{"id":36441248,"url":"https://github.com/pagraf/magicbathynet","last_synced_at":"2026-01-11T21:58:14.919Z","repository":{"id":241755557,"uuid":"748123214","full_name":"pagraf/MagicBathyNet","owner":"pagraf","description":"Quick start guide for benchmarking MagicBathyNet dataset in learning-based bathymetry and pixel-based classification using Remote Sensing imagery.","archived":false,"fork":false,"pushed_at":"2025-06-10T10:16:05.000Z","size":833,"stargazers_count":42,"open_issues_count":1,"forks_count":5,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-12-30T14:29:10.982Z","etag":null,"topics":["aerial-imagery","bathymetry","computer-vision","dataset","deep-learning","depth-estimation","earth-observation","eu-project","magicbathy","models","ocean-data","ocean-mapping","remote-sensing","satellite-imagery","seabed-mapping","semantic-segmentation","sentinel-2","shallow-water","spot6"],"latest_commit_sha":null,"homepage":"https://www.magicbathy.eu","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"other","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/pagraf.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE.txt","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null}},"created_at":"2024-01-25T10:21:08.000Z","updated_at":"2025-12-24T09:02:05.000Z","dependencies_parsed_at":"2024-06-25T12:27:08.998Z","dependency_job_id":"dfe631d8-08f3-402b-9c38-b41f22f01345","html_url":"https://github.com/pagraf/MagicBathyNet","commit_stats":{"total_commits":237,"total_committers":1,"mean_commits":237.0,"dds":0.0,"last_synced_commit":"3d6e2d1116f7f01dbfe28373819421970727e4a6"},"previous_names":["pagraf/magicbathynet"],"tags_count":1,"template":false,"template_full_name":null,"purl":"pkg:github/pagraf/MagicBathyNet","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/pagraf%2FMagicBathyNet","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/pagraf%2FMagicBathyNet/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/pagraf%2FMagicBathyNet/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/pagraf%2FMagicBathyNet/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/pagraf","download_url":"https://codeload.github.com/pagraf/MagicBathyNet/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/pagraf%2FMagicBathyNet/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":28324640,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-01-11T18:42:50.174Z","status":"ssl_error","status_checked_at":"2026-01-11T18:39:13.842Z","response_time":60,"last_error":"SSL_read: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["aerial-imagery","bathymetry","computer-vision","dataset","deep-learning","depth-estimation","earth-observation","eu-project","magicbathy","models","ocean-data","ocean-mapping","remote-sensing","satellite-imagery","seabed-mapping","semantic-segmentation","sentinel-2","shallow-water","spot6"],"created_at":"2026-01-11T21:58:14.345Z","updated_at":"2026-01-11T21:58:14.911Z","avatar_url":"https://github.com/pagraf.png","language":"Jupyter Notebook","readme":"![magicbathynet](https://github.com/pagraf/MagicBathyNet/assets/35768562/85d2f09c-2bc9-4edb-9b3e-5428589fdf64)\n\n\n# MagicBathyNet: A Multimodal Remote Sensing Dataset for Benchmarking Learning-based Bathymetry and Pixel-based Classification in Shallow Waters\n\n[MagicBathyNet](https://www.magicbathy.eu/magicbathynet.html) is a benchmark dataset made up of image patches of Sentinel-2, SPOT-6 and aerial imagery, bathymetry in raster format and seabed classes annotations. Dataset also facilitates unsupervised learning for model pre-training in shallow coastal areas. It is developed in the context of MagicBathy project.