Global Ocean Wind Speed Retrieval From GNSS Reflectometry Using CNN-LSTM Network

被引:15
|
作者
Lu, Cuixian [1 ]
Wang, Zhuo [1 ]
Wu, Zhilu [1 ]
Zheng, Yuxin [1 ]
Liu, Yuxuan [1 ]
机构
[1] Wuhan Univ, Sch Geodesy & Geomat, Wuhan 430079, Peoples R China
来源
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING | 2023年 / 61卷
基金
国家重点研发计划; 中国国家自然科学基金;
关键词
Wind speed; Sea surface; Feature extraction; Global navigation satellite system; Spatial resolution; Sea measurements; Convolutional neural networks; CNN-LSTM; cyclone GNSS (CYGNSS); global navigation satellite system reflectometry (GNSS-R); ocean wind speed; NEURAL-NETWORK;
D O I
10.1109/TGRS.2023.3276173
中图分类号
P3 [地球物理学]; P59 [地球化学];
学科分类号
0708 ; 070902 ;
摘要
Ocean surface winds play an essential role in regulating the Earth's weather and climate, and the cyclone GNSS (CYGNSS) mission launched in 2016 is designed specially to monitor the ocean wind speed. In this study, an innovative model is developed based on a deep learning method to retrieve the ocean wind speed by making full use of the spatiotemporal information of CYGNSS observations. The proposed model named CNN-LSTM is established based on two modules, i.e., the convolution neural network (CNN) module that extracts the spatial features around the specular point (SP) from a two-dimensional (2-D) matrix of delay-Doppler map (DDM) and the long short-term memory (LSTM) module that extracts the temporal features over a time series. The performance of the ocean wind speed derived from CNN-LSTM is assessed with the fifth-generation European Centre for Medium-Range Weather Forecasts (ECMWF) reanalysis (ERA5) products. The results show that the wind speed derived from CNN-LSTM reveals an accuracy of 1.34 m/s in terms of root-mean-square error (RMSE) values, showing an improvement of about 36.8%, 14.6%, and 6.3%, when compared to the official retrieval algorithm called minimum variance estimator (MVE), multilayer perceptron (MLP) net, and CNN, respectively, confirming the feasibility and effectiveness of the designed method. Among all the experiments in this study which apply machine learning-based algorithms, the wind speed achieved by CNN-LSTM presents the smallest RMSE value. Furthermore, the error analyses of the wind speed retrieval in spatial and temporal scales are also discussed, which indicates the robust performance of CNN-LSTM model. The results show that the CNN-LSTM model proposed in this study contributes to offering efficient processing of Global Navigation Satellite Systems Reflectometry (GNSS-R) observations and fully exploits the capabilities of high-accurate ocean wind speed retrieval on a global scale.
引用
收藏
页数:12
相关论文
共 50 条
  • [21] Coastal Ocean Wind Speed Estimation based GNSS-Reflectometry of BeiDou GEO Satellite
    Kasantikul, Kittipong
    Yang, Dongkai
    Wang, Qiang
    2018 OCEANS - MTS/IEEE KOBE TECHNO-OCEANS (OTO), 2018,
  • [22] Global wind speed retrieval from SAR
    Horstmann, J
    Schiller, H
    Schulz-Stellenfleth, J
    Lehner, S
    IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2003, 41 (10): : 2277 - 2286
  • [23] DEVELOPMENT OF A WIND SPEED RETRIEVAL METHOD BASED ON AIRBORNE GNSS REFLECTOMETRY EXPERIMENTS FOR TRITON SATELLITE MISSION
    Tsai, Yung-Fu
    Yang, Dian-Syuan
    Juang, Jyh-Ching
    Yeh, Wen-Hao
    Lo, Shih-Hung
    Hsieh, Ming-Yu
    Lin, Chen-Tsung
    2021 IEEE SPECIALIST MEETING ON REFLECTOMETRY USING GNSS AND OTHER SIGNALS OF OPPORTUNITY 2021 (GNSS+R 2021), 2021, : 1 - 4
  • [24] Hybrid CNN-LSTM Network for Cyberbullying Detection on Social Networks using Textual Contents
    Sultan, Daniyar
    Mendes, Mateus
    Kassenkhan, Aray
    Akylbekov, Olzhas
    INTERNATIONAL JOURNAL OF ADVANCED COMPUTER SCIENCE AND APPLICATIONS, 2023, 14 (09) : 748 - 756
  • [25] Inversion of Radial Shear Velocity Profile for Acoustic Logging Using CNN-LSTM Network
    Li, Jiacheng
    He, Xiao
    Chen, Hao
    Jiang, Can
    Wang, Wenwen
    IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2024, 62 : 1 - 10
  • [26] DUAL-MODE DECOMPOSITION CNN-LSTM INTEGRATED SHORT-TERM WIND SPEED FORECASTING MODEL
    Bi G.
    Zhao X.
    Li L.
    Chen S.
    Chen C.
    Taiyangneng Xuebao/Acta Energiae Solaris Sinica, 2023, 44 (03): : 191 - 197
  • [27] A CNN-LSTM neural network for recognition of puffing in smoking episodes using wearable sensors
    Volkan Y. Senyurek
    Masudul H. Imtiaz
    Prajakta Belsare
    Stephen Tiffany
    Edward Sazonov
    Biomedical Engineering Letters, 2020, 10 : 195 - 203
  • [28] A CNN-LSTM neural network for recognition of puffing in smoking episodes using wearable sensors
    Senyurek, Volkan Y.
    Imtiaz, Masudul H.
    Belsare, Prajakta
    Tiffany, Stephen
    Sazonov, Edward
    BIOMEDICAL ENGINEERING LETTERS, 2020, 10 (02) : 195 - 203
  • [29] Toward the Trajectory Predictor for Automatic Train Operation System Using CNN-LSTM Network
    He, Yijuan
    Lv, Jidong
    Liu, Hongjie
    Tang, Tao
    ACTUATORS, 2022, 11 (09)
  • [30] Pose estimation-based lameness recognition in broiler using CNN-LSTM network
    Nasiri, Amin
    Yoder, Jonathan
    Zhao, Yang
    Hawkins, Shawn
    Prado, Maria
    Gan, Hao
    COMPUTERS AND ELECTRONICS IN AGRICULTURE, 2022, 197