MagicBathyNet: A Multimodal Remote Sensing Dataset for Bathymetry Prediction and Pixel-based Classification in Shallow Waters

MagicBathyNet is a new multimodal benchmark dataset made up of image patches of Sentinel-2, SPOT-6 and aerial imagery, bathymetry in raster format and seabed classes annotations.

The MagicBathyNet dataset is constructed in the context of MagicBathy research project funded by the European Commission for the period 2023-2025 (GA 101063294) at the Remote Sensing Image Analysis (RSiM) group at TU Berlin and the Big Data Analytics in Earth Observation group at the Berlin Institute for the Foundations of Learning and Data (BIFOLD).

MagicBathyNet contains 3355 RGB co-registered triplets of Sentinel-2 (S2), SPOT-6, and aerial image patches, complemented by 1244 RGB co-registered S2 and SPOT-6 doublets, 3354 DSM (Digital Surface Model) raster patches for the aerial patches and 3396 DSM raster patches for S2 and SPOT-6. Additionally, it contains 533 annotated raster patches for seabed habitat and type, facilitating supervised pixel-based classification. Each patch covers 180x180m, represented by 18x18 pixels in S2 imagery, 30x30 pixels in SPOT-6 imagery and 720x720 pixels in airborne imagery. 




If you use MagicBathyNet in your research, please cite our paper:

P. Agrafiotis, L. Janowski, D. Skarlatos, and B. Demir, "MagicBathyNet: A Multimodal Remote Sensing Dataset for Bathymetry Prediction and Pixel-based Classification in Shallow Waters", IGARSS 2024 - 2024 IEEE International Geoscience and Remote Sensing Symposium, Athens, Greece, 2024, pp. 249-253, doi: 10.1109/IGARSS53475.2024.10641355.

or

P. Agrafiotis, L. Janowski, D. Skarlatos, and B. Demir, "MagicBathyNet: A Multimodal Remote Sensing Dataset for Bathymetry Prediction and Pixel-based Classification in Shallow Waters", arXiv:2405.15477, 2024.

Overlayed predicted bathymetry, predicted seabed classes and aerial imagery (works only with mouse).

Image 1
Image 2
Image 3


Download MagicBathyNet Download code and pretrained models Paper in arXiv.org Paper in IEEE


ESA is acknowledged for providing the SPOT-6 images within its TPM programme in the frame of proposal PP0092443 and Airbus for being the provider of the original SPOT-6 images. The Dep. of Land and Surveys of Cyprus is acknowledged for providing the LiDAR reference data for Cyprus.