\n\u003cbr /\u003e\n\u003cbr /\u003e\n[![MagicBathy](https://img.shields.io/badge/MagicBathy-Project-red.svg)](https://www.magicbathy.eu) \u003cbr /\u003e\nDOI of GitHub Repository [![DOI](https://zenodo.org/badge/748123214.svg)](https://doi.org/10.5281/zenodo.15630601)\n\u003cbr /\u003e\n\n# Package for benchmarking MagicBathyNet dataset in learning-based bathymetry and pixel-based classification.\n\nThis repository contains the code of the paper \"P. Agrafiotis, Ł. 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.\"\u003cbr /\u003e\n\n[![arXiv](https://img.shields.io/badge/arXiv-Paper-\u003cCOLOR\u003e.svg)](https://arxiv.org/abs/2405.15477) [![IEEE](https://img.shields.io/badge/IEEE-Paper-blue.svg)](https://ieeexplore.ieee.org/document/10641355)\n\n## Citation\n\nIf you find this repository useful, please consider giving a star ⭐.\u003cbr /\u003e\nIf you use the code in this repository or the dataset please cite:\n\n\u003eP. Agrafiotis, Ł. 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.\n```\n@INPROCEEDINGS{10641355,\n  author={Agrafiotis, Panagiotis and Janowski, Łukasz and Skarlatos, Dimitrios and Demir, Begüm},\n  booktitle={IGARSS 2024 - 2024 IEEE International Geoscience and Remote Sensing Symposium}, \n  title={MAGICBATHYNET: A Multimodal Remote Sensing Dataset for Bathymetry Prediction and Pixel-Based Classification in Shallow Waters}, \n  year={2024},\n  volume={},\n  number={},\n  pages={249-253},\n  doi={10.1109/IGARSS53475.2024.10641355}}\n```\n\u003cbr /\u003e\n\n# Getting started\n\n## Downloading the dataset\n\nFor downloading the dataset and a detailed explanation of it, please visit the MagicBathy Project website at [https://www.magicbathy.eu/magicbathynet.html](https://www.magicbathy.eu/magicbathynet.html)\n\n\n## Dataset structure\nThe folder structure should be as follows:\n```\n┗ 📂 magicbathynet/\n  ┣ 📂 agia_napa/\n  ┃ ┣ 📂 img/\n  ┃ ┃ ┣ 📂 aerial/\n  ┃ ┃ ┃ ┣ 📜 img_339.tif\n  ┃ ┃ ┃ ┣ 📜 ...\n  ┃ ┃ ┣ 📂 s2/\n  ┃ ┃ ┃ ┣ 📜 img_339.tif\n  ┃ ┃ ┃ ┣ 📜 ...\n  ┃ ┃ ┣ 📂 spot6/\n  ┃ ┃ ┃ ┣ 📜 img_339.tif\n  ┃ ┃ ┃ ┣ 📜 ...\n  ┃ ┣ 📂 depth/\n  ┃ ┃ ┣ 📂 aerial/\n  ┃ ┃ ┃ ┣ 📜 depth_339.tif\n  ┃ ┃ ┃ ┣ 📜 ...\n  ┃ ┃ ┣ 📂 s2/\n  ┃ ┃ ┃ ┣ 📜 depth_339.tif\n  ┃ ┃ ┃ ┣ 📜 ...\n  ┃ ┃ ┣ 📂 spot6/\n  ┃ ┃ ┃ ┣ 📜 depth_339.tif\n  ┃ ┃ ┃ ┣ 📜 ...\n  ┃ ┣ 📂 gts/\n  ┃ ┃ ┣ 📂 aerial/\n  ┃ ┃ ┃ ┣ 📜 gts_339.tif\n  ┃ ┃ ┃ ┣ 📜 ...\n  ┃ ┃ ┣ 📂 s2/\n  ┃ ┃ ┃ ┣ 📜 gts_339.tif\n  ┃ ┃ ┃ ┣ 📜 ...\n  ┃ ┃ ┣ 📂 spot6/\n  ┃ ┃ ┃ ┣ 📜 gts_339.tif\n  ┃ ┃ ┃ ┣ 📜 ...\n  ┃ ┣ 📜 [modality]_split_bathymetry.txt\n  ┃ ┣ 📜 [modality]_split_pixel_class.txt\n  ┃ ┣ 📜 norm_param_[modality]_an.txt\n  ┃\n  ┣ 📂 puck_lagoon/\n  ┃ ┣ 📂 img/\n  ┃ ┃ ┣ 📜 ...\n  ┃ ┣ 📂 depth/\n  ┃ ┃ ┣ 📜 ...\n  ┃ ┣ 📂 gts/\n  ┃ ┃ ┣ 📜 ...