ERA5¶
ECMWF’s global reanalysis used as a high-resolution meteorological baseline for hazard experiments.
Overview¶
ERA5 is ECMWF’s fifth-generation global reanalysis, combining historical observations with a modern data assimilation system to produce temporally consistent atmospheric fields.
PyHazards uses ERA5 as a shared meteorological baseline for flood, wildfire, and weather-aware graph workflows, including the HydroGraphNet example path.
At a Glance¶
Provider |
ECMWF / Copernicus Climate Change Service (C3S) |
|---|---|
Hazard Family |
Shared Forcing |
Source Role |
Reanalysis |
Coverage |
Global |
Geometry |
Regular latitude-longitude grid |
Spatial Resolution |
~0.25 deg x 0.25 deg |
Temporal Resolution |
Hourly |
Update Cadence |
Daily ERA5T updates with about 5-day latency, followed by final validated releases after 2-3 months |
Period of Record |
1940-present |
Formats |
GRIB and NetCDF |
Inspection CLI |
|
Data Characteristics¶
Global hourly fields on a regular latitude-longitude grid.
Single-level products with optional pressure-level and model-level variables.
Common variables include near-surface meteorology, precipitation, radiation, and atmospheric state variables.
Recent dates may mix validated ERA5 with preliminary ERA5T data.
Typical Use Cases¶
Meteorological forcing for flood, wildfire, and extreme-weather prediction models.
Climate variability analysis and environmental feature engineering.
Shared reanalysis input for graph and spatiotemporal benchmark pipelines.
Access¶
Use the links below to access the upstream source or its public documentation.
PyHazards Usage¶
Use the inspection command for direct file validation, then feed local ERA5 files into HydroGraphNet-style helper loaders when you need graph-temporal training inputs.
This dataset is currently documented as an external or inspection-first
source rather than a public load_dataset(...) entrypoint.
Inspection Workflow¶
Use the documented inspection path below to validate local files before training or analysis.
python -m pyhazards.datasets.era5.inspection --path pyhazards/data/era5_subset --max-vars 10
Notes¶
ERA5 is inspection-first in the public catalog; the downstream HydroGraphNet helper is documented here for convenience but is not a
load_dataset(...)registry entry.