DL_bathy pretrained model weights

Temporary home: this repo currently lives under a personal account (Amy5133) while the author arranges access to the buckai-observatory Hugging Face org that DL_bathy's inference.py defaults to. Expect this to move to buckai-observatory/dl-bathy-weights later; inference.py's HF_DEFAULT_REPO_ID will be updated to match when it does.

Pretrained weights for the five models compared in Hsu & Moortgat (2026), From Local Training to Large-Scale Mapping: A Comparative Assessment of Machine Learning and Deep Learning for Transferable Satellite-Derived Bathymetry, Remote Sensing 18(11): 1768, 10.3390/rs18111768. Trained and evaluated using the DL_bathy pipeline: github.com/buckai-observatory/DL_bathy.

Repository layout

./
β”œβ”€β”€ best_model.pth                         ConvNeXt-Large, best-val checkpoint (default for inference.py)
β”œβ”€β”€ deeplabv3_bathy_final.pth              ConvNeXt-Large, final-epoch checkpoint
β”œβ”€β”€ metadata.json                          ConvNeXt-Large training run config + metrics
β”œβ”€β”€ resnet101/
β”‚   β”œβ”€β”€ best_model.pth
β”‚   β”œβ”€β”€ deeplabv3_bathy_final.pth
β”‚   └── metadata.json
β”œβ”€β”€ resnet50/
β”‚   β”œβ”€β”€ best_model.pth
β”‚   β”œβ”€β”€ deeplabv3_bathy_final.pth
β”‚   └── metadata.json
β”œβ”€β”€ efficientnet_b4/
β”‚   β”œβ”€β”€ best_model.pth
β”‚   β”œβ”€β”€ deeplabv3_bathy_final.pth
β”‚   └── metadata.json
└── random_forest/
    └── trained_model_20260126_173237.joblib

For each DeepLabV3+ backbone, both the best-validation-metric checkpoint (best_model.pth) and the final-epoch checkpoint (deeplabv3_bathy_final.pth) are included, alongside the training run's metadata.json (configuration + metrics, written by step2_train_test.py). All four were trained with the SWF (Smooth Weight Function) depth-weighted loss (loss_type: "swf" in each metadata.json).

Load a .pth checkpoint with segmentation_models_pytorch via the DL_bathy repo's inference.py (load_model(filename=..., encoder_name=...)); load the .joblib file with joblib.load() into scikit-learn.


Model Card β€” DL_bathy (satellite-derived bathymetry)

Overview

  • Model name: DL_bathy DeepLabV3+ satellite-derived bathymetry
  • Model type: fully-convolutional segmentation network (regression head)
  • Task: per-pixel water depth estimation (metres) from Sentinel-2 L2A imagery
  • Architecture: smp.DeepLabV3Plus with a 12-band input head, single-channel regression output, and an ImageNet-pretrained encoder
  • Default encoder: tu-convnext_large (ConvNeXt-Large, timm backend). Alternate encoders trained by the same pipeline: efficientnet-b4, resnet50, resnet101.
  • License: MIT (matches the DL_bathy repository)

Intended use

  • Predicting shallow-water bathymetry (depth in metres) over any location covered by Sentinel-2, given a cloud-free (or SCL-masked) L2A tile containing bands B01–B12.
  • Research and educational use: reproducing the results of Hsu & Moortgat (2026); benchmarking against other satellite-derived bathymetry (SDB) approaches; exploring transfer to new geographies.

Out-of-scope / cautions

  • Deep water: the training distribution is shallow-water reef and coastal environments (< ~25 m). Predictions for open ocean or turbid inland water bodies are extrapolations and should not be trusted without independent validation.
  • Turbidity, sun glint, breaking waves: not explicitly handled by the model; masking these upstream (e.g. using SCL or a scene-level QA step) is the caller's responsibility.
  • Not a real-time / navigational product: outputs are research-grade, not certified for maritime navigation, dredging planning, or any safety-critical use.

Training data

  • Ground truth: airborne LiDAR bathymetry (see Hsu & Moortgat, 2026 for the full site list and processing chain).
  • Public reference subset: an open subset of the ground-truth data is shipped in Ground_Truth.zip in the DL_bathy repository for reproducibility and demo purposes. The full training dataset includes commercially licensed LiDAR that cannot be redistributed; this is documented in the repo's Data availability section.
  • Sentinel-2 imagery: L2A reflectance bands 1–12 (B01–B12), fetched at the training AOIs / dates via the geoai-datacubes pipeline. Cloud and shadow pixels are excluded via the SCL band during training.

TODO: total number of training patches, patch size (px), split ratios, augmentation strategy, and per-site sample counts.

Training configuration

See each architecture's metadata.json in this repo for the exact per-run configuration (loss type, SWF hyperparameters, learning rate, epochs trained, best validation loss, etc.). Summary common to all four:

  • Input channels: 12 (Sentinel-2 bands B01–B12)
  • Output: single-channel regression, no activation (raw depth in metres)
  • Loss: SWF (depth-weighted RMSE) β€” see SWF_beta / SWF_Z0 in each metadata.json
  • Optimiser: AdamW, weight-decay 1e-4
  • Scheduler: ReduceLROnPlateau (factor 0.5)
  • Hardware / wall-clock time: TODO

Evaluation

TODO β€” from the release training run:

  • Held-out test set: RMSE (m), MAE (m), RΒ², bias
  • Per-depth-bin performance (e.g. RMSE at 0–5 m, 5–10 m, 10–15 m, > 15 m)
  • Transfer performance on a geographically-held-out site, if measured

How to use

Minimal example (needs pip install huggingface_hub geoai-datacubes and the DL_bathy repository on the Python path):

from inference import predict_from_geoai_datacubes

# Predict bathymetry over a small AOI in the Great Barrier Reef (the same
# region the public Ground_Truth.zip covers).
depths, meta = predict_from_geoai_datacubes(
    aoi=[145.14, -14.56, 145.66, -14.26],
    time_range=("2020-06-01", "2020-09-30"),
    max_cloud_coverage=0.20,
)
print(f"Predicted depth map shape: {depths.shape}, dtype: {depths.dtype}")

To load a non-default architecture:

from inference import load_model, predict_depth

model = load_model(filename="resnet101/best_model.pth", encoder_name="resnet101")

See notebooks/dl_bathy_demo.ipynb in the DL_bathy repository for a Colab-ready end-to-end walkthrough on the public GBR subset.

Citation

If you use these weights, please cite:

  • Hsu, H.-J., & Moortgat, J. (2026). From Local Training to Large-Scale Mapping: A Comparative Assessment of Machine Learning and Deep Learning for Transferable Satellite-Derived Bathymetry. Remote Sensing 18(11): 1768. https://doi.org/10.3390/rs18111768
  • The DL_bathy software: see CITATION.cff in the DL_bathy repository.

Version history

  • v0.1.0 β€” first upload, reproducing the setup used in Hsu & Moortgat (2026).
Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. πŸ™‹ Ask for provider support