Inspiration
Air pollution remains one of the most serious public health and environmental threats of our time, causing millions of premature deaths annually. Yet, most cities still rely on fixed, expensive monitoring stations that fail to capture localized variations in pollution levels.
The inspiration for this project came from a simple question: What if we could see the air we breathe? By combining drones, low-cost sensors, and real-time data visualization, we aimed to create a tool that makes air quality transparent, measurable, and actionable. Our goal was to design a scalable solution that empowers communities, researchers, and policymakers to better understand(and eventually reduce)air pollution.
What it does
Our system uses drones equipped with air quality sensors to collect real-time data on key pollutants such as PM2.5, NO₂, and CO₂. The data, tagged with GPS coordinates and timestamps, is transmitted to a cloud server, processed, and visualized through an interactive app.
Key features include:
Real-time pollution mapping: Visualizes air quality as dynamic heatmaps.
Historical data analysis: Allows users to track pollution trends over time.
Threshold alerts: Notifies when pollutant levels exceed safe limits.
Scalability: Multiple drones can operate simultaneously for city-wide coverage.
In essence, the system transforms drones into mobile air monitoring units, turning invisible pollution into clear, actionable insights.
How we built it
Hardware Integration:
Selected lightweight sensors (PMS5003 for PM2.5, MQ-series for gases) and mounted them on a quadcopter platform.
Used an ESP32 microcontroller for data collection and wireless transmission.
Calibrated sensors using readings from nearby ground stations.
Data Pipeline:
Programmed the microcontroller to send GPS-tagged sensor readings to a cloud database in real time.
Built a backend using Python Flask for receiving and storing incoming data.
App Development:
Designed a frontend using React.js and Leaflet.js for interactive map visualization.
Created real-time heatmaps, time-series graphs, and a dashboard for analytics.
What's next for Drone-Based Air Quality Mapping Using Sensor-Equipped UAVs
Deploy in real-world environments: Test the system in urban areas to identify pollution hotspots.
Add machine learning models: Predict future air quality trends based on collected data and weather patterns.
Enhance scalability: Develop a fleet management system for multiple drones covering wider areas.
Partner with environmental agencies: Use our data for public dashboards and city-level decision-making.
Build citizen access tools: Create mobile interfaces that let individuals monitor air quality around them.
Log in or sign up for Devpost to join the conversation.