Modelling Particulate Matter (PM10) Variations During Transboundary Haze Events Using a Modified Quantile Regression Approach

IF 4.1 Q2 CHEMISTRY, ANALYTICAL
Nur Alis Addiena A. Rahim, Norazian Mohamed Noor, Izzati Amani Mohd Jafri, Ahmad Zia Ul-Saufie, Mohamad Anuar Kamaruddin, Mohd Remy Rozainy Mohd Arif Zainol, Andrei Victor Sandu, Petrica Vizureanu, Gyorgy Deak
{"title":"Modelling Particulate Matter (PM10) Variations During Transboundary Haze Events Using a Modified Quantile Regression Approach","authors":"Nur Alis Addiena A. Rahim,&nbsp;Norazian Mohamed Noor,&nbsp;Izzati Amani Mohd Jafri,&nbsp;Ahmad Zia Ul-Saufie,&nbsp;Mohamad Anuar Kamaruddin,&nbsp;Mohd Remy Rozainy Mohd Arif Zainol,&nbsp;Andrei Victor Sandu,&nbsp;Petrica Vizureanu,&nbsp;Gyorgy Deak","doi":"10.1002/ansa.70027","DOIUrl":null,"url":null,"abstract":"<p>Severe haze episodes in Southeast Asia, largely attributed to transboundary pollution from neighbouring countries, have led to substantial environmental degradation and adverse health effects. This study presents the development of a novel air quality forecasting model specifically developed to predict particulate matter with a diameter of less than 10 µm (PM<sub>10</sub>) concentrations 1 to 3 days in advance during transboundary haze events in Malaysia. The innovation lies in the integration of quantile regression (QR) with advanced feature selection techniques—namely, Relief-based ranking, correlation-based selection and principal component analysis (PCA)—to form modified predictive models. These hybrid models, referred to as QR-Relief, QR-correlation and QR-PCA, demonstrated superior performance over traditional QR and multiple linear regression models across four urban locations: Klang, Melaka, Pasir Gudang and Petaling Jaya. Model accuracy was evaluated using selected performance metrics, including mean absolute error, normalized absolute error and root mean square error. The results indicate that reducing the dimensionality of input variables through analytical feature selection significantly improves predictive reliability. Furthermore, model validation using an independent dataset from 2019 confirmed their real-world applicability. This methodological advancement provides a robust analytical framework for developing early warning systems during haze events, offering valuable decision-support tools for environmental and public health management.</p>","PeriodicalId":93411,"journal":{"name":"Analytical science advances","volume":"6 2","pages":""},"PeriodicalIF":4.1000,"publicationDate":"2025-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/ansa.70027","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Analytical science advances","FirstCategoryId":"1085","ListUrlMain":"https://onlinelibrary.wiley.com/doi/10.1002/ansa.70027","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"CHEMISTRY, ANALYTICAL","Score":null,"Total":0}
引用次数: 0

Abstract

Severe haze episodes in Southeast Asia, largely attributed to transboundary pollution from neighbouring countries, have led to substantial environmental degradation and adverse health effects. This study presents the development of a novel air quality forecasting model specifically developed to predict particulate matter with a diameter of less than 10 µm (PM10) concentrations 1 to 3 days in advance during transboundary haze events in Malaysia. The innovation lies in the integration of quantile regression (QR) with advanced feature selection techniques—namely, Relief-based ranking, correlation-based selection and principal component analysis (PCA)—to form modified predictive models. These hybrid models, referred to as QR-Relief, QR-correlation and QR-PCA, demonstrated superior performance over traditional QR and multiple linear regression models across four urban locations: Klang, Melaka, Pasir Gudang and Petaling Jaya. Model accuracy was evaluated using selected performance metrics, including mean absolute error, normalized absolute error and root mean square error. The results indicate that reducing the dimensionality of input variables through analytical feature selection significantly improves predictive reliability. Furthermore, model validation using an independent dataset from 2019 confirmed their real-world applicability. This methodological advancement provides a robust analytical framework for developing early warning systems during haze events, offering valuable decision-support tools for environmental and public health management.

Abstract Image

利用改进的分位数回归方法模拟跨界雾霾事件中颗粒物(PM10)的变化
东南亚严重的雾霾事件主要归因于邻国的越界污染,导致严重的环境退化和不利的健康影响。本研究提出了一种新的空气质量预测模型,专门用于在马来西亚跨境雾霾事件期间提前1至3天预测直径小于10微米的颗粒物(PM10)浓度。其创新之处在于将分位数回归(QR)与先进的特征选择技术(即基于地形的排序、基于相关性的选择和主成分分析(PCA))相结合,形成改进的预测模型。这些混合模型,被称为QR- relief, QR-correlation和QR- pca,在巴生,马六甲,巴西尔古当和八打灵查亚四个城市地区显示出优于传统QR和多元线性回归模型的性能。使用选定的性能指标评估模型精度,包括平均绝对误差、归一化绝对误差和均方根误差。结果表明,通过分析性特征选择降低输入变量的维数可以显著提高预测的可靠性。此外,使用2019年独立数据集的模型验证证实了它们在现实世界中的适用性。这一方法上的进步为雾霾事件早期预警系统的发展提供了一个强有力的分析框架,为环境和公共卫生管理提供了有价值的决策支持工具。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
CiteScore
4.60
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信