\n  ┃ ┣ 📜 [modality]_split_bathymetry.txt\n  ┃ ┣ 📜 [modality]_split_pixel_class.txt\n  ┃ ┣ 📜 norm_param_[modality]_pl.txt\n```\nThe mapping between RGB color values and classes is:\n\n```\nFor the Agia Napa area:\n0 : (0, 128, 0),   #seagrass\n1 : (0, 0, 255),   #rock\n2 : (255, 0, 0),   #macroalgae\n3 : (255, 128, 0), #sand\n4 : (0, 0, 0)}     #Undefined (black)\n\nFor the Puck Lagoon area:\n0 : (255, 128, 0), #sand\n1 : (0, 128, 0) ,  #eelgrass/pondweed\n2 : (0, 0, 0)}     #Undefined (black)\n```\n\n## Clone the repo\n\n`git clone https://github.com/pagraf/MagicBathyNet.git`\n\n## Installation Guide\nThe requirements are easily installed via Anaconda (recommended):\n\n`conda env create -f environment.yml`\n\nAfter the installation is completed, activate the environment:\n\n`conda activate magicbathynet`\n\nOpen Jupyter Notebook:\n\n`jupyter notebook`\n\n## Train and Test the models\nTo train and test the **bathymetry** models use **MagicBathyNet_bathymetry.ipynb**.\n\nTo train and test the **pixel-based classification** models use **MagicBathyNet_pixelclass.ipynb**.\n\n## Pre-trained Deep Learning Models\nWe provide code and model weights for the following deep learning models that have been pre-trained on MagicBathyNet for pixel-based classification and bathymetry tasks:\n\n### Pixel-based classification\n| Model Names | Modality | Area | Pre-Trained PyTorch Models                                                                                                                | \n| ----------- |----------| ---- |----------------------------------------------------------------------------------------------------------------------------------------------|\n| U-Net | Aerial | Agia Napa | [unet_aerial_an.zip](https://drive.google.com/file/d/1vrYwOGEPbiuyvAmtE8-SfbDfzVWU8oMD/view?usp=sharing) |\n| SegFormer | Aerial | Agia Napa         | [segformer_aerial_an.zip](https://drive.google.com/file/d/1rUr_KvAgOKwBmykLoprUy4Aw4fCiYGIm/view?usp=sharing)            |\n| U-Net | Aerial | Puck Lagoon | [unet_aerial_pl.zip](https://drive.google.com/file/d/1PVIRvFpiw4xf6xgLCF4Bzhpb_2wD3Q3G/view?usp=sharing) |\n| SegFormer | Aerial | Puck Lagoon         | [segformer_aerial_pl.zip](https://drive.google.com/file/d/1c_YNKXvANd71piMEmGOa1hdo6J58ZynP/view?usp=sharing)            |\n| U-Net | SPOT-6 | Agia Napa        | [unet_spot6_an.zip](https://drive.google.com/file/d/1GNpk6zG-t0e853B5ntd5ETJEeyShnMkL/view?usp=sharing)            |\n| SegFormer | SPOT-6 | Agia Napa      | [segformer_spot6_an.zip](https://drive.google.com/file/d/198k981Qdvw8Y5eZ8sMGVDIcPC8B-uDkx/view?usp=sharing)      |\n| U-Net | SPOT-6 | Puck Lagoon        | [unet_spot6_pl.zip](https://drive.google.com/file/d/1h3jZ-QY8xiI6Q4O7jXO3BzZDyO08W1A0/view?usp=sharing)            |\n| SegFormer | SPOT-6 | Puck Lagoon      | [segformer_spot6_pl.zip](https://drive.google.com/file/d/12p4AdmHgK0PWsxJ6x2pedqqzfkJ2f4E-/view?usp=sharing )      |\n| U-Net | Sentinel-2 | Agia Napa     | [unet_s2_an.zip](https://drive.google.com/file/d/19FeZ60AK67z-DCFWhjqDrV6-Xlyicgqn/view?usp=sharing)   | \n| SegFormer | Sentinel-2 | Agia Napa    | [segformer_s2_an.zip](https://drive.google.com/file/d/1nOKhVecid3yjAg0fF-rTV2-cGmUMj6nh/view?usp=sharing)   |\n| U-Net | Sentinel-2 | Puck Lagoon    | [unet_s2_pl.zip](https://drive.google.com/file/d/1iySJta5qPegW7TEy5yIiFvqr816THEuY/view?usp=sharing)   | \n| SegFormer | Sentinel-2 | Puck Lagoon    | [segformer_s2_pl.zip](https://drive.google.com/file/d/1T7iP7khBBK0YsQzdUHAUksX9Q_Qbw5kW/view?usp=sharing)   |\n\n### Learning-based Bathymetry\n| Model