Scribd
Upload
7 views2 pages

Phase1. (Team 11) Document

The project aims to predict air quality index (AQI) levels using machine learning techniques and historical environmental data to address air pollution issues. Key objectives include identifying pollutants influencing AQI and providing visual insights for decision-making. The methodology involves data collection, cleaning, exploratory data analysis, model building, and optional deployment using tools like Streamlit or Flask.

Uploaded by

dillirani805
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
7 views2 pages

Phase1. (Team 11) Document

The project aims to predict air quality index (AQI) levels using machine learning techniques and historical environmental data to address air pollution issues. Key objectives include identifying pollutants influencing AQI and providing visual insights for decision-making. The methodology involves data collection, cleaning, exploratory data analysis, model building, and optional deployment using tools like Streamlit or Flask.

Uploaded by

dillirani805
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 2

Phase-1

Student Name: Dilli Rani K, Henaprincy M, Gayathri P


Register Number: 212923106013, 212923106022, 212923106018
Institution: St. Joseph College of Engineering
Department: Electronics and Communication Engineering
Date of Submission: 25.04.2025

1.Problem Statement

Air pollution poses serious health and environmental risks. Accurately predicting air quality
levels can help authorities take timely action to protect public health and mitigate harmful
effects. The goal is to use machine learning techniques to forecast air quality and identify
contributing factors.

2.Objectives of the Project

❖ Predict future air quality index (AQI) levels using historical environmental data.
❖ Identify key pollutants and features that influence AQI.
❖ Provide insights and visualizations to aid decision-making and public awareness.

3.Scope of the Project

Analyze historical air quality datasets.


Develop regression or classification models to predict AQI.
Create dashboards or visualizations for interpretability.
Constraints:
Model depends on data availability and quality; real-time deployment may be limited by data
access.

4.Data Sources

Dataset from Kaggle:


[e.g., “Air Quality Data in India”]
Public dataset, static (can be updated periodically)

Variables:
PM2.5, PM10, NO2, SO2, CO, temperature, humidity, wind speed, etc.

5.High-Level Methodology
Data Collection:
Download from Kaggle/UCI or via API.

Data Cleaning:
Handle missing values, remove duplicates, standardize formats.

EDA:
Use seaborn/matplotlib for correlation heatmaps, time series plots.

Feature Engineering:
Add rolling averages, time lags, or weather indices.

Model Building:
Random Forest, XGBoost, LSTM (for time series).

Model Evaluation:
RMSE, MAE, R² score.

Visualization & Interpretation:


Dashboards, plots showing pollutant trends.

Deployment:
Optional—deploy using Streamlit or Flask for demo purposes.

6.Tools and Technologies

Programming Language: Python


Notebook/IDE: Jupyter Notebook, Google Colab
Libraries: pandas, numpy, matplotlib, seaborn, scikit-learn, XGBoost
Optional Tools for Deployment: Streamlit, Flask

7.Team Members and Roles

K. Dilli Rani – Data collection, EDA, model building


M. Hena princy – Data cleaning, feature engineering
P. Gayathri– Visualization, report preparation, deployment

You might also like