Volume 40 Issue 4
Jul.  2020
Turn off MathJax
Article Contents
LUO Liming, BAI Weihua, SUN Yueqiang, XIA Junming. GNSS-R Sea Surface Wind Speed Inversion Based on Tree Model Machine Learning Method[J]. Chinese Journal of Space Science, 2020, 40(4): 595-601. doi: 10.11728/cjss2020.04.595
Citation: LUO Liming, BAI Weihua, SUN Yueqiang, XIA Junming. GNSS-R Sea Surface Wind Speed Inversion Based on Tree Model Machine Learning Method[J]. Chinese Journal of Space Science, 2020, 40(4): 595-601. doi: 10.11728/cjss2020.04.595

GNSS-R Sea Surface Wind Speed Inversion Based on Tree Model Machine Learning Method

doi: 10.11728/cjss2020.04.595
  • Received Date: 2018-12-05
  • Rev Recd Date: 2020-05-25
  • Publish Date: 2020-07-15
  • GNSS-R is a new technique based on GNSS satellite reflection signals, and it can be applied to the inversion of sea surface wind field. The traditional GNSS-R technology inversion of sea surface wind field mainly has waveform matching and experience function. The waveform matching method is time-consuming and computationally intensive; the empirical function method often uses only a small amount of physical observations, which causes waste of additional information and loss of certain inversion precision. The accuracy of the traditional method of wind speed inversion is about 2m·s-1. In order to improve the inversion accuracy of sea surface wind speed, the tree model algorithm decision tree, random forest and GBDT commonly used in the field of machine learning are introduced to predict the sea surface wind speed. The training set and the verification set are constructed by using GNSS-R and ECMWF data. The training set is used for model learning, and the verification set is used to test the inversion effect of the model. The prediction error of decision tree and random forest is about 0.6m·s-1, and the prediction error of GBDT and other algorithms is about 2m·s-1, which meets the requirements of wind speed inversion. Compared with the traditional GNSS-R inversion method, the machine learning tree model algorithm performs better and has stable performance and less error on the verification set. Therefore, the machine learning tree model algorithm can be applied to the sea surface wind speed inversion.

     

  • loading
  • [1]
    ZHANG Lei, SHI Hanqing, LONG Zhiyong, et al. A review of methods for retrieving sea surface wind field from spaceborne synthetic aperture radar images[J]. Marine Sci. Bull., 2012, 31(6):713-720(张雷, 石汉青, 龙智勇, 等. 星载合成孔径雷达图像反演海面风场方法综述[J]. 海洋通报, 2012, 31(6):713-720)
    [2]
    LÜ Fan, XIU Chundi, WANG Feng, et al. Simulation analysis of GNSS-R sea surface wind field inversion model[J]. J. Naut. Navig., 2018, 6(3):87-91, 97(吕帆, 修春娣, 王峰, 等. GNSS-R海面风场反演模型仿真分析[J]. 导航定位学报, 2018, 6(3):87-91, 97)
    [3]
    MARTIN N M. A Passive Reflectometry and Interferometry System (PARIS) application to ocean altimetry[J]. Esa J., 1993, 17(4):331-355
    [4]
    YANG D K, ZHANG Y Q, LU Y, et al. GPS reflections for sea surface wind speed measurement[J]. IEEE Geosci. Remote Sens. Lett., 2008, 5(4):569-572
    [5]
    SHEN L C, JUANG J C, TSAI C L, et al. Stream soil moisture estimation by reflected GPS signals with ground truth measurements[J]. IEEE Trans. Instr. Meas., 2009, 58(3):730-737
    [6]
    WAN Wei, CHEN Xiuwan, PENG Xuefeng, et al. Progress and prospect of GNSS remote sensing research and application[J]. J. Remote Sens., 2016, 20(5):858-874(万玮, 陈秀万, 彭学峰, 等. GNSS遥感研究与应用进展和展望[J]. 遥感学报, 2016, 20(5):858-874)
    [7]
    YU K, RIZOS C, BURRAGE D, et al. An overview of GNSS remote sensing[J]. Eurasip J. Adv. Signal Proc., 2014, 2014(1):134
    [8]
    BAI Weihua. GNSS-R Marine Remote Sensing Technology Research[D]. