Scalable Air-Quality Sensor Placement

This repository contains the website for the paper "Scalable Air-Quality Sensor Placement via Gradient-Based Mutual Information Maximization" accepted to AAAI 2026 (AI for Social Impact Track).

Authors: Zeel B Patel, Vinayak Rana, Nipun Batra

Website

Visit the live website at: https://sustainability-lab.github.io/gdmi/

About

Air pollution is a leading global health threat, yet many developing countries lack dense monitoring infrastructure. This work presents a scalable, gradient-based optimization framework that treats sensor coordinates as differentiable parameters for optimal sensor placement.

Key Results:

• 4% RMSE improvement over Maximum Variance heuristic
• Orders of magnitude speedup over information-theoretic methods
• Runtime independent of candidate pool size
• Spatially balanced placements avoiding clustering

Local Development

To build and preview the website locally:

# Install Quarto from https://quarto.org/docs/get-started/

# Render the website
quarto render

# Preview locally
quarto preview

Deployment

The website is automatically deployed to GitHub Pages using GitHub Actions whenever changes are pushed to the main branch.

To enable GitHub Pages:

1. Go to repository Settings > Pages
2. Select "GitHub Actions" as the source
3. The site will be deployed automatically on the next push

Citation

If you use this work in your research, please cite:

@inproceedings{patel2026scalable,
  title={Scalable Air-Quality Sensor Placement via Gradient-Based
         Mutual Information Maximization},
  author={Patel, Zeel B and Rana, Vinayak and Batra, Nipun},
  booktitle={Proceedings of the AAAI Conference on
             Artificial Intelligence},
  year={2026},
  note={AI for Social Impact Track}
}

License

This work is part of the Sustainability Lab at IIT Gandhinagar and Washington University in St. Louis.

Contact

• Zeel B Patel: zeel.patel@iitgn.ac.in
• Vinayak Rana: vinayak.rana@iitgn.ac.in
• Nipun Batra: nipun.batra@iitgn.ac.in