{
  "fetched_at": "2026-10-19T23:51:29Z",
  "source_url": "https://www.kaggle.com/competitions/esa-eo4soilprotection-2024-predicting-erosion-cat/data",
  "pages": [
    {
      "name": "data-description",
      "content": "##Training Dataset (train_erosion.csv):\nThis dataset includes training points for model development. Use this dataset to train your models, understanding the distinct features and indicators of each erosion category. There are four erosion categories:\n- 0 = No Gully/badland\n- 1 = Gully\n- 2 = Badland\n- 3 = Landslides\n\n##Validation Dataset (test_erosion.csv)\nThe dataset contains both public and private test points. Public points are available for internal validation of your models. It will help you fine-tune and assess the accuracy of your predictions during the development phase. Private dataset represents the final test of your model's effectiveness in real-world scenarios. Your goal is to predict these hidden values accurately. \n\n## Columns\nExplanation of columns (variables) in the training dataset can be found [here](https://docs.google.com/document/d/1IbzrJuyOBRFNTzXzcvw_y0O25fVfj2osJFs1TukHflw/edit?usp=sharing).\n\n##Important columns are:\n* `sample_id`: unique ID\n* `Coor_X`, `Coor_Y`: easting and northing in EPSG 3035\n* `observation_year`: observation year\n* ` UUID`: Universally Unique Identifier (https://en.wikipedia.org/wiki/Universally_unique_identifier) this allows you to point to exact sample / unique row\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "Soil erosion poses a significant threat to environmental stability, impacting food security and ecosystem health. This hackathon focuses on developing practical solutions that utilize open Earth Observation (EO) data provided by ESA and other leading space agencies to help map occurrence of gully erosion at detailed spatial resolution. Your innovative models will contribute to enhancing the accuracy of soil degradation estimates, aiding in the fight against soil erosion.\n\n![Figure 1](https://www.googleapis.com/download/storage/v1/b/kaggle-user-content/o/inbox%2F6592816%2Fc684da63c6f5ab41e4d653b43460a2f0%2FScreenshot%20from%202024-01-31%2022-22-03.png?generation=1706736140378171&alt=media)",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "The submissions will be evaluated using **weighted F1-score**, to select models that achieve both high precision in correctly identifying erosion events and high recall in detecting as many true erosion instances as possible.\n\n## Submission File\nFor each `sample_id` in the test set, the participants must predict the erosion class `Code` (string/factor or integer). The file should contain a header and have the following format:\n```\nsample_id,Code\n1012,0\n5006,1\n9999,2\n ```",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "rules",
      "content": "##General\n1. Hackathon will run in two rounds. In the first round, top 5 best performing candidates (evaluation criteria in Kaggle) meeting all other requirements will be selected and invited to submit their computational notebooks. In the second round, the best (winner) and 2nd best participants will be selected by the review committee based on their computational notebook. Participants that do not reveal their modeling steps or are not able to reproduce results will not be considered for the best price.\n2. Hackathons / results need to be submitted via Kaggle.com in a timely manner. Deadlines will be followed strictly in second. Submission outside the deadline will not be considered.\n3. Participants will be given a number of covariate layers that they can use to model the target feature (SOC / occurrence of gully erosion), but can also add new layers of choice. Basically participants have complete freedom to choose a modeling framework and add additional covariates, however, results produced need to be reproducible i.e. ALL steps need to be documented in code. The reviewing committee might request to access some additional input data to check that the procedure is correct.\n4. Winners of the hackathons will be invited to present their steps during the event at ESRIN (either online or in person).\n5. Maximum number of participants in the participating team allowed is: 2.\n\n##Submission Limits\nParticipants may submit a maximum of 5 entries per day.\nParticipants may select up to 2 final submissions for judging.\n\n##Competition Timeline\n* Start Date: February 2, 2024\n* End Date: February 16, 2024\n\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "abstract",
      "content": "Welcome to our hackathon events hosted by the [OpenGeoHub Foundation](https://opengeohub.org/) in collaboration with the European Space Agency (ESA) as part of the **[ESA Symposium on EO 4 Soil Protection and Restoration 6–7 March 2024 at ESA-ESRIN center, Frascati, Italy](https://www.eo4soilprotection.org/)**! The European Space Agency (ESA), along with EO research communities, recognizes the urgency of improving monitoring systems for soil health. These hackathons aim to unite researchers, students, scientists, and technology enthusiasts to address these challenges using open-source remote sensing data and legacy soil data.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Timeline",
      "content": "- Start: 2nd of February, 2024\n- Close: **16th of February 23:59 CET, 2024**\n- Winners announced: 7th March 2024 at the closing session of the Symposium.\n- **The deadlines will be followed strictly.** May the best team win!",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Rewards and Recognition",
      "content": "Winners of the hackathon will be awarded the chance to showcase their results at ESA’s Symposium on Earth Observation for Soil Protection and Restoration, scheduled in Frascati, Italy, from March 6–7, 2024. Additionally, the winning teams will receive:\n\n- A €15k voucher for cloud processing at ESA’s NoR.\n- A life-long Enhanced Membership for the Open Access PeerJ journals.\n- A 15-minute slot to present their method at the Symposium.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Acknowledgements",
      "content": "These hackathons were made possible thanks to the AI4SoilHealth and Open-Earth-Monitor Cyberinfrastructure projects. [AI4SoilHealth](https://ai4soilhealth.eu/) project has received funding from the European Union’s Horizon Europe research and innovation programme under grant agreement [No. 101086179](https://cordis.europa.eu/project/id/101086179). [EarthMonitor.org](https://earthmonitor.org/) project has received funding from the European Union’s Horizon Europe research an innovation programme under grant agreement [No. 101059548](https://cordis.europa.eu/project/id/101059548). \n\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Literature of interest",
      "content": "- Agostini, M., Mondini, A. C., Torri, D., & Rossi, M. (2022). Modelling seasonal variation of gully erosion at the catchment scale. Earth Surface Processes and Landforms, 47(2), 436-458. https://doi.org/10.1002/esp.5259 \n- Borrelli, P., Alewell, C., Alvarez, P., Anache, J. A. A., Baartman, J., Ballabio, C., ... & Panagos, P. (2021). Soil erosion modelling: A global review and statistical analysis. Science of the total environment, 780, 146494. https://doi.org/10.1016/j.scitotenv.2021.146494\n- Huang, X., Xiong, L., Jiang, Y., Li, S., Liu, K., Ding, H., & Tang, G. (2023). Mapping gully affected areas by using Sentinel 2 imagery and digital elevation model based on the Google Earth Engine. Catena, 233, 107473. https://doi.org/10.1016/j.catena.2023.107473 \n- Vanmaercke, M., Panagos, P., Vanwalleghem, T., Hayas, A., Foerster, S., Borrelli, P., ... & Poesen, J. (2021). Measuring, modelling and managing gully erosion at large scales: A state of the art. Earth-Science Reviews, 218, 103637. https://doi.org/10.1016/j.earscirev.2021.103637 ",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}