📦 Resources & Download

Access all key data, code, and paper links for the GeoPlant dataset and benchmarks.

---

🚀 Main Links

Resource	Description	Link
📄 Dataset Paper	NeurIPS 2024 paper detailing the dataset and benchmark	NeurIPS Paper (PDF)
🧠 GitHub Repository	Codebase with data loaders, baseline models, and utilities	GeoPlant Repo
🚀 Starter Notebooks	Baseline models, pipelines, and scripts	GeoPlant Code on Kaggle
📦 Full Dataset	Full data including PO and environmental rasters	GeoPlant Seafile

---

🗃️ Dataset Download

• Kaggle: Download the Presence-Absence (PA) data and ready-to-use subsets directly.
• Seafile: Full dataset including all raw environmental rasters, images, and PO data.
• HuggingFace: Browse models and pretrained weights in this collection.

---

💻 Code & Baselines

• GitHub: plantnet/GeoPlant
  – PyTorch data loaders, training scripts, and evaluation code
  – Fully reproducible baselines and benchmarks
  – Issue tracker for questions and bug reports

• Kaggle Code:
  Baseline notebooks for quick-start, all executable in-browser.

---

📚 Documentation

• Dataset Overview: Details on PA/PO data, species coverage, and splits.
• Environmental Predictors: All available modalities.
• Baselines & Benchmarking: Tasks, metrics, and baseline performance.

---

❓ Questions or Issues?

• For dataset or technical questions, open an issue on GitHub.
• For contribution, bug fixes, or ideas, create a pull request or discussion thread!

---

Tip: For large downloads, prefer the zipped archives on Seafile. See ReadMe files inside each folder for detailed variable descriptions and file organization.

📑 Citation

If you use GeoPlant in your research or applications, please cite the dataset paper:

BibTeX

@inproceedings{picek2024geoplant,
  title={GeoPlant: A Large-Scale Multimodal Dataset for High-Resolution Plant Species Prediction},
  author={Picek, Lukáš and Joly, Alexis and Servajean, Maximilien and Botella, Chris and others},
  booktitle={Advances in Neural Information Processing Systems (NeurIPS) Datasets and Benchmarks Track},
  year={2024},
  url={https://proceedings.neurips.cc/paper_files/paper/2024/file/e4e7de47202bda8133dd3e8b46205cf2-Paper-Datasets_and_Benchmarks_Track.pdf}
}