Name | Modality | Area | Pre-Trained PyTorch Models                                                                                                                | \n| ----------- |----------| ---- |----------------------------------------------------------------------------------------------------------------------------------------------|\n| Modified U-Net for bathymetry | Aerial | Agia Napa | [bathymetry_aerial_an.zip](https://drive.google.com/file/d/1-qUlQMHdZDZKkeQ4RLX54o4TK6juwOqD/view?usp=sharing) |\n| Modified U-Net for bathymetry | Aerial | Puck Lagoon         | [bathymetry_aerial_pl.zip](https://drive.google.com/file/d/1SN8YH-WZIdR4e5Zl0uQK4OM62z_WNCks/view?usp=sharing)            |\n| Modified U-Net for bathymetry | SPOT-6 | Agia Napa        | [bathymetry_spot6_an.zip](https://drive.google.com/file/d/1giG-MrJQZ2YLDzjOd2h-u2vr9gfI1jO0/view?usp=sharing)            |\n| Modified U-Net for bathymetry | SPOT-6 | Puck Lagoon      | [bathymetry_spot6_pl.zip](https://drive.google.com/file/d/1Cf1gAsEUfACkBep4i_0gB-pp_L0bvaU_/view?usp=sharing)      |\n| Modified U-Net for bathymetry | Sentinel-2 | Agia Napa    | [bathymetry_s2_an.zip](https://drive.google.com/file/d/15esoghCHHHilQJxTBBjmHpAAde-AHdtE/view?usp=sharing)   | \n| Modified U-Net for bathymetry | Sentinel-2 | Puck Lagoon    | [bathymetry_s2_pl.zip](https://drive.google.com/file/d/1oCnD5ePwVW3ORix4GWRcMUp_kSL5p9Se/view?usp=sharing)   |\n\nTo achieve the results presented in the paper, use the parameters and the specific train-evaluation splits provided in the dataset. Parameters can be found [here](https://drive.google.com/file/d/1gkIG99WFI6LNP7gsRvae9FZWU3blDPgv/view?usp=sharing) while train-evaluation splits are included in the dataset.\n\n## Example testing results\nExample patch of the Agia Napa area (left), pixel classification results obtained by U-Net (middle) and predicted bathymetry obtained by MagicBathy-U-Net (right). For more information on the results and accuracy achieved read our [paper](https://www.magicbathy.eu/). \n\n\n![img_410_aerial](https://github.com/pagraf/MagicBathyNet/assets/35768562/132b4166-b012-476b-9653-b511ede2c6f3)\n![aerial_410_unet](https://github.com/pagraf/MagicBathyNet/assets/35768562/8a293815-87b4-4f45-b5de-c99f7c827bb5)\n![depth_410_aerial](https://github.com/pagraf/MagicBathyNet/assets/35768562/7995efd7-f85e-4411-8037-4a68c9780bfb)\n\n\n\n## Authors\nPanagiotis Agrafiotis [https://www.user.tu-berlin.de/pagraf/](https://www.user.tu-berlin.de/pagraf/)\n\n## Feedback\nFeel free to give feedback, by sending an email to: agrafiotis@tu-berlin.de\n\u003cbr /\u003e\n\u003cbr /\u003e\n\n# Funding\nThis work is part of **MagicBathy project funded by the European Union’s HORIZON Europe research and innovation programme under the Marie Skłodowska-Curie GA 101063294**. Work has been carried out at the [Remote Sensing Image Analysis group](https://rsim.berlin/). For more information about the project visit [https://www.magicbathy.eu/](https://www.magicbathy.eu/).\n","funding_links":[],"categories":[],"sub_categories":[],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fpagraf%2Fmagicbathynet","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fpagraf%2Fmagicbathynet","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fpagraf%2Fmagicbathynet/lists"}