A novel multi-factor & multi-scale method for PM2.5 concentration forecasting

被引:43
|
作者
Yuan, Wenyan [1 ]
Wang, Kaiqi [1 ]
Bo, Xin [2 ]
Tang, Ling [3 ,4 ]
Wu, Junjie [4 ]
机构
[1] Beijing Univ Chem Technol, Sch Sci, Beijing 100029, Peoples R China
[2] Minist Environm Protect Peoples Republ China, Appraisal Ctr Environm & Engn, Beijing 100012, Peoples R China
[3] Beijing Univ Chem Technol, Sch Econ & Management, 15 Beisanhuan East Rd, Beijing 100029, Peoples R China
[4] Beihang Univ, Sch Econ & Management, Beijing 100191, Peoples R China
关键词
Air quality forecast; Multi-scale analysis; Meteorological factors; Multivariate empirical mode decomposition; Big data; EMPIRICAL MODE DECOMPOSITION; ENSEMBLE LEARNING-PARADIGM; EARLY-WARNING SYSTEM; FUZZY SYNTHETIC EVALUATION; SHORT-TERM-MEMORY; NEURAL-NETWORK; HYBRID MODEL; AIR; PREDICTION; ALGORITHM;
D O I
10.1016/j.envpol.2019.113187
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
In the era of big data, a variety of factors (particularly meteorological factors) have been applied to PM2.5 concentration prediction, revealing a clear discrepancy in timescale. To capture the complicated multi scale relationship with PM2.5-related factors, a novel multi-factor & multi-scale method is proposed for PM2.5 forecasting. Three major steps are taken: (1) multi-factor analysis, to select predictive factors via statistical tests; (2) multi-scale analysis, to extract scale-aligned components via multivariate empirical mode decomposition; and (3) PM2.5 prediction, including individual prediction at each timescale and ensemble prediction across different timescales. The empirical study focuses on the PM2.5 of Cangzhou, which is one of the most air-polluted cities in China, and indicates that the proposed multi factor & multi-scale learning paradigms statistically outperform their corresponding original techniques (without multi-factor and multi-scale analysis), semi-improved variants (with either multi-factor or multi-scale analysis), and similar counterparts (with other multi-scale analyses) in terms of prediction accuracy. (C) 2019 Elsevier Ltd. All rights reserved.
引用
收藏
页数:11
相关论文
共 50 条
  • [1] A Multi-Scale Method for PM2.5 Forecasting with Multi-Source Big Data
    YUAN Wenyan
    DU Hongchuan
    LI Jieyi
    LI Ling
    JournalofSystemsScience&Complexity, 2023, 36 (02) : 771 - 797
  • [2] A Multi-Scale Method for PM2.5 Forecasting with Multi-Source Big Data
    Wenyan Yuan
    Hongchuan Du
    Jieyi Li
    Ling Li
    Journal of Systems Science and Complexity, 2023, 36 : 771 - 797
  • [3] A Multi-Scale Method for PM2.5 Forecasting with Multi-Source Big Data
    Yuan, Wenyan
    Du, Hongchuan
    Li, Jieyi
    Li, Ling
    JOURNAL OF SYSTEMS SCIENCE & COMPLEXITY, 2023, 36 (02) : 771 - 797
  • [4] Toward Prediction of Roadside PM2.5 Concentration: A Multi-Factor Prediction Method
    Wei, Zhonghua
    Wang, Shihao
    Ding, Dongtong
    Peng, Jingxuan
    CICTP 2023: INNOVATION-EMPOWERED TECHNOLOGY FOR SUSTAINABLE, INTELLIGENT, DECARBONIZED, AND CONNECTED TRANSPORTATION, 2023, : 225 - 234
  • [5] PM2.5 concentration forecasting through a novel multi-scale ensemble learning approach considering intercity synergy
    Yu, Yang
    Li, Hongtao
    Sun, Shaolong
    Li, Yongwu
    SUSTAINABLE CITIES AND SOCIETY, 2022, 85
  • [6] Multi-factor PM2.5 concentration optimization prediction model based on decomposition and integration
    Yang, Hong
    Wang, Wenqian
    Li, Guohui
    URBAN CLIMATE, 2024, 55
  • [7] A multi-scale method for forecasting oil price with multi-factor search engine data
    Tang, Ling
    Zhang, Chengyuan
    Li, Ling
    Wang, Shouyang
    APPLIED ENERGY, 2020, 257
  • [8] Spatiotemporal Distribution Characteristics and Multi-Factor Analysis of Near-Surface PM2.5 Concentration in Local-Scale Urban Areas
    Liu, Lin
    He, Huiyu
    Zhu, Yushuang
    Liu, Jing
    Wu, Jiani
    Tan, Zhuang
    Xie, Hui
    ATMOSPHERE, 2023, 14 (10)
  • [9] Extraction of multi-scale features enhances the deep learning-based daily PM2.5 forecasting in cities
    Dong, Liang
    Hua, Pei
    Gui, Dongwei
    Zhang, Jin
    CHEMOSPHERE, 2022, 308
  • [10] Extraction of multi-scale features enhances the deep learning-based daily PM2.5 forecasting in cities
    Dong, Liang
    Hua, Pei
    Gui, Dongwei
    Zhang, Jin
    Chemosphere, 2022, 308