Scribd
Upload
35 views

Air Quality Prediction System

Uploaded by

Aakriti Basnet
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
35 views

Air Quality Prediction System

Uploaded by

Aakriti Basnet
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 11

Air Quality Prediction

System
Presented by : Aakriti Basnet
Contents
• Introduction
• Objectives
• Feasibility Analysis
• Requirement Analysis
• Flowchart
• Algorithm Used
• Gantt Chart
• Expected Outcomes
Introduction
• AQI prediction system is the project where we compare the two
machine learning algorithms in predicting the Air Quality Index and its
predominant.
• The Air Quality Index (AQI) system uses a specific algorithm to
simplify and standardize the reporting of air pollution levels to the
public.
• One among them is the popular machine learning method, support
vector machine (SVM) to forecast pollutant and particulate levels and
to predict the air quality index(AQI) and other is Random Forest
Regression.
Objectives
The objectives of the AQI Prediction System are:

• Protect Public Health: Provide accurate AQI predictions to reduce health risks from
pollutants.
• Data Integration: Collect and integrate data from multiple sources to monitor air
pollution.
• Advanced Prediction Models: Use machine learning to forecast AQI levels accurately.
• Real-time Processing: Quickly process data for real-time AQI updates.
• User Accessibility: Create user-friendly interfaces and alert systems for the public.
• Support Policy Making: Help policymakers with reliable AQI data and insights.
• Community Engagement: Educate and engage the community on air quality issues.
Feasibility Analysis
The AQI prediction system is feasible for three main reasons:
• Technical Feasibility: Python and its libraries like scikit-learn and matplotlib provide
robust tools for developing and visualizing predictive models. Jupyter Notebook aids in
data analysis and prototyping, while Django facilitates seamless web application
development.
• Economic Feasibility: The system is cost-effective, balancing initial costs with
significant benefits. Improved public health, better environmental compliance, and
enhanced monitoring efficiency justify the investment, leading to optimized return on
investment (ROI).
• Scheduling Feasibility: A structured timeline and skilled personnel ensure efficient
development across phases like data acquisition, model training, and web app
creation. Risk management strategies address potential challenges, ensuring reliable
and accurate system operation.
Requirement
Analysis

Functional requirements
include data collection and
preprocessing, model training
and validation, and prediction
display through a user
interface.
Non-functional requirements
encompass system
performance, scalability, and
usability.
Flowchart
Algorithm Used
• Random Forest: Uses many decision trees to make predictions about
AQI by averaging their results. It’s good at handling complex data and
combining multiple factors to give a more accurate prediction.

• Support Vector Machine (SVM): Finds the best boundary that


separates different AQI categories based on features like pollutant
levels. It’s effective for classifying data into clear categories by
drawing a dividing line in the data space.
Gantt Chart
Expected Outcomes
• Accurate Air Quality Forecasts: The system predicts levels of pollutants like PM2.5,
PM10, NO2, SO2, CO, and O3, helping protect public health with timely alerts.
• Data Integration: It combines information from ground sensors, satellites, and
weather stations for comprehensive air quality monitoring across different areas.
• Advanced Modeling: Using cutting-edge machine learning, the system offers
reliable and adaptable AQI predictions, even during unexpected pollution events.
• Policy Support and Community Engagement: The system aids policymakers in
creating effective air quality regulations and encourages public participation in
improving local air quality through educational campaigns and interactive features.
Thank you!!
Any Question?

You might also like