AI Potluck
Back to Gap Map Model components / Scientific AI models

TerraMind

IBM
open weights / Overall score: 3.8

TerraMind is an any-to-any generative Earth-observation model developed by IBM, ESA Phi-Lab, and Forschungszentrum Juelich. It processes six satellite and terrain modalities, learns both pixel- and token-scale representations, and can generate missing modalities or supply embeddings for fine-tuned downstream models through TerraTorch.

Verified 2026-09-10 via the Hugging Face model card and IBM repository.

Openness

3 high confidence
3.0
license
Apache-2.0(OSI)
weights
open(Apache-2.0 ungated checkpoint)
data
open(TerraMesh dataset published on Hugging Face)
code
partial(inference, generation, and fine-tuning examples without the full pretraining pipeline)

TerraMind publishes its weights and named training dataset, but the product repository documents use and adaptation rather than an end-to-end pretraining run.

Adoption

1 high confidence
1.0

2,922 downloads in the trailing 30 days for the declared large checkpoint.

Capability

5 high confidence
5.0

TerraMind is the top anchor because one primary card directly establishes all four attributes without relying on downstream task-count prose.

Verified 2026-09-10