{
  "fetched_at": "2026-10-19T20:48:06Z",
  "source_url": "https://www.kaggle.com/competitions/10316-materials-design-with-ml-and-ai-jan-24/data",
  "pages": [
    {
      "name": "data-description",
      "content": "\n## File descriptions\n*   **train.json** - the training set\n*   **test.json**  - the test set\n*   **submission_example.csv** - a sample submission file in the correct format (hform is here a random number)\n\n## Data fields\n* 'id' - arbitrary id for the materials\n* 'formula' - Stoichiometric formula\n* 'atoms' - The ase.atoms object of the material\n* 'hform' - Heat of formation [eV/atom]",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "<h2>Predicting thermodynamical stability for 2D materials using machine learning</h2>\n<p>This competition is part of the course <a href=\"https://kurser.dtu.dk/course/10316\" target=\"_blank\"> 10316 Materials design with machine learning and artificial intelligence</a> at DTU January 2024. During the first two weeks you have learned the basics of programming and machine learning, and now it's time to apply these skills in a real world problem.</p>\n<p>The objective of the competition is to build a machine learning model that predicts the heat of formation (hform) of 2D materials. Heat of formation is the energy of the material with respect to the standard states of its constituent element </p>\n\n\n<p>The dataset for the competition consists of 12,000 2D materials along with their DFT-calculated heat of formation. The structures are provided as <a href=\"https://wiki.fysik.dtu.dk/ase/ase/atoms.html\" target=\"_blank\"> <strong> Atoms </strong> </a> objects containing the atomic numbers and positions for the structure. The dataset is divided into two sets (66.6% for training and 33.3% for testing). For the test set, only the structures  are provided (and not the heat of formation).</p>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "<p>The evaluation metric for this competition is <a href=\"https://en.wikipedia.org/wiki/Root-mean-square_deviation\" target=\"_blank\"> RMSE-Score (Root-mean-squared-error)</a>. The RMSE score is a commonly used measure of the differences between of observed values and predicted values by an estimator or model. The RMSE score is given by:</p>\n<p>\\[ RMSE = \\sqrt{\\frac{\\sum_i (\\hat{y}_i-y_i)^2}{N}} \\]</p>\n<p>where i runs over samples in the test set and N is the number of samples.</p> \n<h2>Submission Format</h2>\n<p>For every structure in the dataset the submission file should contain a row with 2 columns. The first column is the structure id and the second column is the predicted heat of formation </p>\n<pre>id,hform<br>1,0<br>2,0<br>3,0</pre>\n<hr>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "rules",
      "content": "This is a page where you can include rules that participants must accept before joining. You may wish to include rules like:\n\n - Don't cheat!\n - Apply yourself!\n - Have fun!\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Timeline",
      "content": "<ul> \n<li>  Monday 16th of January, 10:00 - Competition launches </li> \n<li>  Thursday 19th of January, 11:59 (noon) - Submission deadline </li>\n<li>  Friday 20th of January, 9:00 - Poster session and winner ceremony </li> \n</ul>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}