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

Attention-based parallel networks (APNet) for PM2.5 spatiotemporal prediction

Zhu, Jiaqi; Deng, Fang*; Zhao, Jiachen; Zheng, Hao北京理工大学
Science of the Total Environment2021-5-15DOI: 10.1016/j.scitotenv.2021.145082
61被引12阅读
引用收藏
分享

摘要

Urban particulate matter forecast is an important part of air pollution early warning and control management, especially the forecast of fine particulate matter (PM2.5). However, the existing PM2.5 concentration prediction methods cannot effectively capture the complex nonlinearity of PM2.5 concentration, and most of them cannot accurately simulate the temporal and spatial dependence of PM2.5 concentration at the same time. In this paper, we propose an attention-based parallel network (APNet), which can extract short-term and long-term temporal features simultaneously based on the attention-based CNN-LSTM multilayer structure to predict PM2.5 concentration in the next 72 h. Firstly, the Maximum Information Coefficient (MIC) is designed for spatiotemporal correlation analysis, fully considering the linearity, non-linearity and non-functionality between the data of each monitoring station. The potential inherent features of the input data are effectively extracted through the convolutional neural network (CNN). Then, an optimized long short-term memroy (LSTM) network captures the short-term mutations of the time series. An attention mechanism is further designed for the proposed model, which automatically assigns different weights to different feature states at different time stages to distinguish their importance, and can achieve precise temporal and spatial interpretability. In order to further explore the long-term time features, we propose a Bi-isnvi parallel module to extract the periodic characteristics of PM2.5 concentration from both previous and posterior directions. Experimental results based on a real-world dataset indicates that the proposed model outperforms other existing state-of-the-art methods. Moreover, evaluations of recall (0.790), precision (0.848) (threshold: 151 mu g/m(3)) for 72 h prediction also verify the feasibility degrees four proposed model. The methodology can be used for predicting other multivariate time series data in the future.

学科与关键词

关键词
Spatiotemporal correlationPM2.5 predictionAttention mechanismDeep learningCNNTransformation-gate 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
  • Densely connected convolutional networks with attention long short-term memory for estimating PM2.5 values from images
    Zhang, Bo; Geng, Ziyao; Zhang, Hanwen; Pan, Jianguo*JOURNAL OF CLEANER PRODUCTION, 2022, 333: 130101.被引 8
  • A hybrid CNN-LSTM model for predicting PM2.5 in Beijing based on spatiotemporal correlation
    Ding, Chen; Wang, Guizhi*; Zhang, Xinyue; Liu, Qi; Liu, XiaodongENVIRONMENTAL AND ECOLOGICAL STATISTICS, 2021, 28(3): 503-522.被引 33
查看全部 →

发表信息

论文状态
公开发表
期刊
Science of the Total Environment
发表日期
2021-05-15
卷期
第 769 卷
页码
145082
DOI
10.1016/j.scitotenv.2021.145082
语言
MULTI-LANGUAGE
期刊收录
NSL
期刊等级
1区
成果收录
SCIE
资助标注
National Science Fund for Distinguished Young Scholars of China [62025301]; Key Program of National Natural Science Foundation of China [61933002]

作者

  • Z

    Zhu, Jiaqi (第一作者)

    beijing inst technol

  • D

    Deng, Fang (通讯)

    beijing inst technol

查看全部 4 位作者收起作者
  • Z

    Zhao, Jiachen

    beijing inst technol

  • Z

    Zheng, Hao

    beijing inst technol

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