Predicting Ozone Pollution in Urban Areas Using Machine Learning and Quantile Regression Models

被引:1
|
作者
Cueva, Fernando [1 ,2 ]
Saquicela, Victor [1 ]
Sarmiento, Juan [1 ]
Cabrera, Fanny [1 ]
机构
[1] Univ Cuenca, Av 12 Abril S-N, Cuenca, Azuay, Ecuador
[2] Rochester Inst Technol, One Lomb Mem Dr, Rochester, NY 14623 USA
关键词
Ozone; Pollutants; Ensemble models; Neural networks; Quantile regression; AIR-POLLUTION; CHINA;
D O I
10.1007/978-3-030-89941-7_20
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Ozone is the most harmful secondary pollutant in terms of negative effects on climate change and human health. Predicting ozone emission levels has therefore gained importance within the field of environmental management. This study, performed in the Andean city of Cuenca, Ecuador, compares the performance of two methodologies currently used for this task and based on machine learning and quantile regression techniques. These techniques were applied using cross-sectional data to predict the ozone concentration per city block during the year 2018. Our results reveal that ozone concentration is significantly influenced by nitrogen dioxide, sedimentary particles, sulfur dioxide, traffic, and spatial features. We use the mean square error, the coefficient of determination, and the quantile loss as evaluation metrics for the performance of the ozone prediction models, employing a cross-validation scheme with a fold. Our work shows that the random forest technique outperforms gradient boosting prediction, neural network, and quantile regression methods.
引用
收藏
页码:281 / 296
页数:16
相关论文
共 50 条
  • [1] Predicting uncertainty of machine learning models for modelling nitrate pollution of groundwater using quantile regression and UNEEC methods
    Rahmati, Omid
    Choubin, Bahram
    Fathabadi, Abolhasan
    Coulon, Frederic
    Soltani, Elinaz
    Shahabi, Himan
    Mollaefar, Eisa
    Tiefenbacher, John
    Cipullo, Sabrina
    Bin Ahmad, Baharin
    Bui, Dieu Tien
    [J]. SCIENCE OF THE TOTAL ENVIRONMENT, 2019, 688 : 855 - 866
  • [2] Predicting pollution incidents through semiparametric quantile regression models
    Roca-Pardinas, J.
    Ordonez, C.
    [J]. STOCHASTIC ENVIRONMENTAL RESEARCH AND RISK ASSESSMENT, 2019, 33 (03) : 673 - 685
  • [3] Predicting pollution incidents through semiparametric quantile regression models
    J. Roca-Pardiñas
    C. Ordóñez
    [J]. Stochastic Environmental Research and Risk Assessment, 2019, 33 : 673 - 685
  • [4] Forecasting Ozone Pollution using Recurrent Neural Nets and Multiple Quantile Regression
    Flores-Vergara, Daniel
    Nanculef, Ricardo
    Valle, Carlos
    Osses, Mauricio
    Jacques, Aldonza
    Dominguez, Maria
    [J]. 2019 IEEE CHILEAN CONFERENCE ON ELECTRICAL, ELECTRONICS ENGINEERING, INFORMATION AND COMMUNICATION TECHNOLOGIES (CHILECON), 2019,
  • [5] Predicting trace gas concentrations using quantile regression models
    Mercedes Conde-Amboage
    Wenceslao González-Manteiga
    César Sánchez-Sellero
    [J]. Stochastic Environmental Research and Risk Assessment, 2017, 31 : 1359 - 1370
  • [6] Predicting trace gas concentrations using quantile regression models
    Conde-Amboage, Mercedes
    Gonzalez-Manteiga, Wenceslao
    Sanchez-Sellero, Cesar
    [J]. STOCHASTIC ENVIRONMENTAL RESEARCH AND RISK ASSESSMENT, 2017, 31 (06) : 1359 - 1370
  • [7] Machine learning approaches for predicting microplastic pollution in peatland areas
    Tran, Huu-Tuan
    Hadi, Mohammed
    Nguyen, Thi Thu Hang
    Hoang, Hong Giang
    Nguyen, Minh-Ky
    Nguyen, Khoi Nghia
    Vo, Dai-Viet N.
    [J]. MARINE POLLUTION BULLETIN, 2023, 194
  • [8] Machine learning for predicting shallow groundwater levels in urban areas
    Labianca, Ane
    Koch, Julian
    Jjensen, Karsten Hogh
    Sonnenborg, Torben O.
    Kidmose, Jacob
    [J]. JOURNAL OF HYDROLOGY, 2024, 632
  • [10] Machine learning analysis of socioeconomic drivers in urban ozone pollution in Chinese cities
    Xiang, Kun
    Shi, Danxi
    Xiang, Xiangyun
    [J]. ENVIRONMENTAL MONITORING AND ASSESSMENT, 2024, 196 (03)