Can Scene-Level NWP Cloud Cover Replace Expert Pixel Labels? A Large-Scale Assessment with ERA5, GFS and CloudSEN12+

Deep learning cloud detectors require large volumes of pixel-level labels that are expensive to produce. Gridded cloud cover from ERA5 reanalysis and GFS forecasts could serve as freely available weak supervision. We assess this hypothesis through a large-scale comparison of NWP total cloud cover with expert-annotated cloud masks from CloudSEN12+ (Sentinel-2, 10m) over 48,000 globally distributed samples (2017–2022). ERA5 shows moderate agreement (r=0.42, MAE ∼30%), with performance strongly dependent on cloud type. We then train U-Net cloud segmentation models that differ only in the source of their labels, on a region-disjoint partition of the dataset, and evaluate them on 975 held-out expert-annotated patches. Expert labels yield a binary cloud IoU of 0.78 and a scene-level accuracy of 0.92, against 0.47 and 0.71 for ERA5-derived weak labels. Increasing the weak supervision from 200 to 20,000 patches produces no systematic improvement over the tested range, which suggests that, for this label formulation, the limitation lies in what each label expresses rather than in how many are available; 849 expert-annotated patches outperform 20,000 weakly labelled ones. Pretraining on ERA5 labels and fine-tuning on expert masks is worse than training from scratch at every annotation budget that we tested. Training on ERA5 labels does improve on applying the same labels directly as a mask, from 0.38 to 0.47 in binary cloud IoU, and the resulting model remains usable for coarse scene-level screening where no pixel-level annotation exists. Results provide practical guidelines for leveraging NWP products in deep learning training pipelines where expert annotations are scarce.

Authors

Institutions

Publication Details

Journal
Applied Sciences
Published
2026-11-18
DOI
https://doi.org/10.3390/app162211444
Primary Topic
Advanced Neural Network Applications
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Can Scene-Level NWP Cloud Cover Replace Expert Pixel Labels? A Large-Scale Assessment with ERA5, GFS and CloudSEN12+

A. Anzalone, Antonio Pagliaro
Applied Sciences
Advanced Neural Network Applications
article

Can Scene-Level NWP Cloud Cover Replace Expert Pixel Labels? A Large-Scale Assessment with ERA5, GFS and CloudSEN12+

A. Anzalone, Antonio Pagliaro
article en

Abstract

Deep learning cloud detectors require large volumes of pixel-level labels that are expensive to produce. Gridded cloud cover from ERA5 reanalysis and GFS forecasts could serve as freely available weak supervision. We assess this hypothesis through a large-scale comparison of NWP total cloud cover with expert-annotated cloud masks from CloudSEN12+ (Sentinel-2, 10m) over 48,000 globally distributed samples (2017–2022). ERA5 shows moderate agreement (r=0.42, MAE ∼30%), with performance strongly dependent on cloud type. We then train U-Net cloud segmentation models that differ only in the source of their labels, on a region-disjoint partition of the dataset, and evaluate them on 975 held-out expert-annotated patches. Expert labels yield a binary cloud IoU of 0.78 and a scene-level accuracy of 0.92, against 0.47 and 0.71 for ERA5-derived weak labels. Increasing the weak supervision from 200 to 20,000 patches produces no systematic improvement over the tested range, which suggests that, for this label formulation, the limitation lies in what each label expresses rather than in how many are available; 849 expert-annotated patches outperform 20,000 weakly labelled ones. Pretraining on ERA5 labels and fine-tuning on expert masks is worse than training from scratch at every annotation budget that we tested. Training on ERA5 labels does improve on applying the same labels directly as a mask, from 0.38 to 0.47 in binary cloud IoU, and the resulting model remains usable for coarse scene-level screening where no pixel-level annotation exists. Results provide practical guidelines for leveraging NWP products in deep learning training pipelines where expert annotations are scarce.

Applied SciencesVol. 16(22)
Istituto Nazionale di Fisica Nucleare, Sezione di Catania (IT), Istituto di Astrofisica Spaziale e Fisica cosmica di Palermo (IT), Fondazione ICSC Centro Nazionale di Ricerca in High Performance Computing, Big Data e Quantum Computing (IT), National Institute for Astrophysics (IT)
Climate action
Advanced Neural Network Applications
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon