A SURVEY ON PREDICTING AIR QUALITY WITH MACHINE LEARNING TECHNIQUES
Author Name: 1. Shilpi Vishwakarma, 2. Shekhar 3. Arjun Singh
Volume/Issue: 06/01
Country: India
DOI NO.: 08.2020-25662434 DOI Link: https://doi-ds.org/doilink/06.2025-82924949/UIJIR
Affiliation:
- ABSS Institute of Technology, Meerut, UP, India
- Dewan VS Institute of Engineering & Technology, Meerut, UP, India
- ABSS Institute of Technology, Meerut, UP, India
ABSTRACT
Air quality plays a vital role in shaping environmental and public health outcomes. With rising concerns about pollution and its detrimental effects, accurate forecasting has become critical for informed planning and effective intervention. This study focuses on leveraging machine learning (ML) models for air quality prediction, aiming to deliver precise and timely assessments. A variety of ML algorithms—including support vector machines, random forests, neural networks, and gradient boosting—are applied to model the relationships between air pollutants and meteorological variables. The dataset combines historical air quality indicators with corresponding weather data from multiple monitoring sites. Data preprocessing techniques, including feature selection and outlier handling, are used to improve model robustness. Additionally, cross-validation-based hyper parameter tuning is employed to optimize prediction accuracy. Model performance is evaluated using standard metrics such as Mean Absolute Error (MAE) and Root Mean Square Error (RMSE).
Key words: Air pollution forecasting, support vector machine, random forest, gradient boosting, predictive modeling
No comment