Skip to content

An IoT-powered system for real-time air quality monitoring and analysis. This project integrates environmental sensors with a machine learning model to predict and assess air quality indices. Features include data visualization, predictive analytics, and automated alerts for actionable insights.

License

Notifications You must be signed in to change notification settings

Awais-Asghar/Crowd-Sourced-AQI-Monitoring-System

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

25 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Crowd-Sourced AQI Monitoring System

Project Status Platform Tool Communication Simulation License

Description

An IoT-based, community-driven air quality monitoring system designed to provide real-time AQI (Air Quality Index) estimation using multiple sensors. Built for both urban and rural coverage, this project empowers individuals to participate in environmental monitoring and decision-making.


Overview

This project presents a low-cost, scalable solution for air quality monitoring using IoT. It uses MQ-series gas sensors, particulate matter sensors, temperature & humidity sensors, and Bluetooth communication to calculate and visualize AQI in real-time.


What is AQI (Air Quality Index)? The Air Quality Index (AQI) is a standardized system used to measure and report the quality of air in a specific location. It tells you how clean or polluted the air is, and what associated health effects might be a concern for you.

  • AQI ranges from 0 to 500.
  • Lower AQI = cleaner air
  • Higher AQI = more polluted air
AQI Range Air Quality Health Impact
0–50 Good Air quality is satisfactory
51–100 Moderate Acceptable; some pollutants may affect very sensitive people
101–150 Unhealthy (Sensitive Groups) May cause health effects for sensitive groups
151–200 Unhealthy Everyone may begin to experience health effects
201–300 Very Unhealthy Health warnings of emergency conditions
301–500 Hazardous Health alert: everyone may be affected

AQI is calculated based on concentrations of pollutants like:

  • PM2.5, PM10
  • CO (Carbon Monoxide)
  • O₃ (Ozone)
  • SO₂ (Sulfur Dioxide)
  • NO₂ (Nitrogen Dioxide)

Image


What is Crowd-Sourcing?

Crowd-sourcing is the practice of collecting data, services, or information by engaging a large number of people, especially from a community or public platform. In this project:

  • Crowd-sourced AQI monitoring means many individuals place sensors in different locations (homes, streets, neighborhoods).
  • These devices collect air quality data from multiple locations simultaneously.
  • The data is combined to create a detailed and widespread pollution map, much more efficiently and cheaply than using a few government stations.

Image

Image


Hardware Used

Component Functionality
Arduino UNO Main microcontroller
MQ135 CO₂, NH₃, benzene detection
MQ7 Carbon Monoxide (CO)
MQ2 Smoke, LPG, Methane
PMS5003 PM2.5, PM10 detection
DHT11 / DHT22 Temperature & Humidity
BME280 Pressure, Temp, Humidity
HC-05 Bluetooth Mobile communication
16x2 LCD Display Real-time local display

Image


Block Diagram

Image

System Design

My Crowd-Sourced AQI Monitoring System is designed using IoT architecture with low-cost, easily available hardware components. It consists of:

1. Sensor Unit

  • Gas Sensors: MQ135, MQ7, MQ2 – detect CO₂, NH₃, CO, smoke, etc.
  • Particulate Matter Sensor: PMS5003 – measures PM2.5 and PM10.
  • Environmental Sensors: DHT11/DHT22 and BME280 – for temperature, humidity, and pressure.

2. Processing Unit

  • Arduino UNO: Reads data from all sensors and processes it.

3. Display Unit

  • 16x2 LCD: Displays real-time values of gas concentrations, PM levels, temperature, humidity, and calculated AQI.

4. Communication Module

  • HC-05 Bluetooth: Sends processed data to a mobile app for visualization and logging.

5. Crowd-Sourcing

  • Multiple such devices are deployed in various locations by different users (the crowd), forming a distributed monitoring network.

6. Optional Mobile App

  • Receives real-time AQI data via Bluetooth.

Working Principle

1. Data Sensing

Each sensor continuously reads the concentration of gases (like CO, CO₂, NH₃), particulate matter (PM2.5, PM10), temperature, and humidity.

2. Data Processing

  • Arduino processes the raw values.
  • Using standard EPA formulas, it calculates the AQI for each pollutant.
  • The maximum AQI among CO, PM2.5, PM10 is selected as the overall AQI.

3. Display and Transmission

  • The AQI and sensor readings are shown on the LCD.
  • The same data is sent to a connected mobile device via Bluetooth.

4. Crowd-Sourcing Model

  • When many users deploy this system in different areas, a network of real-time AQI monitors is created.
  • This increases the spatial coverage and data accuracy of air quality reports.

5. Validation

The system's output was compared with official AQI data from the US Embassy in Islamabad and showed 99% accuracy.

Sample AQI Calculation

Pollutant Concentration AQI Value AQI Category
PM2.5 162 µg/m³ 212.5 Very Unhealthy
PM10 170 µg/m³ 108.4 Unhealthy (Sensitive Groups)
CO 0.32 ppm 3.6 Good
Overall AQI 212.4 Very Unhealthy

Image


Methodology

Image

Image


Results & Analysis

Taken on 19th December, 2024 – 10:42 PM – Islamabad

Parameter Value AQI Value Health Impact
PM2.5 162 µg/m³ 212.40 Very Unhealthy
PM10 170 µg/m³ 108.42 Unhealthy (Sensitive)
CO 0.32 ppm 0 Good
  • Our AQI: 212.40
  • Accuracy: 99% vs US Embassy AQI System

Image


Future Work

Image


Contributors

  • Awais Asghar
  • Muhammad Hammad Sarwar
  • Muhammad Ashar Javid
  • School of Electrical Engineering & Computer Science (SEECS), NUST

About

An IoT-powered system for real-time air quality monitoring and analysis. This project integrates environmental sensors with a machine learning model to predict and assess air quality indices. Features include data visualization, predictive analytics, and automated alerts for actionable insights.

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages