ScholarMate
English简体中文繁體中文
客服热线:400-1616-289
登录注册
期刊论文

PM2.5 concentrations forecasting in Beijing through deep learning with different inputs, model structures and forecast time

Yang, Jie; Yan, Rui; Nong, Mingyue; Liao, Jiaqiang; Li, Feipeng; Sun, Wei*中山大学; 中国科学院
Atmospheric Pollution Research2021-9DOI: 10.1016/j.apr.2021.101168
49被引3阅读
引用收藏
分享

摘要

Timely and accurate air quality forecasting is of great significance for prevention and mitigation of air pollution. However, most of the previous forecasting models only considered either temporal or spatial prediction. The effects of different inputs, model structures and leading hours on the model performance were still less investigated. In this study, three kinds of deep learning neural networks (the long short-term memory (LSTM), the convolutional neural networks (CNN), and CNN-LSTM) were developed for 1- to 24-h forecasting of spatiotemporal PM2.5 concentrations. The back propagation neural network (BPNN) was employed as the control model. Three types of input data (previous PM2.5 concentrations plus meteorological data, air quality data and the six most correlated variables, respectively) at multiple stations in Beijing from 2015 to 2016 were employed for model development. The results showed that PM2.5 concentrations in the past hours, hybrid air quality indexes or other pollutant concentrations, and wind speed can be used as good candidate predictors. For the 1-h forecasting, the LSTM and the CNN-LSTM with the most correlated variables were the best models with top 2 performance. For the 2- to 24-h forecasting, the LSTM was the optimal model for forecasting over 12 h while the CNN-LSTM was generally better for forecasting within 12 h. This study demonstrated that deep learning outperformed shallow learning models in hourly PM2.5 forecasting and suggested that optimizing the input and structure of the model helped to improve the performance of multiple-hour PM2.5 forecasting.

学科与关键词

关键词
Air quality predictionPM25CNNLSTMCNN-LSTM
相关
加载中…
  • Deep learning-based PM2.5 prediction considering the spatiotemporal correlations: A case study of Beijing, China
    Pak, Unjin*; Ma, Jun; Ryu, Unsok; Ryom, Kwangchol; Juhyok, U.; Pak, Kyongsok; Pak, ChanilScience of the Total Environment, 2020, 699: 133561.被引 225
  • Forecasting hourly PM2.5 concentration with an optimized LSTM model
    Tran, Huynh Duy; Huang, Hsiang-Yu; Yu, Jhih-Yuan; Wang, Sheng-Hsiang*Atmospheric Environment, 2023, 315: 120161.被引 7
  • A Hybrid CNN-LSTM Model for Forecasting Particulate Matter (PM2.5)
    Li, Taoying*; Hua, Miao; Wu, XuIEEE Access, 2020, 8: 26933-26940.被引 207
查看全部 →

发表信息

论文状态
公开发表
期刊
Atmospheric Pollution Research
发表日期
2021-09
卷期
第 12 卷, 第 9 期
页码
101168
DOI
10.1016/j.apr.2021.101168
语言
ENGLISH
期刊收录
NSL
期刊等级
3区
成果收录
SCIE
资助标注
Top-Notch Young Talents of Pearl River Talents Plan [2019QN01G106]; Innovation Group Project of Southern Marine Science and Engineering Guangdong Labo-ratory (Zhuhai) [311021018]; Hundred Talents Program of Sun Yat-Sen University [37000-18841201]; National Undergraduate Training Programs for Innovation and Entrepreneurship [201901211]

作者

  • Y

    Yang, Jie (第一作者)

    sun yat sen univ · chinese acad sci · inst geog sci & nat resources res

  • Y

    Yan, Rui

    sun yat sen univ · chinese acad sci · inst geog sci & nat resources res

查看全部 6 位作者收起作者
  • N

    Nong, Mingyue

    sun yat sen univ

  • L

    Liao, Jiaqiang

    sun yat sen univ · chinese acad sci · inst geog sci & nat resources res

  • L

    Li, Feipeng

    sun yat sen univ

  • S

    Sun, Wei (通讯)

    sun yat sen univ

登录解锁更多功能

  • 收藏这篇,随时在“我的 · 收藏”找回
  • 认领你的成果,生成推广素材
  • 关注作者获取最新成果
  • 加入项目组、协同写作
注册 / 登录

产品服务

  • 科研之友
  • 创新城
  • 科创云

服务支持

  • 帮助中心
  • 隐私政策
  • 服务条款

联系方式

在线客服:【】
客服热线:400-1616-289
电子邮箱:support@scholarmate.com

关注或下载科研之友

微信二维码
微信公众号
客户端下载二维码
下载客户端
科研成果科研人员科研机构科研动态爱瑞思软件

©2026 深圳市科研之友网络服务有限公司

公安备案图标粤公网安备 44030502000213
粤ICP备 16046710 号粤B2-20110417