Real Time Air Quality Monitoring and Forecasting by Eye in the Sky
This project is to develop an Air Pollutant Index (API) Monitoring System, which consists of different gas detector as a sensor for CO, CO2, Oxone, PM2.5 which are the root causes of pollution, Arduino Uno and Raspberry pi. Readings from the sensor has been compared with reference data from the Air
2025-06-28 16:34:42 - Adil Khan
Real Time Air Quality Monitoring and Forecasting by Eye in the Sky
Project Area of Specialization Electrical/Electronic EngineeringProject SummaryThis project is to develop an Air Pollutant Index (API) Monitoring System, which consists of different gas detector as a sensor for CO, CO2, Oxone, PM2.5 which are the root causes of pollution, Arduino Uno and Raspberry pi. Readings from the sensor has been compared with reference data from the Air Visual open source application that provide an extended dataset. The developed gas detector is expected to provide a relatively accurate API reading and suitable to be used for the detection and monitoring of pollution of various areas. The most demanding thing would be this system will give the real time data and will show the quality of the air based on the standard air quality. The system will detect the number of vehicles that are causing pollution and will do so by image segmentation. The cameraon the device will take real time pictures of the area and using the concept of machine learning and image processing we will get the information of the cause of pollution. The system will give the user the indication of the air quality and based on given parameters it will let the user know how much the environmental air is polluted or safe. This system will do everything on behalf of human in such a way that for a smart city when people will have less time for spending and there will be more industry and air will be more polluted this device will let people know how safe the air is.
Project ObjectivesThe main objectives of this project are:
- Developing hardware to track and assert the air quality in a city based on IOT topology.
- To machine learn the device for image segmentation.
- Samples metrics the EPA uses to calculate Air Quality Index and calculates AQI.
- To develop a portable API acquisition device that can get real time information and status of air pollutants.
There are two phases of the project:
Phase I is considered of sensor-based detection of gases which would be interface with the micro-controller.
Phase II comprises of collection of GPS data to create route map approach and implement Machine Learning
Software Implementation
Interfacing of Senors
We are using Arduino IDE for interfacing of all the sensors and Arduino nano as a microcontroller and for interfacing we have to perform the following tasks
- Establish connection between device and network
- Read sensor values/inputs
- Converting the analog values to digital using converter
- Uploading data to a server
- Creating Webpage for user Interface
- Read for upload data
- Display it on webpage and mobile app
Interfacing of API’s
- Saving dataset to server
- Calculating API’s of the preset Data
- Measuring the concentration of air pollutant using sensors and comparing them with preset values
- Calculating sub-API of all the pollutants and then calculating the total API
- Classifying API according to the color-coded API indicator
- Displaying API value and indicator
Image Processing using Machine Learning
- Feature mapping using the scale-invariant feature transform (SIFT) algorithm
- Image registration using the random sample consensus (RANSAC) algorithm
- Image Classification using artificial neural networks
- Image classification using convolutional neural networks (CNNs)
- Image Classification using machine learning
Hardware Implementation
Assembling of Drone
- Making the frame
- Assembling the motors
- Mounting the electronic speed controllers
- Adding the landing gear
- Mount the flight controller
- Configuring and connecting the flight controller to the electronic speed controllers.
- Calibrating its parameters using software
Assembling of Sensos
- Connecting sensors with Arduino using breadboard and jumpers
This project is a solution to monitor air quality parameters in Cities, compliant to international requirements on computing the Air Quality Index.
The data collected from air quality monitoring helps us assess impacts caused by poor air quality on public health.
The data collected from air quality monitoring would primarily help us identify polluted areas, the level of pollution and air quality level.
Air quality monitoring would assist in determining if air pollution control programmes devised in a locality are working efficiently or not.
Air quality data helps us understand the mortality rate of any location due to air pollution. We can also assess and compare the short term and long term diseases/disorders which are a result of air pollution.
Based upon the data collected control measures can be devised for protection of environment and health of all living organisms.
Technical Details of Final DeliverableThe final product will be a drone consisting of multiple sensors which will be used to detect the presence of poisonous gases at a certain altitude i.e 350-400m and will also predict the air quality using API(application program interface) through raspberry pi by some algorithms, we compare our detected sensors values to presets values, the presets values are store in database, we have taken data from the field to our server with our device. We have taken values for CO2, CO, O3, and dust. We have randomly taken presets data that is comparable with the rates that we considered as standard value. We have taken values from the environment that will show in the real time for our system. We can compare these achieved values with our table which values we taken as standard. That is, like for CO2 250 to 350 ppm and 350-1000 is at low risk according to the table. Then, 1000 to 2000 and 2000 to 5000 range is at moderate level. For 5000 it is at high level and at last above 40,000 ppm it is at very high level.
After that we have an option that is by the server it sends a message that how the level is varying on everyday basis and at which level such as low, moderate, high to the mobile app.
Our project device showed that it is effective with some highly working sensors it can really be a reliable one to everybody and its data’s will be a key to take some necessary steps for the betterment of the society as it will help to identify the affected area so that we can take early steps to reduce damages for the next generation.
Final Deliverable of the Project HW/SW integrated systemCore Industry HealthOther IndustriesCore Technology Internet of Things (IoT)Other TechnologiesSustainable Development Goals Good Health and Well-Being for People, Sustainable Cities and CommunitiesRequired Resources| Item Name | Type | No. of Units | Per Unit Cost (in Rs) | Total (in Rs) |
|---|---|---|---|---|
| Total in (Rs) | 79910 | |||
| Drone Kit | Equipment | 1 | 15500 | 15500 |
| APM 2.8 Flight Controller | Miscellaneous | 1 | 5500 | 5500 |
| M&N GPS with compass and stand | Equipment | 1 | 3000 | 3000 |
| 500mw 3Dr Radio 433 915 Telemetry Kit 433 Mhz 915Mhz Module | Equipment | 1 | 5900 | 5900 |
| Power lipo battery 11.1V 2200mA | Miscellaneous | 1 | 4000 | 4000 |
| FlySky FS-TH9X 9CH Tx with FS-R9B and charger, battery | Equipment | 1 | 14500 | 14500 |
| Gopro camera | Equipment | 1 | 15000 | 15000 |
| Flight Controller Board-anti vibration set | Equipment | 1 | 1706 | 1706 |
| MQ9 CO and flammable gas sensor | Equipment | 1 | 410 | 410 |
| MQ131 O3 sensor | Equipment | 1 | 3787 | 3787 |
| CCS811 TVOC sensor | Equipment | 1 | 3000 | 3000 |
| PMS5003 PM2.5 sensor | Equipment | 1 | 2577 | 2577 |
| DHT11 | Equipment | 1 | 350 | 350 |
| Raspberry pi 3 module B | Equipment | 1 | 4180 | 4180 |
| jumper wires, breadboard, led, resistor | Miscellaneous | 1 | 500 | 500 |