Skip to content
Other

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 moreDetails
Base 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
Discuss Telegram 0 2

Will it run?

Runs in BF16

Fits without quantisation.

  • BF16weights 1.1 GB · ready files1.7 GB
  • FP8 / INT8recommendedweights 0.6 GB1.1 GB
  • 4-bitweights 0.3 GB0.9 GB

Tip: go 8-bit.FP8 / INT8 is within about a percent of full precision in quality, takes half the memory and runs faster on RTX 40/50 and H100. Full precision only pays off for fine-tuning.

What to get for this model

Massed ComputeOpen Massed Compute

Your own GPU: FP8 / INT8 — from RTX 2060 · BF16 — from RTX 2060

Massed Compute hourly prices, November 2026. The discounted price applies with the coupon at checkout.

Estimate: weights plus working memory. Long videos, high resolutions and long contexts need more.

Run it on Massed Compute

The script downloads the model to the rented machine. How to run it is in the model card.

  1. 1. Rent a machine with a fitting GPU

    Open Massed Compute
  2. 2. Paste the script into the machine's terminal

    Connect over SSH (the Massed Compute panel shows the command) or open a terminal on the machine's desktop.

    HF_TOKEN / CIVITAI_TOKENThe script starts with token lines: paste yours between the quotes. The Hugging Face token is for gated models, the Civitai one for Civitai models.

    # freddyvillota/AQUA-PRITHVI-EO-2.0-300M-TL
    mkdir -p ~/models
    curl -LsSf https://astral.sh/uv/install.sh | sh
    source "$HOME/.local/bin/env"
    uv tool install "huggingface_hub[cli]"
    hf download freddyvillota/AQUA-PRITHVI-EO-2.0-300M-TL --local-dir ~/models/AQUA-PRITHVI-EO-2.0-300M-TL
    # The model is in ~/models. How to run it is in the model card (link above).
  3. 3. Use it

    The model is in ~/models. How to run it is in the model card (link above).

Stop the machine in the panel when you are done: it bills by the minute while it runs.

How to speed it up

Picked for this model type. Choose your hardware above to see what fits you exactly.

  • FlashAttention 44.0.0b40from November 18, 2026new release

    fastest exact attention on B200

    Kernels for Blackwell (beta). Exact attention without quantisation — fine for everything, LLMs included.

    How to enable: pip install flash-attn-4; vLLM and SGLang pick it up themselves.

    Earlier generations (2)
    • FlashAttention 3 — The Hopper (H100/H200) version with FP8.
    • FlashAttention 2 — The standard for RTX 30/40/50 and A100: exact attention without the memory cost of long contexts.
  • torch.compile2.15.0from October 28, 2026new release

    10–30% for free

    Compiles the model for your GPU. Slower first run, faster afterwards.

    How to enable: model = torch.compile(model); in ComfyUI the TorchCompileModel node.

Model family

New posts about versions of Prithvi-EO-2.0-300M-TL (quants, finetunes, LoRAs) will show up under the bell.

Fine-tunes 5All on Hugging Face

About the model

freddyvillota/AQUA-PRITHVI-EO-2.0-300M-TL
Author
freddyvillota
Category
Other
Released
Posted

On NeyroLearn

Hugging Face

20

Ask AI about this model

Answered by Gemini 4 · the chat is kept only in this tab

Comments