activity
20242026
collaborators

6 papers

physics.ao-ph2026

Representing the Surface Ocean in ECMWF's data-driven forecasting system AIFS

Sara Hahner, Lorenzo Zampieri, Jean-Raymond Bidlot +22

Machine-learning (ML) models, such as the AIFS at the ECMWF, have revolutionised weather forecasting in recent years. We present an extension of the AIFS that jointly models the at…

physics.ao-ph2026

Downscaling weather forecasts from Low- to High-Resolution with Diffusion Models

Joffrey Dumont Le Brazidec, Simon Lang, Martin Leutbecher +9

We introduce a probabilistic diffusion-based method for global atmospheric downscaling implemented within the Anemoi framework. The approach transforms low-resolution ensemble fore…

physics.ao-ph2026

AIFS-COMPO: A Global Data-Driven Atmospheric Composition Forecasting System

Paula Harder, Johannes Flemming, Mihai Alexe +3

We introduce AIFS-COMPO, a skilful medium-range data-driven global forecasting system for aerosols and reactive gases. Building on the ECMWF Artificial Intelligence Forecast System…

physics.ao-ph2025

Observation-guided Interpolation Using Graph Neural Networks for High-Resolution Nowcasting in Switzerland

Ophélia Miralles, Daniele Nerini, Jonas Bhend +2

Recent advances in neural weather forecasting have shown significant potential for accurate short-term forecasts. However, adapting such gridded approaches to smaller, topographica…

physics.ao-ph2025

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

Gabriel Moldovan, Ewan Pinnington, Ana Prieto Nemesio +18

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 thr…

physics.ao-ph2024

AIFS-CRPS: Ensemble forecasting using a model trained with a loss function based on the Continuous Ranked Probability Score

Simon Lang, Mihai Alexe, Mariana C. A. Clare +15

Over the last three decades, ensemble forecasts have become an integral part of forecasting the weather. They provide users with more complete information than single forecasts as…