🍿POPCORN: High-resolution Population Maps Derived from Sentinel-1 and Sentinel-2 🌍🛰️

🏦 Photogrammetry and Remote Sensing, ETH Zürich
🍇Environmental Computation Science and Earth Observation Laboratory, EPFL Sion
💡TL;DR
POPCORN is a lightweight population mapping method using free satellite images and minimal data, surpassing existing accuracy and providing interpretable maps for mapping populations in data-scarce regions.
High resolution population maps of Rwanda derived from Sentinel-1 and Sentinel-2

🏋️ Performance

We evaluate the performance of POPCORN on three datasets: Switzerland, Rwanda, and Puerto Rico.

POPCORN scatter plott series

Our ensembled version BAG-OF-POPCORN outperforms existing methods including those with access to high-resolution satellite imagery and building footprints.

POPCORN Swiss Performance

🛠️ How it works

The core of our method is a neural network model, termed POPCORN. It uses Sentinel-1, Sentinel-2 and a coarse population census outputs high-resolution population maps.

POPCORN overview scheme

The model has two components: (1) a pre-trained, frozen built-up area extractor; and (2) a building occupancy module that we train through weak supervision with coarse census counts, as illustrated in the Figure below. The model operates at the full Sentinel-1/-2 resolution, i.e., its output has a nominal spatial resolution of 10m. However, for the final product and evaluation, we recommend aggregating the raw output to a 1ha (100x100m) grid, as done for the evaluation of the paper.

Popcorn training scheme

📰 News

  • 14th May 2024: Predictions for Switzerland (`che`), Rwanda (`rwa`), and Puerto Rico (`pricp2`) are now downloadable in `.tif` format. Download the data here .
  • 12th May 2024: We updated the code base with our sparse head implementation. All experiments can now be run with <24GB GPU Memory. View Code on GitHub.
  • 5th May 2024: We published the training code. View Code on GitHub.
  • 20th March 2024: We published the evaluation code and the pretrained models. View Code on GitHub.
  • 17th March 2024: Website is live. Visit Website.

🎓 Citation

@article{metzger2023high,
  title={High-resolution Population Maps Derived from Sentinel-1 and Sentinel-2},
  author={Metzger, Nando and Daudt, Rodrigo Caye and Tuia, Devis and Schindler, Konrad},
  journal={arXiv preprint arXiv:2311.14006},
  year={2023} 
}