Error in ERA5 2m Temperature identified using GraphCast

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Christensen, Hannah M., Barker, Jack, Antonio, Bobby, Bonavita, Massimo, Dahoui, Mohamed, de Rosnay, Patricia
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866911360575602688
author Christensen, Hannah M.
Barker, Jack
Antonio, Bobby
Bonavita, Massimo
Dahoui, Mohamed
de Rosnay, Patricia
author_facet Christensen, Hannah M.
Barker, Jack
Antonio, Bobby
Bonavita, Massimo
Dahoui, Mohamed
de Rosnay, Patricia
contents Reanalyses such as ERA5 have long been foundational for weather and climate science. They have also found a new use case, as training and verification data for machine-learnt weather prediction (MLWP) models. Here we compare short-lead time (6h) forecasts from the MLWP model GraphCast against ERA5. In doing so, we identify a recurrent, spatially coherent error in 2m Temperature centred on the Ethiopian Highlands, that occurs predominantly at 0600 UTC. We show that these error events are not an error in the forecast from GraphCast, but are in fact an error in ERA5, and are also present in the ECMWF operational analysis. They arise from the 2D optimal interpolation procedure, when surface reports are assimilated that are temporally displaced compared to the background forecast. This produces spuriously warm analysis increments over Ethiopia on approximately 7\% of dates at 0600 UTC across the reanalysis record. The spread from the ensemble of data assimilation partially flags these cases but is underdispersive. We assess the impact on GraphCast, which was trained on ERA5. While GraphCast can largely ignore these unphysical error events, a small systematic degradation in forecast skill over the region is observed. We discuss implications for using reanalysis as truth in machine learning training and verification, and recommend simple changes to reduce such artefacts in future analyses.
format Preprint
id arxiv_https___arxiv_org_abs_2601_04701
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Error in ERA5 2m Temperature identified using GraphCast
Christensen, Hannah M.
Barker, Jack
Antonio, Bobby
Bonavita, Massimo
Dahoui, Mohamed
de Rosnay, Patricia
Atmospheric and Oceanic Physics
Reanalyses such as ERA5 have long been foundational for weather and climate science. They have also found a new use case, as training and verification data for machine-learnt weather prediction (MLWP) models. Here we compare short-lead time (6h) forecasts from the MLWP model GraphCast against ERA5. In doing so, we identify a recurrent, spatially coherent error in 2m Temperature centred on the Ethiopian Highlands, that occurs predominantly at 0600 UTC. We show that these error events are not an error in the forecast from GraphCast, but are in fact an error in ERA5, and are also present in the ECMWF operational analysis. They arise from the 2D optimal interpolation procedure, when surface reports are assimilated that are temporally displaced compared to the background forecast. This produces spuriously warm analysis increments over Ethiopia on approximately 7\% of dates at 0600 UTC across the reanalysis record. The spread from the ensemble of data assimilation partially flags these cases but is underdispersive. We assess the impact on GraphCast, which was trained on ERA5. While GraphCast can largely ignore these unphysical error events, a small systematic degradation in forecast skill over the region is observed. We discuss implications for using reanalysis as truth in machine learning training and verification, and recommend simple changes to reduce such artefacts in future analyses.
title Error in ERA5 2m Temperature identified using GraphCast
topic Atmospheric and Oceanic Physics
url https://arxiv.org/abs/2601.04701