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

Presto

NASA Harvest
open source / Overall score: 2.4

Presto, the Pretrained Remote Sensing Transformer, is a lightweight self-supervised model from NASA Harvest for remote-sensing pixel timeseries. It consumes between one and twenty-four monthly timesteps of Sentinel-1 SAR, Sentinel-2 optical, ERA5 meteorology, SRTM topography, Dynamic World classes, and latitude and longitude, and exposes an encoder whose pooled embeddings are fine-tuned for downstream classification and regression.

The pretrained weights ship inside the MIT repository as data/default_model.pt rather than on a model hub, so the adoption band is read from GitHub stars. Verified 2026-09-10 via the repository README, LICENSE, and contents listings.

Openness

5 high confidence
5.0
license
MIT(OSI)
weights
open(data/default_model.pt shipped in the MIT repository and loaded by the package's load_pretrained helper)
data
open(scripts/generate_data.py rebuilds the corpus end to end from Earth Engine, with the tile list, tile statistics and a sample shard shipped in the repository)
code
open(self-supervised train.py, eval.py, configs, and the end-to-end data-generation pipeline)

The weights, the self-supervised pretraining script, and the pipeline that rebuilds the corpus all ship under a plain MIT license with no added attribution or use clause, which is the ladder's top rung.

Adoption

1 medium confidence
1.0

The weights ship inside the repository rather than on a model hub, so no download count exists and 280 GitHub stars are used as a last-resort reach signal.

Capability

3 high confidence
3.0

Two attributes are stated directly. The encoder-decoder reconstructs masked inputs, which the category does not count as generative, and a variable count of monthly timesteps is one temporal scale rather than several.

  • https://raw.githubusercontent.com/nasaharvest/presto/main/README.md recorded 2026-09-10

    Shows construct_finetuning_model adding a linear head for finetuning and a jupyter notebook demonstrating finetuning on different downstream tasks, and specifies the input tensor as the S1, S2, ERA5, and SRTM bands plus Dynamic World classes and latitude and longitude.

Verified 2026-09-10