Explainable AI analysis for smog rating prediction

Abstract Smog poses a direct threat to human health and the environment. Addressing this issue requires understanding how smog is formed. While major contributors include industries, fossil fuels, crop burning, and ammonia from fertilizers, vehicles play a significant role. Individually, a vehicle’s...

Full description

Saved in:
Bibliographic Details
Main Authors: Yazeed Yasin Ghadi, Sheikh Muhammad Saqib, Tehseen Mazhar, Ahmad Almogren, Wajahat Waheed, Ayman Altameem, Habib Hamam
Format: Article
Language:English
Published: Nature Portfolio 2025-03-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-92788-x
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850029814268821504
author Yazeed Yasin Ghadi
Sheikh Muhammad Saqib
Tehseen Mazhar
Ahmad Almogren
Wajahat Waheed
Ayman Altameem
Habib Hamam
author_facet Yazeed Yasin Ghadi
Sheikh Muhammad Saqib
Tehseen Mazhar
Ahmad Almogren
Wajahat Waheed
Ayman Altameem
Habib Hamam
author_sort Yazeed Yasin Ghadi
collection DOAJ
description Abstract Smog poses a direct threat to human health and the environment. Addressing this issue requires understanding how smog is formed. While major contributors include industries, fossil fuels, crop burning, and ammonia from fertilizers, vehicles play a significant role. Individually, a vehicle’s contribution to smog may be small, but collectively, the vast number of vehicles has a substantial impact. Manually assessing the contribution of each vehicle to smog is impractical. However, advancements in machine learning make it possible to quantify this contribution. By creating a dataset with features such as vehicle model, year, fuel consumption (city), and fuel type, a predictive model can classify vehicles based on their smog impact, rating them on a scale from 1 (poor) to 8 (excellent). This study proposes a novel approach using Random Forest and Explainable Boosting Classifier models, along with SMOTE (Synthetic Minority Oversampling Technique), to predict the smog contribution of individual vehicles. The results outperform previous studies, with the proposed model achieving an accuracy of 86%. Key performance metrics include a Mean Squared Error of 0.2269, R-Squared (R2) of 0.9624, Mean Absolute Error of 0.2104, Explained Variance Score of 0.9625, and a Max Error of 4.3500. These results incorporate explainable AI techniques, using both agnostic and specific models, to provide clear and actionable insights. This work represents a significant step forward, as the dataset was last updated only five months ago, underscoring the timeliness and relevance of the research.
format Article
id doaj-art-e6419542a48b4cbb85b8a862c3617f4e
institution DOAJ
issn 2045-2322
language English
publishDate 2025-03-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-e6419542a48b4cbb85b8a862c3617f4e2025-08-20T02:59:24ZengNature PortfolioScientific Reports2045-23222025-03-0115112310.1038/s41598-025-92788-xExplainable AI analysis for smog rating predictionYazeed Yasin Ghadi0Sheikh Muhammad Saqib1Tehseen Mazhar2Ahmad Almogren3Wajahat Waheed4Ayman Altameem5Habib Hamam6Department of Computer Science and Software Engineering, Al Ain UniversityDepartment of Computing and Information Technology, Gomal UniversitySchool of Computer Science, National College of Business Administration and EconomicsDepartment of Computer Science, College of Computer and Information Sciences, King Saud UniversityDepartment of Electrical and Computer Engineering, Purdue UniversityDepartment of Natural and Engineering Sciences, College of Applied Studies and Community Services, King Saud UniversityFaculty of Engineering, Uni de MonctonAbstract Smog poses a direct threat to human health and the environment. Addressing this issue requires understanding how smog is formed. While major contributors include industries, fossil fuels, crop burning, and ammonia from fertilizers, vehicles play a significant role. Individually, a vehicle’s contribution to smog may be small, but collectively, the vast number of vehicles has a substantial impact. Manually assessing the contribution of each vehicle to smog is impractical. However, advancements in machine learning make it possible to quantify this contribution. By creating a dataset with features such as vehicle model, year, fuel consumption (city), and fuel type, a predictive model can classify vehicles based on their smog impact, rating them on a scale from 1 (poor) to 8 (excellent). This study proposes a novel approach using Random Forest and Explainable Boosting Classifier models, along with SMOTE (Synthetic Minority Oversampling Technique), to predict the smog contribution of individual vehicles. The results outperform previous studies, with the proposed model achieving an accuracy of 86%. Key performance metrics include a Mean Squared Error of 0.2269, R-Squared (R2) of 0.9624, Mean Absolute Error of 0.2104, Explained Variance Score of 0.9625, and a Max Error of 4.3500. These results incorporate explainable AI techniques, using both agnostic and specific models, to provide clear and actionable insights. This work represents a significant step forward, as the dataset was last updated only five months ago, underscoring the timeliness and relevance of the research.https://doi.org/10.1038/s41598-025-92788-xMachine learningRandom forestExplainable boosting classifierSMOTEExplainable-AI
spellingShingle Yazeed Yasin Ghadi
Sheikh Muhammad Saqib
Tehseen Mazhar
Ahmad Almogren
Wajahat Waheed
Ayman Altameem
Habib Hamam
Explainable AI analysis for smog rating prediction
Scientific Reports
Machine learning
Random forest
Explainable boosting classifier
SMOTE
Explainable-AI
title Explainable AI analysis for smog rating prediction
title_full Explainable AI analysis for smog rating prediction
title_fullStr Explainable AI analysis for smog rating prediction
title_full_unstemmed Explainable AI analysis for smog rating prediction
title_short Explainable AI analysis for smog rating prediction
title_sort explainable ai analysis for smog rating prediction
topic Machine learning
Random forest
Explainable boosting classifier
SMOTE
Explainable-AI
url https://doi.org/10.1038/s41598-025-92788-x
work_keys_str_mv AT yazeedyasinghadi explainableaianalysisforsmogratingprediction
AT sheikhmuhammadsaqib explainableaianalysisforsmogratingprediction
AT tehseenmazhar explainableaianalysisforsmogratingprediction
AT ahmadalmogren explainableaianalysisforsmogratingprediction
AT wajahatwaheed explainableaianalysisforsmogratingprediction
AT aymanaltameem explainableaianalysisforsmogratingprediction
AT habibhamam explainableaianalysisforsmogratingprediction