Efficient Air Quality Prediction Models Based on Supervised Machine Learning Techniques

Air pollution is a serious concern for public health, linked to many diseases and an increase in fatalities. To tackle these issues, it's crucial to set up prediction systems allowing officials to act before high pollution levels occur. This study explores how supervised machine learning method...

Full description

Saved in:
Bibliographic Details
Main Authors: Oumoulylte Mariame, El Allaoui Ahmad, Farhaoui Yousef, Boughrous Ali Ait
Format: Article
Language:English
Published: EDP Sciences 2025-01-01
Series:E3S Web of Conferences
Online Access:https://www.e3s-conferences.org/articles/e3sconf/pdf/2025/32/e3sconf_joe52025_02012.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849336117478817792
author Oumoulylte Mariame
El Allaoui Ahmad
Farhaoui Yousef
Boughrous Ali Ait
author_facet Oumoulylte Mariame
El Allaoui Ahmad
Farhaoui Yousef
Boughrous Ali Ait
author_sort Oumoulylte Mariame
collection DOAJ
description Air pollution is a serious concern for public health, linked to many diseases and an increase in fatalities. To tackle these issues, it's crucial to set up prediction systems allowing officials to act before high pollution levels occur. This study explores how supervised machine learning methods can help predict air quality based on historicaland current environmental data. We assess the effectiveness of algorithms such as Random Forest, K-Nearest Neighbors, Support Vector Machine, Logistic Regression, and Gradient Boosting. Important factors like PM2.5, PM10, NO2, SO2, and CO pollution levels are examined, along with weather elements like temperature and humidity. Our findings suggest that machine learning models can reliably forecast air quality, helping manage pollution and protect public health, with Random Forest showing the best results among the models tested.
format Article
id doaj-art-409c5daecd9c4f94b3bd3417646d34a6
institution Kabale University
issn 2267-1242
language English
publishDate 2025-01-01
publisher EDP Sciences
record_format Article
series E3S Web of Conferences
spelling doaj-art-409c5daecd9c4f94b3bd3417646d34a62025-08-20T03:45:04ZengEDP SciencesE3S Web of Conferences2267-12422025-01-016320201210.1051/e3sconf/202563202012e3sconf_joe52025_02012Efficient Air Quality Prediction Models Based on Supervised Machine Learning TechniquesOumoulylte Mariame0El Allaoui Ahmad1Farhaoui Yousef2Boughrous Ali Ait3IMIA laboratory, T-IDMS, FST Errachidia, Moulay Ismail University of MeknesIMIA laboratory, T-IDMS, FST Errachidia, Moulay Ismail University of MeknesIMIA laboratory, T-IDMS, FST Errachidia, Moulay Ismail University of MeknesResearch Team: Bio-ressources, Environment and Health, Department of Biology, FST Errachidia, Moulay Ismail University of MeknesAir pollution is a serious concern for public health, linked to many diseases and an increase in fatalities. To tackle these issues, it's crucial to set up prediction systems allowing officials to act before high pollution levels occur. This study explores how supervised machine learning methods can help predict air quality based on historicaland current environmental data. We assess the effectiveness of algorithms such as Random Forest, K-Nearest Neighbors, Support Vector Machine, Logistic Regression, and Gradient Boosting. Important factors like PM2.5, PM10, NO2, SO2, and CO pollution levels are examined, along with weather elements like temperature and humidity. Our findings suggest that machine learning models can reliably forecast air quality, helping manage pollution and protect public health, with Random Forest showing the best results among the models tested.https://www.e3s-conferences.org/articles/e3sconf/pdf/2025/32/e3sconf_joe52025_02012.pdf
spellingShingle Oumoulylte Mariame
El Allaoui Ahmad
Farhaoui Yousef
Boughrous Ali Ait
Efficient Air Quality Prediction Models Based on Supervised Machine Learning Techniques
E3S Web of Conferences
title Efficient Air Quality Prediction Models Based on Supervised Machine Learning Techniques
title_full Efficient Air Quality Prediction Models Based on Supervised Machine Learning Techniques
title_fullStr Efficient Air Quality Prediction Models Based on Supervised Machine Learning Techniques
title_full_unstemmed Efficient Air Quality Prediction Models Based on Supervised Machine Learning Techniques
title_short Efficient Air Quality Prediction Models Based on Supervised Machine Learning Techniques
title_sort efficient air quality prediction models based on supervised machine learning techniques
url https://www.e3s-conferences.org/articles/e3sconf/pdf/2025/32/e3sconf_joe52025_02012.pdf
work_keys_str_mv AT oumoulyltemariame efficientairqualitypredictionmodelsbasedonsupervisedmachinelearningtechniques
AT elallaouiahmad efficientairqualitypredictionmodelsbasedonsupervisedmachinelearningtechniques
AT farhaouiyousef efficientairqualitypredictionmodelsbasedonsupervisedmachinelearningtechniques
AT boughrousaliait efficientairqualitypredictionmodelsbasedonsupervisedmachinelearningtechniques