Pangu-Weather IFS Reforecast API

GribStream Code: aiwppanguifs

Official source: The CIRA and NOAA GSL AI Weather Prediction archive runs Pangu-Weather from ECMWF IFS analyses for reproducible community evaluation.

Current GribStream coverage: aiwppanguifs begins with the May 27, 2025 00 UTC cycle and grows as new cycles arrive. That timestamp is the defined start of this GribStream series.

Experimental research availability: The registry warns that data may be missing and availability is not guaranteed; the public README says the data are provided as-is and documents earlier publication-timing and directory-structure changes. This evaluation dataset is not an official operational NOAA or ECMWF forecast. Do not make it the sole dependency for availability-sensitive systems: monitor forecasted_at freshness and keep an operational fallback dataset.

Version continuity: Each GribStream code is pinned to the current source-model version. A materially different upstream model version will receive a separate dataset code rather than being silently joined to this history.

Description

Pangu-Weather is a data-driven global model. AIWP runs this variant with IFS from ECMWF IFS analyses and selects a period beginning in January 2022 to avoid overlap with model training or fine-tuning.

The Pangu-Weather paper describes its design. Pangu-Weather treats pressure levels as a third spatial dimension in a 3D Earth-specific transformer and uses prediction networks for 1, 3, 6, and 24-hour advances. Published results describe specific experiments and do not guarantee performance for this current archive.

The Pangu-Weather inventory covers 2 metre temperature, 10 metre wind and mean sea-level pressure, plus geopotential, temperature, wind and specific humidity on 13 pressure levels. These fields support analysis of large-scale circulation, thermal structure, moisture transport, and weather-system evolution.

The aiwppangu variant uses the other initial-condition system. Comparing them helps study sensitivity to the starting state, but does not isolate model quality by itself: GFS and IFS are different analysis systems. This page covers IFS.

This deterministic product does not quantify forecast uncertainty and does not include precipitation, clouds, radiation, or surface fluxes. For operational decisions, compare it with current authoritative guidance. The team asks users to cite the AIWP archive paper.

Detail

• Archive begins: 2025-05-27
• Official AIWP dataset registry: https://registry.opendata.aws/aiwp/
• Key features:
  • Complete 1,440 by 721 global grid: 1,038,240 cells at 0.25 degree spacing.
  • 00 and 12 UTC cycles with forecast hours 0 through 240 at 6-hour intervals.
  • 9 source variable names and 69 exact selectors: 2 metre temperature, 10 metre wind and mean sea-level pressure, plus geopotential, temperature, wind and specific humidity on 13 pressure levels.
  • Published names, levels, float32 values, and units remain unchanged; the generated inventory documents every selector.
• Resolution: Regular global 0.25 degree grid with 1,440 longitudes by 721 latitudes.
• Temporal coverage: 00 and 12 UTC cycles; 6-hour steps through 240 hours, or 10 days.
• Primary uses: AI-model evaluation, initial-condition comparison, forecast verification, synoptic analysis, wind and temperature studies, cyclone research, and machine-learning benchmarks.

Related datasets

• The same model with the other initial-condition system
• GFS for NOAA operational global guidance
• IFS Oper for ECMWF operational global guidance

Parameters