Towards Cleaner Cities: Estimating Vehicle-Induced PM<sub>2.5</sub> with Hybrid EBM-CMA-ES Modeling

In developing countries, vehicle emissions are a major source of atmospheric pollution, worsened by aging vehicle fleets and less stringent emissions regulations. This results in elevated levels of particulate matter, contributing to the degradation of urban air quality and increasing concerns over...

Full description

Saved in:
Bibliographic Details
Main Authors: Saleh Alotaibi, Hamad Almujibah, Khalaf Alla Adam Mohamed, Adil A. M. Elhassan, Badr T. Alsulami, Abdullah Alsaluli, Afaq Khattak
Format: Article
Language:English
Published: MDPI AG 2024-11-01
Series:Toxics
Subjects:
Online Access:https://www.mdpi.com/2305-6304/12/11/827
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850267098519961600
author Saleh Alotaibi
Hamad Almujibah
Khalaf Alla Adam Mohamed
Adil A. M. Elhassan
Badr T. Alsulami
Abdullah Alsaluli
Afaq Khattak
author_facet Saleh Alotaibi
Hamad Almujibah
Khalaf Alla Adam Mohamed
Adil A. M. Elhassan
Badr T. Alsulami
Abdullah Alsaluli
Afaq Khattak
author_sort Saleh Alotaibi
collection DOAJ
description In developing countries, vehicle emissions are a major source of atmospheric pollution, worsened by aging vehicle fleets and less stringent emissions regulations. This results in elevated levels of particulate matter, contributing to the degradation of urban air quality and increasing concerns over the broader effects of atmospheric emissions on human health. This study proposes a Hybrid Explainable Boosting Machine (EBM) framework, optimized using the Covariance Matrix Adaptation Evolution Strategy (CMA-ES), to predict vehicle-related PM<sub>2.5</sub> concentrations and analyze contributing factors. Air quality data were collected from Open-Seneca sensors installed along the Nairobi Expressway, alongside meteorological and traffic data. The CMA-ES-tuned EBM model achieved a Mean Absolute Error (MAE) of 2.033 and an R<sup>2</sup> of 0.843, outperforming other models. A key strength of the EBM is its interpretability, revealing that the location was the most critical factor influencing PM<sub>2.5</sub> concentrations, followed by humidity and temperature. Elevated PM<sub>2.5</sub> levels were observed near the Westlands roundabout, and medium to high humidity correlated with higher PM<sub>2.5</sub> levels. Furthermore, the interaction between humidity and traffic volume played a significant role in determining PM<sub>2.5</sub> concentrations. By combining CMA-ES for hyperparameter optimization and EBM for prediction and interpretation, this study provides both high predictive accuracy and valuable insights into the environmental drivers of urban air pollution, providing practical guidance for air quality management.
format Article
id doaj-art-47dae3be98a34fc09823fa359d190d31
institution OA Journals
issn 2305-6304
language English
publishDate 2024-11-01
publisher MDPI AG
record_format Article
series Toxics
spelling doaj-art-47dae3be98a34fc09823fa359d190d312025-08-20T01:53:56ZengMDPI AGToxics2305-63042024-11-01121182710.3390/toxics12110827Towards Cleaner Cities: Estimating Vehicle-Induced PM<sub>2.5</sub> with Hybrid EBM-CMA-ES ModelingSaleh Alotaibi0Hamad Almujibah1Khalaf Alla Adam Mohamed2Adil A. M. Elhassan3Badr T. Alsulami4Abdullah Alsaluli5Afaq Khattak6Civil and Environmental Engineering Department, Faculty of Engineering—Rabigh Branch, King Abdulaziz University, Jeddah 21589, Saudi ArabiaDepartment of Civil Engineering, College of Engineering, Taif University, Taif 21944, Saudi ArabiaDepartment of Civil Engineering, College of Engineering, Bisha University, Bisha 61361, Saudi ArabiaDepartment of Civil Engineering, College of Engineering, Taif University, Taif 21944, Saudi ArabiaDepartment of Civil Engineering, College of Engineering and Architecture, Umm Al-Qura University, Makkah 24382, Saudi