live in dev
Atmos
A cheaper, denser air quality network for Bengaluru.
Atmos is a Python + FastAPI project that simulates and optimizes air quality sensor placement across the city. The system combines real-time WAQI data, traffic-weighted zone analysis, and optimization algorithms to propose an efficient sensor network that is cheaper and more effective than the existing CAAQMS stations.
- the problem
- Bengaluru's 14 CAAQMS stations are expensive and sparse, leaving much of the city without a nearby air quality reading.
- what I built
- A FastAPI model that combines live WAQI data, traffic-weighted zones and an optimiser to place a cheaper, denser sensor network, compared side by side with the existing stations.
What it does
- Live PM2.5 and AQI readings for Bengaluru from the WAQI API, with realistic fallback data if the API is down
- Traffic-weighted zones, so sensors go where people and pollution actually are
- A hybrid optimiser using the Bounding Phase method and Golden Ratio search
- An interactive map of sensor coverage and PM2.5 per zone
- A side-by-side comparison against the 14 existing CAAQMS stations
- AQI lookup per neighbourhood, zone statistics, and a guide to PM2.5 safety
How it's built
each layer feeds the one below
Data
- WAQI live PM2.5 / AQI
- fallback data generator
Model
- traffic-weighted zones
- Bounding Phase + Golden Ratio search
- proportional sensor allocation
App
- FastAPI JSON API: /api/model, /api/optimize, /api/stats
- Jinja2 pages: map, compare, zone lookup
PythonFastAPIJavaScript