# Weather in three dimensions.

Pangu-Weather demonstrated medium-range forecasting with three-dimensional neural networks.

Canonical: https://brightaifuture.com/discoveries/pangu
Format: discovery
Source publication: 2023-07-05
Bright publication: 2026-09-05
Substantive update: None recorded
Evidence and review: Demonstrated; confidence: unassessed; source-checked; legacy source check. Legacy source check; no named human reviewer is recorded in this projection.

## The human problem

Forecasting must capture conditions across atmospheric layers.

## The prior constraint

Traditional systems numerically integrate physical equations.

## AI’s actual role

A three-dimensional architecture learned spatial weather relationships.

## The documented result

The paper reported strong forecast accuracy and computational speed.

## Why it may matter

Another route toward more accessible forecasting tools.

## Limitations

The evaluation does not prove better decisions or preparedness.

## Unresolved questions

Validate unusual weather and distribution shifts.

## Provenance and history

{
  "dates": {
    "eventDate": null,
    "publicationDate": "2023-07-05",
    "captureDate": null,
    "lastReviewedDate": "2026-09-05"
  },
  "provenance": {
    "origin": "legacy-projection",
    "externalId": "pangu"
  },
  "revisions": [],
  "corrections": []
}

## Original sources

- [Accurate medium-range global weather forecasting with 3D neural networks](https://www.nature.com/articles/s41586-023-06185-3)

## Continue exploring

- [Planet](https://brightaifuture.com/worlds/planet)
- [How much earlier could we understand what is coming?](https://brightaifuture.com/threads/weather)
- [Extended story and historical record](https://brightaifuture.com/stories/weather-in-three-dimensions)
- [Open this record in the interactive world](https://brightaifuture.com/?event=pangu)