Hybrid Population Based Training–ResNet Framework for Traffic-Related PM2.5 Concentration Classification

Traffic emissions serve as one of the most significant sources of atmospheric PM2.5 pollution in developing countries, driven by the prevalence of aging vehicle fleets and the inadequacy of regulatory frameworks to mitigate emissions effectively. This study presents a Hybrid Population-Based Trainin...

Full description

Saved in:
Bibliographic Details
Main Authors: Afaq Khattak, Badr T. Alsulami, Caroline Mongina Matara
Format: Article
Language:English
Published: MDPI AG 2025-03-01
Series:Atmosphere
Subjects:
Online Access:https://www.mdpi.com/2073-4433/16/3/303
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850204637520461824
author Afaq Khattak
Badr T. Alsulami
Caroline Mongina Matara
author_facet Afaq Khattak
Badr T. Alsulami
Caroline Mongina Matara
author_sort Afaq Khattak
collection DOAJ
description Traffic emissions serve as one of the most significant sources of atmospheric PM2.5 pollution in developing countries, driven by the prevalence of aging vehicle fleets and the inadequacy of regulatory frameworks to mitigate emissions effectively. This study presents a Hybrid Population-Based Training (PBT)–ResNet framework for classifying traffic-related PM2.5 levels into hazardous exposure (HE) and acceptable exposure (AE), based on the World Health Organization (WHO) guidelines. The framework integrates ResNet architectures (ResNet18, ResNet34, and ResNet50) with PBT-driven hyperparameter optimization, using data from Open-Seneca sensors along the Nairobi Expressway, combined with meteorological and traffic data. First, analysis showed that the PBT-tuned ResNet34 was the most effective model, achieving a precision (0.988), recall (0.971), F1-Score (0.979), Matthews Correlation Coefficient (MCC) of 0.904, Geometric Mean (G-Mean) of 0.962, and Balanced Accuracy (BA) of 0.962, outperforming alternative models, including ResNet18, ResNet34, and baseline approaches such as Feedforward Neural Networks (FNN), Bidirectional Long Short-Term Memory (BiLSTM), Bidirectional Gated Recurrent Unit (BiGRU), and Gene Expression Programming (GEP). Subsequent feature importance analysis using a permutation-based strategy, along with SHAP analysis, revealed that humidity and hourly traffic volume were the most influential features. The findings indicated that medium to high humidity values were associated with an increased likelihood of HE, while medium to high traffic volumes similarly contributed to the occurrence of HE.
format Article
id doaj-art-bb02d97c612a4c8cb4472dac44a1a866
institution OA Journals
issn 2073-4433
language English
publishDate 2025-03-01
publisher MDPI AG
record_format Article
series Atmosphere
spelling doaj-art-bb02d97c612a4c8cb4472dac44a1a8662025-08-20T02:11:15ZengMDPI AGAtmosphere2073-44332025-03-0116330310.3390/atmos16030303Hybrid Population Based Training–ResNet Framework for Traffic-Related PM2.5 Concentration ClassificationAfaq Khattak0Badr T. Alsulami1Caroline Mongina Matara2Department of Civil, Structural and Environmental Engineering, Trinity College Dublin, D02PN40 Dublin, IrelandCivil Engineering Department, College of Engineering and Architecture, Umm Al-Qura University, Makkah 24381, Saudi ArabiaCivil Engineering Department, Technical University of Nairobi, Nairobi P.O. Box 30197-00100, KenyaTraffic emissions serve as one of the most significant sources of atmospheric PM2.5 pollution in developing countries, driven by the prevalence of aging vehicle fleets and the inadequacy of regulatory frameworks to mitigate emissions effectively. This study presents a Hybrid Population-Based Training (PBT)–ResNet framework for classifying traffic-related PM2.5 levels into hazardous exposure (HE) and acceptable exposure (AE), based on the World Health Organization (WHO) guidelines. The framework integrates ResNet architectures (ResNet18, ResNet34, and ResNet50) with PBT-driven hyperparameter optimization, using data from Open-Seneca sensors along the Nairobi Expressway, combined with meteorological and traffic data. First, analysis showed that the PBT-tuned ResNet34 was the most effective model, achieving a precision (0.988), recall (0.971), F1-Score (0.979), Matthews Correlation Coefficient (MCC) of 0.904, Geometric Mean (G-Mean) of 0.962, and Balanced Accuracy (BA) of 0.962, outperforming alternative models, including ResNet18, ResNet34, and baseline approaches such as Feedforward Neural Networks (FNN), Bidirectional Long Short-Term Memory (BiLSTM), Bidirectional Gated Recurrent Unit (BiGRU), and Gene Expression Programming (GEP). Subsequent feature importance analysis using a permutation-based strategy, along with SHAP analysis, revealed that humidity and hourly traffic volume were the most influential features. The findings indicated that medium to high humidity values were associated with an increased likelihood of HE, while medium to high traffic volumes similarly contributed to the occurrence of HE.https://www.mdpi.com/2073-4433/16/3/303air qualityPM2.5ResNetpopulation-based training
spellingShingle Afaq Khattak
Badr T. Alsulami
Caroline Mongina Matara
Hybrid Population Based Training–ResNet Framework for Traffic-Related PM2.5 Concentration Classification
Atmosphere
air quality
PM2.5
ResNet
population-based training
title Hybrid Population Based Training–ResNet Framework for Traffic-Related PM2.5 Concentration Classification
title_full Hybrid Population Based Training–ResNet Framework for Traffic-Related PM2.5 Concentration Classification
title_fullStr Hybrid Population Based Training–ResNet Framework for Traffic-Related PM2.5 Concentration Classification
title_full_unstemmed Hybrid Population Based Training–ResNet Framework for Traffic-Related PM2.5 Concentration Classification
title_short Hybrid Population Based Training–ResNet Framework for Traffic-Related PM2.5 Concentration Classification
title_sort hybrid population based training resnet framework for traffic related pm2 5 concentration classification
topic air quality
PM2.5
ResNet
population-based training
url https://www.mdpi.com/2073-4433/16/3/303
work_keys_str_mv AT afaqkhattak hybridpopulationbasedtrainingresnetframeworkfortrafficrelatedpm25concentrationclassification
AT badrtalsulami hybridpopulationbasedtrainingresnetframeworkfortrafficrelatedpm25concentrationclassification
AT carolinemonginamatara hybridpopulationbasedtrainingresnetframeworkfortrafficrelatedpm25concentrationclassification