embed2scale/TerraCodec-1.0-FP-S2L2A

TerraCodec

Neural Compression for Earth Observation

TerraCodec (TEC) is a family of pretrained neural compression codecs for multispectral Sentinel-2 satellite imagery. The models compress optical Earth observation data using learned latent representations and entropy coding.

Compared to classical codecs such as JPEG2000 or WebP, TerraCodec achieves 3–10× higher compression at comparable reconstruction quality on multispectral satellite imagery. Temporal models further improve compression by exploiting redundancy across seasonal image sequences of satellite imagery.

---

Model Family

Model	Available Checkpoints	Description
terracodec_v1_fp_s2l2a	λ = 0.5, 2, 10, 40, 200	Factorized-prior image codec. Smallest model and strong baseline for multispectral image compression.
terracodec_v1_elic_s2l2a	λ = 0.5, 2, 10, 40, 200	Enhanced entropy model with spatial and channel context for improved rate–distortion performance.
terracodec_v1_tt_s2l2a	λ = 0.4, 1, 5, 20, 100, 200, 700	Temporal Transformer codec modeling redundancy across seasonal image sequences.
flextec_v1_s2l2a	Single checkpoint (quality = 1–16)	Flexible-rate temporal codec. One model supports multiple compression levels via token-based quality settings.

Lower λ / quality → higher compression
Higher λ / quality → higher reconstruction quality

---

Model Architecture

This repository contains the TEC-FP (Factorized Prior) variants of TerraCodec.

TEC-FP is a convolutional encoder–decoder neural compression model with a fully factorized entropy model for the latent representation. Each quantized latent variable is modeled independently without spatial or channel context. This design enables efficient parallel entropy coding. TEC-FP is the smallest and fastest image codec in the TerraCodec family and is optimized for 12-band Sentinel-2 imagery.

See the paper for additional architectural and training details.

---

Input Format

Codec type	Expected shape	Example
Image codecs	[B, C, H, W]	[1, 12, 256, 256]
Temporal codecs	[B, T, C, H, W]	[1, 4, 12, 256, 256]

• Inputs use 12 Sentinel‑2 L2A spectral bands.
• Recommended spatial size: 256×256. TEC‑FP supports arbitrary spatial sizes; other models expect 256×256.
• Temporal codecs were pretrained on four seasonal frames, but can process any number of timesteps during inference (higher T increases compute).

---

Normalization

Models were trained on SSL4EO-S12 v1.1.

Inputs should be standardized per spectral band using dataset statistics. For S2L2A:

mean = torch.tensor([793.243, 924.863, 1184.553, 1340.936, 1671.402, 2240.082, 2468.412, 2563.243, 2627.704, 2711.071, 2416.714, 1849.625])
std = torch.tensor([1160.144, 1201.092, 1219.943, 1397.225, 1400.035, 1373.136, 1429.170, 1485.025, 1447.836, 1652.703, 1471.002, 1365.307])

Usage

Install TerraCodec:

pip install terracodec

Load pretrained models:

from terracodec import terracodec_v1_fp_s2l2a

model = terracodec_v1_fp_s2l2a(
    pretrained=True,
    compression=10
)

# Fast reconstruction (no bitstream)
reconstruction = model(inputs)

# True compression
compressed = model.compress(inputs)
reconstruction = model.decompress(**compressed)

Feedback

If you have questions, encounter issues or want to discuss improvements:

• open an issue or discussion on GitHub
• or contribute directly to the repository

GitHub repository: https://github.com/IBM/TerraCodec

Citation

If you use TerraCodec in your research, please cite:

@article{terracodec2025,
  title   = {TerraCodec: Compressing Optical Earth Observation Data},
  author  = {Costa Watanabe, Julen and Wittmann, Isabelle and Blumenstiel, Benedikt and Schindler, Konrad},
  journal = {arXiv preprint arXiv:2510.12670},
  year    = {2025}
}