ArabiaDepartment of Civil Engineering, College of Engineering, Taif University, Taif 21944, Saudi ArabiaDepartment of Civil, Structural and Environmental Engineering, Trinity College Dublin, D02 PN40 Dublin, IrelandIn developing countries, vehicle emissions are a major source of atmospheric pollution, worsened by aging vehicle fleets and less stringent emissions regulations. This results in elevated levels of particulate matter, contributing to the degradation of urban air quality and increasing concerns over the broader effects of atmospheric emissions on human health. This study proposes a Hybrid Explainable Boosting Machine (EBM) framework, optimized using the Covariance Matrix Adaptation Evolution Strategy (CMA-ES), to predict vehicle-related PM<sub>2.5</sub> concentrations and analyze contributing factors. Air quality data were collected from Open-Seneca sensors installed along the Nairobi Expressway, alongside meteorological and traffic data. The CMA-ES-tuned EBM model achieved a Mean Absolute Error (MAE) of 2.033 and an R<sup>2</sup> of 0.843, outperforming other models. A key strength of the EBM is its interpretability, revealing that the location was the most critical factor influencing PM<sub>2.5</sub> concentrations, followed by humidity and temperature. Elevated PM<sub>2.5</sub> levels were observed near the Westlands roundabout, and medium to high humidity correlated with higher PM<sub>2.5</sub> levels. Furthermore, the interaction between humidity and traffic volume played a significant role in determining PM<sub>2.5</sub> concentrations. By combining CMA-ES for hyperparameter optimization and EBM for prediction and interpretation, this study provides both high predictive accuracy and valuable insights into the environmental drivers of urban air pollution, providing practical guidance for air quality management.https://www.mdpi.com/2305-6304/12/11/827air qualityPM<sub>2.5</sub>explainable boosting machinecovariance matrix adaptation evolution strategy
spellingShingle Saleh Alotaibi
Hamad Almujibah
Khalaf Alla Adam Mohamed
Adil A. M. Elhassan
Badr T. Alsulami
Abdullah Alsaluli
Afaq Khattak
Towards Cleaner Cities: Estimating Vehicle-Induced PM<sub>2.5</sub> with Hybrid EBM-CMA-ES Modeling
Toxics
air quality
PM<sub>2.5</sub>
explainable boosting machine
covariance matrix adaptation evolution strategy
title Towards Cleaner Cities: Estimating Vehicle-Induced PM<sub>2.5</sub> with Hybrid EBM-CMA-ES Modeling
title_full Towards Cleaner Cities: Estimating Vehicle-Induced PM<sub>2.5</sub> with Hybrid EBM-CMA-ES Modeling
title_fullStr Towards Cleaner Cities: Estimating Vehicle-Induced PM<sub>2.5</sub> with Hybrid EBM-CMA-ES Modeling
title_full_unstemmed Towards Cleaner Cities: Estimating Vehicle-Induced PM<sub>2.5</sub> with Hybrid EBM-CMA-ES Modeling
title_short Towards Cleaner Cities: Estimating Vehicle-Induced PM<sub>2.5</sub> with Hybrid EBM-CMA-ES Modeling
title_sort towards cleaner cities estimating vehicle induced pm sub 2 5 sub with hybrid ebm cma es modeling
topic air quality
PM<sub>2.5</sub>
explainable boosting machine
covariance matrix adaptation evolution strategy
url https://www.mdpi.com/2305-6304/12/11/827
work_keys_str_mv AT salehalotaibi towardscleanercitiesestimatingvehicleinducedpmsub25subwithhybridebmcmaesmodeling
AT hamadalmujibah towardscleanercitiesestimatingvehicleinducedpmsub25subwithhybridebmcmaesmodeling
AT khalafallaadammohamed towardscleanercitiesestimatingvehicleinducedpmsub25subwithhybridebmcmaesmodeling
AT adilamelhassan towardscleanercitiesestimatingvehicleinducedpmsub25subwithhybridebmcmaesmodeling
AT badrtalsulami towardscleanercitiesestimatingvehicleinducedpmsub25subwithhybridebmcmaesmodeling
AT abdullahalsaluli towardscleanercitiesestimatingvehicleinducedpmsub25subwithhybridebmcmaesmodeling
AT afaqkhattak towardscleanercitiesestimatingvehicleinducedpmsub25subwithhybridebmcmaesmodeling