{
  "fetched_at": "2026-10-24T15:36:19Z",
  "source_url": "https://www.kaggle.com/competitions/beyond-visible-spectrum-ai-for-agriculture-2023-p2/data",
  "pages": [
    {
      "name": "data-description",
      "content": "## Un-Supervised training data\n\nThe data for SSL training can be download [https://cropdis.s3.eu-west-2.amazonaws.com/s2a.tar.gz](url)\n\n## Supervised training data\n\n`kaggle competitions download -c beyond-visible-spectrum-ai-for-agriculture-2023-p2`\n\n##Submission Columns\n\n*   `Id` - file name\n*   `Category` - rice, wheat, maize, soybean",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "rules",
      "content": "# Introduction\n\nParticipants from all over the world can take part in the challenge. \nYou must be over 18, or of legal age in your jurisdiction, in order to participate.\n\n\n# Timing and duration\nThe Crop disease challenge will take place online from **1  July to 10 August, 2022**.\n\n\n# Creating and submitting a solution\n\n\n\n1. For the challenge, you will have access to the training datasets and a range of tools in the form of a Jupyter notebook (Starter Pack). No other datasets can be used for the development of your solution. However, pre-trained models are allowed.\n\n- The data for this competition is available in the Kaggle webpage ([Data](https://www.kaggle.com/competitions/beyond-visible-spectrum/data)). It can be downloaded or processed using Kaggle's computing services.\n\n- Here is a short code example for data reading and processing the data ([Starter](https://www.kaggle.com/code/robeson/starter)).\n\n2. Each participant will be allowed to upload their solutions every 12 hours (to avoid overload and unfair behaviors).\n\n3. The final submission of your solution must be made by **10 August, 2022**, and each valid submission must consist a Jupyter notebook with the implementation of their final algorithm to allow the Organizers to reproduce the predictions.\n\n# Challenge evaluation\nThe evaluation of the solutions submitted will be performed in two stages:\n\n1. Quantitative analysis: live scoring of the quality of your solution throughout the challenge, which will be visible on the leaderboard on this platform; \n\n2. Qualitative analysis of your code performed by the Organizers. The qualitative analysis is performed only for proving the validity and reproducibility of your solution.\n\nThe final score is based solely on the quantitative evaluation. However, if the solution turns out to be not reproducible, or if any concerns about its validity arise, the organizers reserve the right to contact the team leader of the corresponding team to resolve such issues. If the issues cannot be resolved, the team will not be eligible to receive prizes.\n\nFor more details on the metrics, see the Metrics section in the Data page.\n\n\n\n\n\n\n\n\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "# Overview\n\nThe Food and Agriculture Organization of the United Nations (FAO) estimates that current agricultural production needs to grow by up to 70 percent by 2050 in order to meet the expected population growth on Earth. This poses a significant challenge for food production, which requires solutions that not only enhance agricultural methods but also adapt them radically to environmental pressures. Big data, machine learning and artificial intelligence (AI) have the potential to play a vital role in this process.\n\nThe crop type classification is an important part of agriculture as an industry. Remote sensing data offers large scale, long term, continuous monitoring on the ground and has long been used as an extremely useful tool for crop classification. Identifying crops using traditional supervised learning methods can be a challenging task, as obtaining a large number of ground-truthing training samples is often a time-consuming and laborious work.\n\n\nIn recent years, there has been a new research trend to train models without using labels, named Self-supervised learning (SSL). It has been effectively applied in many fields such as computer vision, natural language processing, and object detection. In fact, by extracting representative features from unlabelled data, the SSL algorithm has outperformed supervised pre-training on many problems. In this respect, self-supervised learning is a promising avenue for remote sensing research.\n\n\nIn this challenge, we will release a massive remote sensing dataset in cropland area, including multispectral and SAR data for participants to train their self-supervised learning models. A crop classification task will be set up to evaluate the effectiveness of their SSL model.\n\n![](https://raw.githubusercontent.com/robeson1010/Agvision/main/imgs/KAGGLE.png)\n\n\n\n# Challenge keywords\n\nRemote sensing; Hyperspectral; Crop disease; Self-supervised learning; Crop classification; Deep learning\n\n\n# Participation instructions\n\nYou can participate in the competition via this link! [https://www.kaggle.com/t/beb5449750ca4c85bf7c166698f2833b](https://www.kaggle.com/t/beb5449750ca4c85bf7c166698f2833b)\n\n# Workshop/conference\n\nThis challenge is part of the conference on “[The Fourth conference of Monitoring, Early Warning, and Scientific Management of Vegetation Pests and Diseases]()” in Aug 2023.\n\n# Publication and Future Plans \n\nWe will write a summary paper of top 5 winning methods to be published in Remote Sensing Special issue of “Monitoring, Early Warning, and Scientific Management of Vegetation Pests and Diseases”.  \nOur goal is to update the dataset with different types of diseases and continue to make it available for research use.\n\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "The evaluation metric for this competition is the categorization accuracy.\n\nThree types are set as follows: Rust, Health and Other\n\n## Submission Format\n\nSubmission files should contain two columns: `Id` and `Category`. \n\nThe file should contain a header and have the following format:\n```\nId\tCategory\n101.tif\tRust\n102.tif\tHealth\n103.tif\tOther",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "People",
      "content": "# Organisers\nProf. Liangxiu Han, Manchester Metropolitan University\nProf. Wenjiang Huang, Aerospace Information Research Institute, Chinese Academy of Sciences\n\n# Technical Chairs\nDr. Xin Zhang, Manchester Metropolitan University\nDr. Yingying, Dong Aerospace Information Research Institute, Chinese Academy of Sciences\nTam Sobieh, Manchester Metropolitan University\n\n# Primary contact\nLiangxiu Han - Email: l.han@mmu.ac.uk\nWenjiang Huang - Email: huangwj@radi.ac.cn",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}