GeoAI Arctic Mapping Challenge

Resources

A central hub for help, learning materials, and policies for the GeoAI Arctic Mapping Challenge.

💡 Tip: If you’re new here, start with the Quick Links below.

Quick Links

📘 Baseline Notebook

Starter code to load data, train, and format submissions.

Open notebook

🌍 Dataset Page

Data description, formats, and visualization gallery.

View dataset

🧭 Participate

Step-by-step guide to register, submit, and score.

How to participate

🏆 Leaderboard

Track your standing and compare approaches.

Open leaderboard

💬 Discussion Forum

Ask questions and share insights with peers.

Go to forum

📧 Contact

Email the organizing team for help.

geoai-rts@asu.edu

---

Contact Us

• Competition support:
• Technical Q&A: Use the CodeBench forum for public questions: https://codebench.com/geoai-rts/forum

Tutorials & Learning Materials

Official

• Baseline notebook: ../assets/baseline_notebook.ipynb
  Includes data loading, visualization, baseline model, and submission formatter.
• Submission format mini-guide: See Participate → Results Format for JSON schema.

External

• PyTorch segmentation recipes (Instance/semantic fundamentals)
  
• Detectron2 / MaskRCNN quickstarts (for instance masks)
  
• GeoTIFF & raster I/O (rasterio, xarray, rioxarray)
  
• Geospatial features (GDAL, PROJ, coordinate systems refresher)

Terms & Conditions

• Data Usage
  • The dataset is provided for research and competition purposes within this challenge.
  • Redistribution of the dataset or derivatives outside the challenge requires permission from the original data owners and curators.
• Attribution
  • Works or publications using this dataset should cite:
    Yang et al., 2023 (dataset) and Li et al., 2025 (baseline model) (see citations below).
• Submissions
  • Predictions must follow the required submission format and reflect automated model outputs (no manual labeling of test sets).
  • External data usage, if allowed, must be documented in your method description (if disallowed, do not use).
• Teams & Conduct
  • Teaming is allowed (default max 5 members unless otherwise stated).
  • Do not share labels or predictions across different teams.
    
  • Follow the CodeBench code of conduct and site terms.
• Privacy
  • Team name, institution, and scores may appear on the public leaderboard.
• Disqualification
  • Violations of the rules, data misuse, or attempts to game the leaderboard may result in removal from the competition.

Questions about policy? Email

Useful External Resources

• CodeBench Platform: https://codebench.com
  
• Leaderboard: https://codebench.com/geoai-rts/leaderboard
  
• Forum: https://codebench.com/geoai-rts/forum
  
• Dataset Paper (Yang et al., 2023): https://doi.org/10.1016/j.rse.2023.113495
  
• Baseline Model (Li et al., 2025): https://doi.org/10.1109/JSTARS.2025.3564310

Frequently Asked Questions

Q1. Where do I download the data?

A: Register on CodeBench → challenge page → Download tab. Or see the Dataset Page.

Q2. What’s the submission format?

A: COCO-style JSON (see Participate → Results Format). A helper is included in the baseline notebook.

Q4. Can I keep evaluating after prizes are awarded?

A: Yes — use the Benchmark Phase for continuous, no-award evaluation.

Q5. Can I use external data?

A: Follow the rules on the Participate page. If allowed, disclose clearly in your method.