Launch of 2024 ITU GeoAI Challenge

Go back to programme

Launch of 2024 ITU GeoAI Challenge

  • Watch

    * Register (or log in) to the AI4G Neural Network to add this session to your agenda or watch the replay

    • Register

      Watch

      * Register (or log in) to the AI4G Neural Network to add this session to your agenda or watch the replay

    ITU is launching the third edition of the GeoAI Challenge! Students and professionals from around the globe are invited to solve real-world geospatial problems with real-world data by applying artificial intelligence (AI) / machine learning (ML) to advance the United Nations Sustainable Development Goals (SDGs). 

    This session will feature the discussion of three problem statements: 

    • GEO-AI challenge for agricultural plastic cover mapping with satellite imagery”, curated by FAO, the Food and Agriculture Organization of the United Nations.
    • GeoAI Ground-level NO2 Estimation Challenge”, curated by Politecnico di Milano, Department of Civil and Environmental Engineering and University of Padua, Interdepartmental Research Centre in Geomatics (CIRGEO) 
    • GEO-AI challenge for clandestine runways detection in the Peruvian Amazonian basin with open source satellite, curated by the United Nations Office on Drugs and Crime (UNODC) 

    ITU provides a state-of-the-art, free-of-charge compute platform to participants of the Challenge who do not have adequate access to compute in their respective institutions. The compute platform will provide participants with access to: 

    • Free GPUs and CPUs 
    • Hosted Jupyter notebook server 
    • Python kernel 
    • Pre-installed machine learning packages, e.g. PyTorch and Tensorflow 

    In some of the problem statements, a baseline or reference solution may be offered which may include implementations using Jupyter notebooks. 

    Webinars, roundtables and hands-on sessions accompany the GeoAI Challenge. 

    Winners receive cash prizes and certificates. 

    Agenda: 

    • Presentation of the ITU GeoAI Challenge: goals, objectives and outlook. Andrea Manara, ITU 
    • Presentations of problem statements
      • Agricultural plastic cover mapping, Pengyu Hao (FAO) 
        • Q&A  
      • Ground-level NO2 Estimation, Francesco Pirotti (Universita di Padova, progetto GeoAIR)  
        • Q&A
      • GEO-AI challenge for clandestine runways detection in the Peruvian Amazonian basin with open source satellite, Lorenzo Vita, Jorge Caballero (UNODC) 
        • Q&A 
    • Outlook.  Maria Brovelli, Politecnico di Milano 
    • Q&A general  
    Share this session