Forecasting Fine-Grained Air Quality for Locations without Monitoring Stations Based on a Hybrid Predictor with Spatial-Temporal Attention Based Network

被引:6
|
作者
Hsieh, Hsun-Ping [1 ,2 ]
Wu, Su [1 ]
Ko, Ching-Chung [3 ,4 ,5 ]
Shei, Chris [6 ]
Yao, Zheng-Ting [2 ]
Chen, Yu-Wen [7 ]
机构
[1] Natl Cheng Kung Univ, Dept Elect Engn, Tainan 70101, Taiwan
[2] Natl Cheng Kung Univ, Inst Comp, Commun Engn, Tainan 70101, Taiwan
[3] Chi Mei Med Ctr, Dept Med Imaging, Tainan 710402, Taiwan
[4] Chia Nan Univ Pharm & Sci, Dept Hlth & Nutr, Tainan 71710, Taiwan
[5] Natl Sun Yat Sen Univ, Inst Biomed Sci, Kaohsiung 80424, Taiwan
[6] Swansea Univ, Coll Arts & Human, Swansea SA2 8PP, W Glam, Wales
[7] Acad Sinica, Res Ctr Informat Technol Innovat, Taipei 115201, Taiwan
来源
APPLIED SCIENCES-BASEL | 2022年 / 12卷 / 09期
关键词
air quality prediction; deep learning; spatial-temporal attention; INTERPOLATION; IMPACT; PM2.5;
D O I
10.3390/app12094268
中图分类号
O6 [化学];
学科分类号
0703 ;
摘要
Air pollution in cities is a severe and worrying problem because it causes threats to economic development and health. Furthermore, with the development of industry and technology, rapid population growth, and the massive expansion of cities, the total amount of pollution emissions continue to increase. Hence, observing and predicting the air quality index (AQI), which measures fatal pollutants to humans, has become more and more critical in recent years. However, there are insufficient air quality monitoring stations for AQI observation because the construction and maintenance costs are too high. In addition, finding an available and suitable place for monitoring stations in cities with high population density is difficult. This study proposes a spatial-temporal model to predict the long-term AQI in a city without monitoring stations. Our model calculates the spatial-temporal correlation between station and region using an attention mechanism and leverages the distance information between all existing monitoring stations and target regions to enhance the effectiveness of the attention structure. Furthermore, we design a hybrid predictor that can effectively combine the time-dependent and time-independent predictors using the dynamic weighted sum. Finally, the experimental results show that the proposed model outperforms all the baseline models. In addition, the ablation study confirms the effectiveness of the proposed structures.
引用
收藏
页数:17
相关论文
共 50 条
  • [31] Predicting Fine-Grained Air Quality Based on Deep Neural Networks
    Yi, Xiuwen
    Duan, Zhewen
    Li, Ruiyuan
    Zhang, Junbo
    Li, Tianrui
    Zheng, Yu
    [J]. IEEE TRANSACTIONS ON BIG DATA, 2022, 8 (05) : 1326 - 1339
  • [32] Probabilistic air quality forecasting using deep learning spatial-temporal neural network
    Abirami, S.
    Chitra, P.
    [J]. GEOINFORMATICA, 2023, 27 (02) : 199 - 235
  • [33] Fine-Grained Radio Frequency Fingerprint Recognition Network Based on Attention Mechanism
    Zhang, Yulan
    Hu, Jun
    Jiang, Rundong
    Lin, Zengrong
    Chen, Zengping
    [J]. ENTROPY, 2024, 26 (01)
  • [34] Dual attention interactive fine-grained classification network based on data augmentation
    Zhu, Qiangxi
    Kuang, Wenlan
    Li, Zhixin
    [J]. JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION, 2022, 88
  • [35] Sentiment Classification of Reviews Based on BiGRU Neural Network and Fine-grained Attention
    Feng, Xuanzhen
    Liu, Xiaohong
    [J]. 2019 3RD INTERNATIONAL CONFERENCE ON MACHINE VISION AND INFORMATION TECHNOLOGY (CMVIT 2019), 2019, 1229
  • [36] Fine-grained vehicle type detection and recognition based on dense attention network
    Ke, Xiao
    Zhang, Yufeng
    [J]. NEUROCOMPUTING, 2020, 399 (247-257) : 247 - 257
  • [37] A fine-grained classification method based on self-attention Siamese network
    He Can
    Yuan Guowu
    Wu Hao
    [J]. 2021 THE 5TH INTERNATIONAL CONFERENCE ON VIDEO AND IMAGE PROCESSING, ICVIP 2021, 2021, : 148 - 154
  • [38] A Short-term Traffic Flow Forecasting Model Based on Spatial-temporal Attention Neural Network
    Dong, Honghui
    Zhu, Pengcheng
    Gao, Jiayang
    Jia, Limin
    Qin, Yong
    [J]. 2022 IEEE 25TH INTERNATIONAL CONFERENCE ON INTELLIGENT TRANSPORTATION SYSTEMS (ITSC), 2022, : 416 - 421
  • [39] Fine-Grained Visual Classification Network Based on Fusion Pooling and Attention Enhancement
    Xiao, Bin
    Guo, Jingwei
    Zhang, Xingpeng
    Wang, Min
    [J]. Moshi Shibie yu Rengong Zhineng/Pattern Recognition and Artificial Intelligence, 2023, 36 (07): : 661 - 670
  • [40] STGAFormer: Spatial-temporal Gated Attention Transformer based Graph Neural Network for traffic flow forecasting
    Geng, Zili
    Xu, Jie
    Wu, Rongsen
    Zhao, Changming
    Wang, Jin
    Li, Yunji
    Zhang, Chenlin
    [J]. INFORMATION FUSION, 2024, 105