Work

AIFS-DOP: End-to-End Medium-Range Weather Prediction from Observations Alone with Machine Learning

Year: 2026

Type: preprint

Abstract: We introduce the Artificial Intelligence Forecasting System for Direct Observation Prediction (AIFS-DOP). AIFS-DOP is trained on a 40-year harmonized dataset of gridded observations, without using numerical weather prediction (NWP) reanalysis or model data. The resulting model is competitive with ECMWF's Integrated Forecasting System (IFS) when scored on a one year period of forecasts across 2021/2022. This progress on Direct Observation Prediction represents the first time that a data-driven model, trained solely on observations, is competitive with the IFS at medium ranges for several key upper-air and surface headline scores, when verified against observation data.

Source: arXiv (Cornell University)

DOI: 10.48550/arxiv.2606.19093

Authors: Pinnington, Ewan, Lean, Peter, Alexe, Mihai, Boucher, Eulalie, Lang, Simon, Laloyaux, Patrick, Mertes, Gert, Kral, Tomas, de Rosnay, Patricia, Chantry, Matthew, McNally, Anthony

Institution: European Centre for Medium-Range Weather Forecasts

Language: English

Topic: Meteorological Phenomena and Simulations

Subfield: Atmospheric Science

Field: Earth and Planetary Sciences

Domain: Physical Sciences

SDG: Climate action

Open Access status: green

Funders: European Commission, Partnership for Advanced Computing in Europe AISBL, European Organization for the Exploitation of Meteorological Satellites

OpenAlex ID: W7165147083

Cites: 23

Cited by: 8

Related to: 10