{
  "fetched_at": "2026-10-18T14:00:43Z",
  "source_url": "https://www.kaggle.com/competitions/bathymetry-estimation/data",
  "pages": [
    {
      "name": "data-description",
      "content": "<p>The input data used for this competition is composed of raw and preprocessed subtiles extracted from the European Space Agency's Sentinel-2 L1C satellite products. Bathymetry survey data were retrieved from The French Naval Hydrographic and Oceanographic Service (SHOM) and The European Marine Observation and Data Network (EMODnet).\n\nWe use four different locations to create our datasets. French Guiana and Saint Louis in Senegal are used to create the training set. Two different locations on the Portuguese west coast are used to create the test set. The corresponding Sentinel-2 tiles are 22NCL, 28PCC, 29TNE, 29SMD for French Guiana, Saint Louis and the two locations in Portugal, respectively.\n\n<h2>File descriptions</h2>\nThe following CSV files are provided:\n<ul>\n<li><strong>mixed_train.csv</strong> - the training set containing data from French Guiana (22NCL) and Saint Louis (28PCC).</li>\n<li><strong>mixed_validation.csv</strong> - the validation set containing data from French Guiana (22NCL) and Saint Louis (28PCC).</li>\n<li><strong>mixed_test.csv</strong> - the test set containing data from the Portuguese west coast (29TNE, 29SMD).</li>\n</ul>\n\n<h2>Data fields</h2>\nAll input CSV files have the following format:\n<ul>\n<li><strong>image_file_name</strong> - input image file identifier</li>\n<li><strong>z</strong> - the depth corresponding to the input image</li>\n</ul>\n\n<h2>Input image files</h2>\nEach input image is provided in two formats:\n<li><strong>Raw</strong> - The raw image extracted from a full-sized Sentinel-2 image(filename_RAW.npy).</li> \n<li><strong>Filtered</strong> - The preprocessed image extract (filename.npy).</li>\n</ul>\n\n<h2>Input image preprocessing</h2>\nTo preprocess the input subtiles, raw subtiles are passed through a pass-band filter to remove all signals that do not resemble ocean waves, the normalized cross correlation (normxcorr) is calculated based on the remaining signals. The preprocessed images provided in these datasets are the results of the normxcorr function.\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "Coastal areas are constantly under a multitude of pressures resulting from different natural forces. The ability to reliably track and measure the nearshore bathymetry over time is critical for a wide array of applications including coastal development and management, coastal risk monitoring and mitigation, coastal science studies, among others. Performing in-situ bathymetric measurements is challenging and expensive and not always possible due to a variety of reasons.\n\nRemote sensing tools have recently become an important tool to collect different types of data that allows the monitoring of ocean waves in coastal areas. One of those tools is the European Space Agency's (ESA) Sentinel-2 Satellite constellation. The Sentinel-2 constellation is an Earth Observation (EO) mission composed of two twin satellites flying in the same orbit that are phased at 180°, designed to provide a global revisit frequency of 5 days.\n\nIn this competition, satellite imagery provided by the Sentinel-2 mission is coupled with bathymetry survey data (from The French Naval Hydrographic and Oceanographic Service and The European Marine Observation and Data Network) in order to train an AI-based bathymetry inversion model.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "<p>This competition uses Root Mean Squared Error (RMSE) as it's evaluation metric. RMSE is a common metric in Bathymetry Estimation studies, it will used to evaluate the predicted values against ground-truth data.</p>\n\n<p>Submission files should contain two columns: image_id and predicted_z. The file should contain a header and have the following format:</p>\n<pre>image_id,predicted_z<br>example_input_id_1,10.0<br>example_input_id_2,25.0<br></pre>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "rules",
      "content": "",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}