STA-GAN: A Spatio-Temporal Attention Generative Adversarial Network for Missing Value Imputation in Satellite Data

被引:10
|
作者
Wang, Shuyu [1 ,2 ]
Li, Wengen [1 ]
Hou, Siyun [1 ,2 ]
Guan, Jihong [1 ]
Yao, Jiamin [1 ,2 ]
机构
[1] Tongji Univ, Dept Comp Sci & Technol, Shanghai 200082, Peoples R China
[2] Tongji Univ, China Natl Sci Seafloor Observ, Project Management Off, Shanghai 200082, Peoples R China
基金
国家重点研发计划; 中国国家自然科学基金;
关键词
satellite data; data imputation; spatio-temporal analytics; generative adversarial network; SEA-SURFACE TEMPERATURE; MACHINE LEARNING APPROACH; CHLOROPHYLL-A; SPATIAL INTERPOLATION; RECONSTRUCTION; VARIABILITY; PREDICTION; PRODUCTS; COVERAGE;
D O I
10.3390/rs15010088
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
Satellite data is of high importance for ocean environment monitoring and protection. However, due to the missing values in satellite data, caused by various force majeure factors such as cloud cover, bad weather and sensor failure, the quality of satellite data is reduced greatly, which hinders the applications of satellite data in practice. Therefore, a variety of methods have been proposed to conduct missing data imputation for satellite data to improve its quality. However, these methods cannot well learn the short-term temporal dependence and dynamic spatial dependence in satellite data, resulting in bad imputation performance when the data missing rate is large. To address this issue, we propose the Spatio-Temporal Attention Generative Adversarial Network (STA-GAN) for missing value imputation in satellite data. First, we develop the Spatio-Temporal Attention (STA) mechanism based on Graph Attention Network (GAT) to learn features for capturing both short-term temporal dependence and dynamic spatial dependence in satellite data. Then, the learned features from STA are fused to enrich the spatio-temporal information for training the generator and discriminator of STA-GAN. Finally, we use the generated imputation data by the trained generator of STA-GAN to fill the missing values in satellite data. Experimental results on real datasets show that STA-GAN largely outperforms the baseline data imputation methods, especially for filling satellite data with large missing rates.
引用
收藏
页数:20
相关论文
共 50 条
  • [21] Improved generative adversarial network with deep metric learning for missing data imputation
    Al-taezi, Mohammed Ali
    Wang, Yu
    Zhu, Pengfei
    Hu, Qinghua
    Al-badwi, Abdulrahman
    NEUROCOMPUTING, 2024, 570
  • [22] Missing Data Imputation in Transformer District Based on Improved Generative Adversarial Network
    Liu K.
    Zhou F.
    Zhou H.
    Wang C.
    Dianwang Jishu/Power System Technology, 2022, 46 (08): : 3231 - 3239
  • [23] Multi-task Generative Adversarial Network for Missing Mobility Data Imputation
    Shi, Meihui
    Shen, Derong
    Kou, Yue
    Nie, Tiezheng
    Yu, Ge
    PROCEEDINGS OF THE 31ST ACM INTERNATIONAL CONFERENCE ON INFORMATION AND KNOWLEDGE MANAGEMENT, CIKM 2022, 2022, : 4480 - 4484
  • [24] Missing data imputation for traffic flow speed using spatio-temporal cokriging
    Bae, Bumjoon
    Kim, Hyun
    Lim, Hyeonsup
    Liu, Yuandong
    Han, Lee D.
    Freeze, Phillip B.
    TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES, 2018, 88 : 124 - 139
  • [25] Sequential Imputation of Missing Spatio-Temporal Precipitation Data Using Random Forests
    Mital, Utkarsh
    Dwivedi, Dipankar
    Brown, James B.
    Faybishenko, Boris
    Painter, Scott L.
    Steefel, Carl I.
    FRONTIERS IN WATER, 2020, 2
  • [26] Bidirectional spatio-temporal generative adversarial network for video super-resolution
    Yang, Peng
    Chen, Zhangquan
    Sun, Yuankang
    Hu, Zhongjian
    Li, Bing
    PATTERN ANALYSIS AND APPLICATIONS, 2025, 28 (01)
  • [27] Missing Data Repairs for Traffic Flow With Self-Attention Generative Adversarial Imputation Net
    Zhang, Weibin
    Zhang, Pulin
    Yu, Yinghao
    Li, Xiying
    Biancardo, Salvatore Antonio
    Zhang, Junyi
    IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS, 2022, 23 (07) : 7919 - 7930
  • [29] Hyperparameter Tuning to Optimize Implementations of Denoising Autoencoders for Imputation of Missing Spatio-temporal Data
    Siddiqi, Muhammad Danial
    Jiang, Boyuan
    Asadi, Reza
    Regan, Amelia
    12TH INTERNATIONAL CONFERENCE ON AMBIENT SYSTEMS, NETWORKS AND TECHNOLOGIES (ANT) / THE 4TH INTERNATIONAL CONFERENCE ON EMERGING DATA AND INDUSTRY 4.0 (EDI40) / AFFILIATED WORKSHOPS, 2021, 184 : 107 - 114
  • [30] QAR Data Imputation Using Generative Adversarial Network with Self-Attention Mechanism
    Zhao, Jingqi
    Rong, Chuitian
    Dang, Xin
    Sun, Huabo
    BIG DATA MINING AND ANALYTICS, 2024, 7 (01): : 12 - 28