# Adapting one Earth model to many maps

Prithvi-EO-2.0 is a geospatial foundation model that can be adapted to Earth-observation tasks such as flood mapping, crop classification, and land-use analysis.

Canonical: https://brightaifuture.com/discoveries/prithvi-earth-observation
Format: discovery
Source publication: 2024-12-03
Bright publication: 2026-09-19
Substantive update: None recorded
Evidence and review: Demonstrated; confidence: unassessed; source-checked; ai-assisted. AI-assisted comparison with the cited sources. Source-checked means the record was checked against those sources; it does not claim independent reproduction, expert review, or validation of the publisher’s results.

## The human problem

Organizations need current maps of floods, crops, and land change but may have little labeled local data.

## The prior constraint

Each mapping task often required a separately trained model and substantial satellite-data preparation.

## AI’s actual role

The pretrained model converts multispectral satellite time series into representations that a smaller labeled dataset can adapt to a local mapping task.

## The documented result

NASA and IBM publish model variants, code, examples, and task evaluations through the Prithvi repository and model cards.

## Why it may matter

A shared geospatial base can lower the starting cost of local mapping, provided teams validate it against the place and decision at hand.

## Limitations

The Prithvi-EO-2.0 repository code is MIT and the named 300M checkpoint is Apache-2.0, but those terms do not make every satellite input freely redistributable. Performance can shift by region, sensor, season, and local ground truth.

NASA and IBM document the public artifacts and research tasks. This broader mapping record is distinct from Bright's separate Prithvi in-orbit demonstration.

## Unresolved questions



## Provenance and history

{
  "dates": {
    "eventDate": null,
    "publicationDate": "2024-12-03",
    "captureDate": "2026-09-19",
    "lastReviewedDate": "2026-09-19"
  },
  "provenance": {
    "origin": "editorial",
    "externalId": "https://github.com/NASA-IMPACT/Prithvi-EO-2.0"
  },
  "revisions": [
    {
      "id": "revision:open-models-added:prithvi-earth-observation",
      "recordedAt": "2026-09-19",
      "summary": "Bright added this source-checked open-model application record. The cited source publication date is 2024-12-03; 2026-09-19 is when Bright added this record.",
      "sourceIds": [
        "prithvi-eo-2-repository",
        "nasa-open-ai-foundation-models",
        "prithvi-eo-2-paper"
      ]
    }
  ],
  "corrections": []
}

## Original sources

- [Prithvi-EO-2.0](https://github.com/NASA-IMPACT/Prithvi-EO-2.0)
- [NASA open science AI foundation models](https://www.nas.nasa.gov/SC24/research/project27.php)
- [Prithvi-EO-2.0: A Versatile Multi-Temporal Foundation Model for Earth Observation Applications](https://arxiv.org/abs/2412.02732)

## Continue exploring

- [Open Models](https://brightaifuture.com/open-models)
- [Open intelligence](https://brightaifuture.com/worlds/open)
- [What changes when powerful models become open-weight?](https://brightaifuture.com/threads/open)
- [Someone builds on it](https://brightaifuture.com/open-intelligence)