Comment on egusphere-2025-4716

Read full text
Authors: Gabriel Ionut Moldovan, Ewan Pinnington, Ana Prieto Nemesio, Simon T. K. Lang, Zied Ben Bouallègue, Jesper Sören Dramsch, Mihai Alexe, Mario Santa Cruz, Sara Hahner, Harrison Cook, Helen Theissen, Mariana Clare
+9 more Cathal O’Brien, Jan Polster, Linus Magnusson, Gert Mertes, Florian Pinault, Baudouin Raoult, Patricia de Rosnay, RICHARD M. FORBES, Matthew Chantry
Cited by: 0

Abstract

Abstract. 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.

Fields of Study & Subjects

Meteorological Phenomena and Simulations Hydrological Forecasting Using AI Traffic Prediction and Management Techniques

Publication details

Publication date
11 February 2026
Language
EN