---
title: ERA5 (Copernicus Climate Change Service)
summary: ECMWF's reanalysis of the global weather since 1940, produced for the EU's Copernicus programme: the training set of most machine-learned models.
mount: <div class="card"><p class="kicker">Open data and APIs</p><div class="wx-scroll" tabindex="0"><svg class="mg" viewBox="0 0 994 176" width="994" height="176" role="img" aria-label="ERA5 (Copernicus Climate Change Service): what it is connected to"><style>.mg text{font:12px var(--sans);fill:var(--ink)}.mg .mg-sub,.mg .mg-verb{font-size:10px;fill:var(--ink-2)}.mg-node rect{fill:var(--surface);stroke:var(--line-2)}.mg-node.me rect{stroke:var(--focus);stroke-width:2}.mg-node.unstated rect{stroke-dasharray:2 3;fill:var(--paper)}a.mg-node:hover rect,a.mg-node:focus rect{stroke:var(--focus);stroke-width:2}.mg-edge{fill:none;stroke:var(--ink-2);stroke-opacity:.55;stroke-width:1}.mg-edge.unv{stroke-dasharray:5 4}</style><path class="mg-edge" d="M232 23C306 23 306 88 380 88"><title>stated on the page: raw.githubusercontent.com</title></path><text class="mg-verb" x="240" y="19" text-anchor="start">is trained on</text><a class="mg-node " href="model-graphcast.html"><rect x="2" y="8" width="230" height="30" rx="4"/><text x="9" y="21">GraphCast (Google DeepMind)</text><text class="mg-sub" x="9" y="33">Models</text></a><path class="mg-edge" d="M232 63C306 63 306 88 380 88"><title>stated on the page: raw.githubusercontent.com</title></path><text class="mg-verb" x="240" y="59" text-anchor="start">is trained on</text><a class="mg-node " href="model-pangu.html"><rect x="2" y="48" width="230" height="30" rx="4"/><text x="9" y="61">Pangu-Weather (Huawei)</text><text class="mg-sub" x="9" y="73">Models</text></a><path class="mg-edge" d="M232 103C306 103 306 88 380 88"><title>stated on the page: raw.githubusercontent.com</title></path><text class="mg-verb" x="240" y="99" text-anchor="start">is trained on</text><a class="mg-node " href="model-aurora.html"><rect x="2" y="88" width="230" height="30" rx="4"/><text x="9" y="101">Aurora (Microsoft)</text><text class="mg-sub" x="9" y="113">Models</text></a><path class="mg-edge" d="M232 143C306 143 306 88 380 88"><title>stated on the page: cds.climate.copernicus.eu</title></path><text class="mg-verb" x="240" y="139" text-anchor="start">publishes</text><a class="mg-node " href="body-ecmwf.html"><rect x="2" y="128" width="230" height="30" rx="4"/><text x="9" y="141">ECMWF</text><text class="mg-sub" x="9" y="153">Bodies</text></a><g class="mg-node me"><rect x="380" y="73" width="230" height="30" rx="4"/><text x="387" y="86">ERA5 (Copernicus Climate Change Ser…</text><text class="mg-sub" x="387" y="98">Open data and APIs</text></g></svg></div><p class="wx-legend meta">Left: what points at it. Right: what it points at. Each line carries its verb; a dashed line was not confirmed on the page cited, or the site does not say; the table below gives the page and the time read for each. <span class="prov">From <a href="data-era5.json">data-era5.json</a></span></p></div>
---
# ERA5 (Copernicus Climate Change Service)

> Kept by incident.meteorology@web-summit.dinis, 11 November 2026, 11:36 UTC

[Where a forecast comes from](../index.md) · Open data and APIs · id `data-era5` · [as data](data-era5.json)

ECMWF's reanalysis of the global weather since 1940, produced for the EU's Copernicus programme: the training set of most machine-learned models.

**Address:** [https://cds.climate.copernicus.eu/datasets/reanalysis-era5-single-levels](https://cds.climate.copernicus.eu/datasets/reanalysis-era5-single-levels) (leaves this site)

## What it is connected to, and who says so

| This | Verb | That | The page that says so | Read | Check |
|---|---|---|---|---|---|
| ERA5 (Copernicus Climate Change Service) | **is what GraphCast (Google DeepMind) is trained on** | [GraphCast (Google DeepMind)](model-graphcast.md) | [raw.githubusercontent.com](https://raw.githubusercontent.com/google-deepmind/graphcast/main/README.md): "the per-model READMEs for model-specific code. ### Training Data Full model training requires downloading the [ERA5] (link) dataset from [ECMWF] (link) best accessed as Zarr via [WeatherBench2] (link)" | 11:28 UTC, 11 Nov | stated on the page |
| ERA5 (Copernicus Climate Change Service) | **is what Pangu-Weather (Huawei) is trained on** | [Pangu-Weather (Huawei)](model-pangu.md) | [raw.githubusercontent.com](https://raw.githubusercontent.com/198808xc/Pangu-Weather/main/README.md): "0.25 degrees. For each 721x1440 slice, the data format is exactly the same as the `.nc` file download from the ERA5 official website. Note that the numpy arrays should be in single precision (`.astype(np.float32)`), not " | 11:28 UTC, 11 Nov | stated on the page |
| ERA5 (Copernicus Climate Change Service) | **is what Aurora (Microsoft) is trained on** | [Aurora (Microsoft)](model-aurora.md) | [raw.githubusercontent.com](https://raw.githubusercontent.com/microsoft/aurora/main/README.md): "examples.] (link) You can also directly go to [a full-fledged example that runs the model on ERA5] (link) Cite us as follows: ``` @article{bodnar2025aurora, title = {A Foundation Model for the Earth System}, author =" | 11:28 UTC, 11 Nov | stated on the page |
| ERA5 (Copernicus Climate Change Service) | **published by** | [ECMWF](body-ecmwf.md) | [cds.climate.copernicus.eu](https://cds.climate.copernicus.eu/datasets/reanalysis-era5-single-levels): "ERA5 hourly data on single levels from 1940 to present Login - Register Web portal menu Climate Data Store User menu Datasets User guide Applications Forum Live status Login" | 11:29 UTC, 11 Nov | stated on the page |

## Licence: what we may do with it

**Copernicus Climate Change Service (ERA5)**: CC BY 4.0 (stated on the data set's page) ([cds.climate.copernicus.eu](https://cds.climate.copernicus.eu/datasets/reanalysis-era5-single-levels), read 11:29 UTC, 11 Nov, stated on the page).

| Read | Store | Show | Transform | Attribution |
|---|---|---|---|---|
| yes, with a free account | yes | yes, with attribution | yes, with attribution | "Contains modified Copernicus Climate Change Service information [year]". |

A reanalysis: it lags real time by about five days, so it will show Charles only afterwards.


## What it offers for Lisbon and Madeira this week

The best consistent record of what the weather was, hourly, at 0.25°: for comparing Charles with earlier storms afterwards.

- **Endpoint:** `https://cds.climate.copernicus.eu/datasets/reanalysis-era5-single-levels`
- **Key:** a free account and key
- **Format:** GRIB or NetCDF through the CDS API
- **Size:** about 1 MB per variable per day for a small box
- **Cadence:** daily, about five days behind real time
- **This week** (probe read 02:29 UTC, 11 Nov): Not available for 10 to 12 November until about 16 November.

---
Not a warning service: this page explains where data comes from. For warnings follow [IPMA](https://www.ipma.pt/pt/otempo/prev-sam/) and ANEPC.