Skip to content

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

6 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

🌬️ VayuSutra: The Virtual Sensor Grid

License: MIT Build Status Python C++

"Code for Communities" Hackathon Submission Track: CleanAir & Clear Streets (Environment)

📖 About The Project

VayuSutra solves the critical urban challenge of high-cost pollution monitoring by creating a "Virtual Sensor Grid." Municipalities rarely have the budget to deploy physical IoT air quality sensors on every street corner, resulting in massive data blind spots.

Instead of relying on expensive hardware density, VayuSutra utilizes K-Nearest Neighbors (KNN) spatial interpolation combined with Inverse Distance Weighting (IDW) to estimate real-time, block-by-block air quality based on existing, sparse government sensor data (CPCB/WAQI).

Paired with a Gemini AI-driven semantic alert system, VayuSutra transforms raw data into an actionable, localized heat map—empowering municipal planners to instantly deploy targeted interventions like water sprinklers or health advisories exactly where they are needed most.

✨ Key Features

  • 🌐 The Virtual Grid (KNN & IDW): Algorithmic spatial interpolation that fills the gaps between physical monitoring stations to provide hyper-local, street-level AQI estimations.
  • 🗺️ Live Open-Source Heat Map: Built with Leaflet.js and OpenStreetMap, visualizing the pollution data geographically without reliance on paid commercial mapping APIs.
  • 🤖 AI Semantic Alerts: Integrates the Gemini API to analyze spatial data spikes and generate context-aware, human-readable mitigation strategies for municipal workers.
  • ⚡ High-Performance Edge Simulation: Utilizes a C++ data pipeline to simulate and process high-frequency, fluctuating PM2.5 edge data, ensuring the backend can handle real-time IoT hardware streams at scale.

🛠️ Tech Stack

  • Frontend: HTML5, Tailwind CSS, JavaScript, Leaflet.js
  • Backend ML & API: Python, FastAPI, scikit-learn, Uvicorn
  • High-Performance Data Pipeline / Edge Node: C++
  • AI Engine: Google Gemini API
  • External Data: WAQI / OpenAQ APIs

🚀 Getting Started

To run this project locally, follow these steps.

Prerequisites

  • Python 3.10+
  • C++ Compiler (GCC/Clang)
  • Node.js (for Tailwind CLI, optional)

Installation

  1. Clone the repository
    git clone https://github.com/Pranq-lgtm/VayuSutra-AI
    cd VayuSutra

About

VayuSutra: An AI-powered Virtual Sensor Grid using KNN spatial interpolation and high-performance C++ edge processing to map street-level AQI without expensive hardware.

Topics

Resources

Contributing

Stars

2 stars

Watchers

0 watching

Forks

Releases

Packages

Contributors

Languages