Home / Current Issue / Paper 1710528
Predicting Air Quality Index (AQI) in Western Uttar Pradesh Cities Using Machine Learning Models: A Comparative Analysis
Subject area: Science,Engineering and Technology · Area of research: Air Quality Index
DOI: https://doi.org/10.64388/IREV9I3-1710528-450
Abstract
The objective of this project is to use a variety of machine learning techniques to create a reliable predictive model for predicting the Air Quality Index (AQI) in Indian cities in Western Uttar Pradesh. The data came from the Central Pollution Control Board (CPCB) and covered the years January 2024 to December 2024. Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), and Coefficient of Determination (R2) were the primary evaluation metrics used to compare the performance of the four machine learning models: Linear Regression, K-Nearest Neighbors (KNN), Decision Tree Regressor, and Random Forest Regressor. In terms of predicted accuracy, XGBoost outperformed the other algorithms among these models, exhibiting an impressive R2 value of 0.9967. Together with lower MSE and RMSE values, the XGBoost model demonstrated a significant decrease in MAE (3.5282) when compared to the other models, whose MAEs ranged from 18.148. These results suggested that the predictions were more accurate and had less volatility. Agra, Meerut, Ghaziabad, Bareilly, and Vrindavan were the five cities in which the study also examined AQI trends. According to the findings, the highest AQI recorded in Agra was 321.89 in November, while the highest AQI recorded in Meerut was 427.09 in the same month. The highest AQI in Bareilly was recorded in February (118.73), while the highest in Ghaziabad was recorded in January (413.57). October saw the highest AQI in Vrindavan (309.41). These cities' varying average AQIs were a reflection of seasonal variations in air pollution levels.
Keywords
Linear Regression, Random Forest, Decision Tree Regressor, K-Nearest Neighbors (KNN), Western Uttar Pradesh
How to cite this paper
@article{1710528,
author = {Salil Kumar Gupta, Praveen Kumar Yadav},
title = {Predicting Air Quality Index (AQI) in Western Uttar Pradesh Cities Using Machine Learning Models: A Comparative Analysis},
journal = {Iconic Research And Engineering Journals},
year = {2025},
volume = {9},
number = {3},
pages = {237-255},
issn = {2456-8880},
url = {https://www.irejournals.com/formatedpaper/1710528.pdf},
abstract = {The objective of this project is to use a variety of machine learning techniques to create a reliable predictive model for predicting the Air Quality Index (AQI) in Indian cities in Western Uttar Pradesh. The data came from the Central Pollution Control Board (CPCB) and covered the years January 2024 to December 2024. Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), and Coefficient of Determination (R2) were the primary evaluation metrics used to compare the performance of the four machine learning models: Linear Regression, K-Nearest Neighbors (KNN), Decision Tree Regressor, and Random Forest Regressor. In terms of predicted accuracy, XGBoost outperformed the other algorithms among these models, exhibiting an impressive R2 value of 0.9967. Together with lower MSE and RMSE values, the XGBoost model demonstrated a significant decrease in MAE (3.5282) when compared to the other models, whose MAEs ranged from 18.148. These results suggested that the predictions were more accurate and had less volatility. Agra, Meerut, Ghaziabad, Bareilly, and Vrindavan were the five cities in which the study also examined AQI trends. According to the findings, the highest AQI recorded in Agra was 321.89 in November, while the highest AQI recorded in Meerut was 427.09 in the same month. The highest AQI in Bareilly was recorded in February (118.73), while the highest in Ghaziabad was recorded in January (413.57). October saw the highest AQI in Vrindavan (309.41). These cities' varying average AQIs were a reflection of seasonal variations in air pollution levels.},
keywords = {Linear Regression, Random Forest, Decision Tree Regressor, K-Nearest Neighbors (KNN), Western Uttar Pradesh},
month = {September},
doi = {https://doi.org/10.64388/IREV9I3-1710528-450}
}