TPE-LCE-SHAP: A Hybrid Framework for Assessing Vehicle-Related PM2.5 Concentrations

被引：0
|
作者：
Almujibah, Hamad [1 ]
Almaliki, Abdulrazak H. [1 ]
Mongina Matara, Caroline [2 ]
Abdallah Mohammed Elhassan, Adil [1 ]
Alla Adam Mohamed, Khalaf [3 ]
Bakri, Mudthir [4 ]
Khattak, Afaq [5 ]
机构：
[1] Taif University, College of Engineering, Department of Civil Engineering, Taif,21944, Saudi Arabia
[2] Technical University of Kenya, Department of Civil and Construction Engineering, Nairobi,00200, Kenya
[3] Bisha University, College of Engineering, Department of Civil Engineering, Bisha,61361, Saudi Arabia
[4] Qassim University, College of Engineering, Department of Civil Engineering, Buraidah,52571, Saudi Arabia
[5] Tongji University, College of Transportation Engineering, Jiading, Shanghai,201804, China
来源：
IEEE Access | 2024年 / 12卷
关键词：
This study proposes a novel hybrid approach for estimating and analyzing vehicle-related PM2.5 concentrations. The framework integrates the Local Cascade Ensemble (LCE) model; optimized using the Tree-structured Parzen Estimator (TPE) strategy; with SHapley Additive exPlanations (SHAP) to enhance interpretability. It utilizes datasets comprising air quality; meteorological; and traffic data collected from strategically placed sensors along the Nairobi Expressway. Key parameters include hourly traffic volume; average vehicle speed; humidity; wind speed; and temperature. The TPE-tuned LCE model outperformed benchmark algorithms including Random Forest (RF); Extreme Gradient Boosting (XGBoost); Light Gradient Boosting Machine (LightGBM); Adaptive Boosting (AdaBoost); and Multiple Linear Regression (MLR) achieved the lowest Mean Absolute Error (MAE) of 1.94; Mean Squared Error (MSE) of 21.50; Root Mean Squared Error (RMSE) of 4.64; Residual Standard Ratio (RSR) of 0.38; and the highest Coefficient of Determination (R2) of 0.87. SHAP analysis of TPE-tuned LCE model identified location; and wind speed as the most influential predictors of PM2.5 levels. This hybrid framework delivers robust predictive accuracy and actionable insights; making it a valuable tool for effective environmental management and policy making. © 2013 IEEE;
D O I：
10.1109/ACCESS.2024.3505116
中图分类号：
学科分类号：
摘要：
引用
收藏
页码：179219 / 179234
相关论文
共 50 条
  • [1] Measuring and Modelling the Concentration of Vehicle-Related PM2.5 and PM10 Emissions Based on Neural Networks
    Shepelev, Vladimir
    Glushkov, Aleksandr
    Slobodin, Ivan
    Cherkassov, Yuri
    MATHEMATICS, 2023, 11 (05)
  • [2] Impact of Diesel Vehicle Emissions on PM2.5 Concentrations in Seoul Metropolitan Area during the Seasonal PM2.5 Management
    Kim, Yoonha
    Kim, Eunhye
    Kang, Yoon-Hee
    You, Seunghee
    Bae, Minah
    Son, Kyuwon
    Kim, Soontae
    JOURNAL OF KOREAN SOCIETY FOR ATMOSPHERIC ENVIRONMENT, 2021, 37 (01) : 169 - 190
  • [3] Vehicle emissions and PM2.5 mass concentrations in six Brazilian cities
    Andrade, Maria de Fatima
    de Miranda, Regina Maura
    Fornaro, Adalgiza
    Kerr, Americo
    Oyama, Beatriz
    de Andre, Paulo Afonso
    Saldiva, Paulo
    AIR QUALITY ATMOSPHERE AND HEALTH, 2012, 5 (01): : 79 - 88
  • [4] Vehicle emissions and PM2.5 mass concentrations in six Brazilian cities
    Maria de Fatima Andrade
    Regina Maura de Miranda
    Adalgiza Fornaro
    Americo Kerr
    Beatriz Oyama
    Paulo Afonso de Andre
    Paulo Saldiva
    Air Quality, Atmosphere & Health, 2012, 5 : 79 - 88
  • [5] A hybrid framework for forecasting PM2.5 concentrations using multi-step deterministic and probabilistic strategy
    Hui Liu
    Zhu Duan
    Chao Chen
    Air Quality, Atmosphere & Health, 2019, 12 : 785 - 795
  • [6] Deep Ensemble Machine Learning Framework for the Estimation of PM2.5 Concentrations
    Yu, Wenhua
    Li, Shanshan
    Ye, Tingting
    Xu, Rongbin
    Song, Jiangning
    Guo, Yuming
    ENVIRONMENTAL HEALTH PERSPECTIVES, 2022, 130 (03)
  • [7] A hybrid framework for forecasting PM2.5 concentrations using multi-step deterministic and probabilistic strategy
    Liu, Hui
    Duan, Zhu
    Chen, Chao
    AIR QUALITY ATMOSPHERE AND HEALTH, 2019, 12 (07): : 785 - 795
  • [8] Assessing Spatial Heterogeneity of Factor Interactions on PM2.5 Concentrations in Chinese Cities
    Jin, Yuhao
    Zhang, Han
    Shi, Hong
    Wang, Huilin
    Wei, Zhenfeng
    Han, Yuxing
    Cong, Peitong
    REMOTE SENSING, 2021, 13 (24)
  • [9] Comment on "Deep Ensemble Machine Learning Framework for the Estimation of PM2.5 Concentrations"
    Stafoggia, Massimo
    Cattani, Giorgio
    Ancona, Carla
    Gasparrini, Antonio
    Ranzi, Andrea
    ENVIRONMENTAL HEALTH PERSPECTIVES, 2022, 130 (06)
  • [10] Assessing neighborhood variations in ozone and PM2.5 concentrations using decision tree method
    Gao, Ya
    Wang, Zhanyong
    Li, Chao-yang
    Zheng, Tie
    Peng, Zhong-Ren
    BUILDING AND ENVIRONMENT, 2021, 188
12345