bounding layers, an updated training schedule, and an expanded set of variables. The physical constraints substantially improve precipitation forecasts and the new variables show a high level of skill. Upper-air headline scores also show improvement over the previous AIFS version. The AIFS has been fully operational at ECMWF since the 25th of February 2025.
format Preprint
id arxiv_https___arxiv_org_abs_2509_18994
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle An update to ECMWF's machine-learned weather forecast model AIFS
Moldovan, Gabriel
Pinnington, Ewan
Nemesio, Ana Prieto
Lang, Simon
Bouallègue, Zied Ben
Dramsch, Jesper
Alexe, Mihai
Cruz, Mario Santa
Hahner, Sara
Cook, Harrison
Theissen, Helen
Clare, Mariana
O'Brien, Cathal
Polster, Jan
Magnusson, Linus
Mertes, Gert
Pinault, Florian
Raoult, Baudouin
de Rosnay, Patricia
Forbes, Richard
Chantry, Matthew
Atmospheric and Oceanic Physics
We present an update to ECMWF's machine-learned weather forecasting model AIFS Single with several key improvements. The model now incorporates physical consistency constraints through bounding layers, an updated training schedule, and an expanded set of variables. The physical constraints substantially improve precipitation forecasts and the new variables show a high level of skill. Upper-air headline scores also show improvement over the previous AIFS version. The AIFS has been fully operational at ECMWF since the 25th of February 2025.
title An update to ECMWF's machine-learned weather forecast model AIFS
topic Atmospheric and Oceanic Physics
url https://arxiv.org/abs/2509.18994