Prediction of Vehicle-induced Air Pollution based on Advanced Machine Learning Models

Vehicle-induced air pollution is an important issue in the 21st century, posing detrimental effects on human health. Prediction of vehicle-emitted air pollutants and evaluation of the diverse factors that contribute to them are of the utmost importance. This study employed advanced tree-based machin...

Full description

Bibliographic Details
Main Authors: Caroline Matara, Simpson Osano, Amir Okeyo Yusuf, Elisha Ochungo Aketch
Format: Article
Language:English
Published: D. G. Pylarinos 2024-02-01
Series:Engineering, Technology & Applied Science Research
Subjects:
Online Access:https://etasr.com/index.php/ETASR/article/view/6678
_version_ 1797319260711682048
author Caroline Matara
Simpson Osano
Amir Okeyo Yusuf
Elisha Ochungo Aketch
author_facet Caroline Matara
Simpson Osano
Amir Okeyo Yusuf
Elisha Ochungo Aketch
author_sort Caroline Matara
collection DOAJ
description Vehicle-induced air pollution is an important issue in the 21st century, posing detrimental effects on human health. Prediction of vehicle-emitted air pollutants and evaluation of the diverse factors that contribute to them are of the utmost importance. This study employed advanced tree-based machine learning models to predict vehicle-induced air pollutant levels, with a particular focus on fine particulate matter (PM2.5). In addition to a benchmark statistical model, the models employed were Gradient Boosting (GB), Light Gradient Boosting Machine (LGBM), Extreme Gradient Boosting (XGBoost), Extra Tree (ET), and Random Forest (RF). Regarding the evaluation of PM2.5 predictions, the ET model outperformed the others, as shown by MAE of 1.69, MSE of 5.91, RMSE of 2.43, and R2 of 0.71. Afterward, the optimal ET models were interpreted using SHAP analysis to overcome the ET model's lack of explainability. Based on the SHAP analysis, it was determined that temperature, humidity, and wind speed emerged as the primary determinants in forecasting PM2.5 levels.
first_indexed 2024-03-08T04:04:20Z
format Article
id doaj.art-13219086a58e4bed978fb09260f6a783
institution Directory Open Access Journal
issn 2241-4487
1792-8036
language English
last_indexed 2024-03-08T04:04:20Z
publishDate 2024-02-01
publisher D. G. Pylarinos
record_format Article
series Engineering, Technology & Applied Science Research
spelling doaj.art-13219086a58e4bed978fb09260f6a7832024-02-09T06:05:56ZengD. G. PylarinosEngineering, Technology & Applied Science Research2241-44871792-80362024-02-0114110.48084/etasr.6678Prediction of Vehicle-induced Air Pollution based on Advanced Machine Learning ModelsCaroline Matara0Simpson Osano1Amir Okeyo Yusuf2Elisha Ochungo Aketch3Department of Civil & Construction Engineering, University of Nairobi, Kenya | School of Civil and Resource Engineering, Technical University of Kenya, KenyaDepartment of Civil & Construction Engineering, University of Nairobi, KenyaDepartment of Chemistry, University of Nairobi, KenyaDepartment of Civil, Faculty of Engineering and Technology (FoET), Multimedia University, Kenya Vehicle-induced air pollution is an important issue in the 21st century, posing detrimental effects on human health. Prediction of vehicle-emitted air pollutants and evaluation of the diverse factors that contribute to them are of the utmost importance. This study employed advanced tree-based machine learning models to predict vehicle-induced air pollutant levels, with a particular focus on fine particulate matter (PM2.5). In addition to a benchmark statistical model, the models employed were Gradient Boosting (GB), Light Gradient Boosting Machine (LGBM), Extreme Gradient Boosting (XGBoost), Extra Tree (ET), and Random Forest (RF). Regarding the evaluation of PM2.5 predictions, the ET model outperformed the others, as shown by MAE of 1.69, MSE of 5.91, RMSE of 2.43, and R2 of 0.71. Afterward, the optimal ET models were interpreted using SHAP analysis to overcome the ET model's lack of explainability. Based on the SHAP analysis, it was determined that temperature, humidity, and wind speed emerged as the primary determinants in forecasting PM2.5 levels. https://etasr.com/index.php/ETASR/article/view/6678air pollutantsmachine learningSHAP analysis
spellingShingle Caroline Matara
Simpson Osano
Amir Okeyo Yusuf
Elisha Ochungo Aketch
Prediction of Vehicle-induced Air Pollution based on Advanced Machine Learning Models
Engineering, Technology & Applied Science Research
air pollutants
machine learning
SHAP analysis
title Prediction of Vehicle-induced Air Pollution based on Advanced Machine Learning Models
title_full Prediction of Vehicle-induced Air Pollution based on Advanced Machine Learning Models
title_fullStr Prediction of Vehicle-induced Air Pollution based on Advanced Machine Learning Models
title_full_unstemmed Prediction of Vehicle-induced Air Pollution based on Advanced Machine Learning Models
title_short Prediction of Vehicle-induced Air Pollution based on Advanced Machine Learning Models
title_sort prediction of vehicle induced air pollution based on advanced machine learning models
topic air pollutants
machine learning
SHAP analysis
url https://etasr.com/index.php/ETASR/article/view/6678
work_keys_str_mv AT carolinematara predictionofvehicleinducedairpollutionbasedonadvancedmachinelearningmodels
AT simpsonosano predictionofvehicleinducedairpollutionbasedonadvancedmachinelearningmodels
AT amirokeyoyusuf predictionofvehicleinducedairpollutionbasedonadvancedmachinelearningmodels
AT elishaochungoaketch predictionofvehicleinducedairpollutionbasedonadvancedmachinelearningmodels