AQUA-PRITHVI - a model for water ecosystem analysis
1 min readupdated
AQUA-PRITHVI is an adaptation of the IBM/NASA Prithvi-EO-2.0-300M-TL geospatial base model tailored for water surfaces and aquatic ecosystems. Trained via masked spectral reflectance recovery on Landsat and Sentinel-2 satellite data, it effectively extracts vector representations and enhances spectral reconstruction for water bodies. The development targets researchers in Earth remote sensing.
Key features
- Water surface specialization: trained on a corpus of nearly 170 thousand satellite data patches.
- Hybrid architecture: 330 million parameters, with approximately 77 million trainable.
- Improved spectral recovery: 42.9 percent reduction in RMSE compared to the base model.
- TerraTorch integration: native library support for geospatial AI models.
What you can do
- Extract high-quality spectral features for water bodies from HLS satellite imagery.
- Perform spectral reconstruction and self-supervised representation studies.
- Use adapted encoders and autoencoders within the TerraTorch ecosystem.
Example
Loading the model via script:
from load_aqua_prithvi import load_adapted_mae, load_adapted_encoder
model = load_adapted_mae('final_delta.pt', device='cpu')
encoder_model = load_adapted_encoder('AQUA_PRITHVI_DAPT_V2_encoder.pt', device='cpu')
Read more
DetailsBase model: IBM/NASA Prithvi-EO-2.0-300M-TL
Metrics: Spectral reflectance RMSE 0.00516 (42.9 percent better)
Data: 169,429 HLS satellite imagery patches (2018-2024)
Requirements: PyTorch, TerraTorch










Comments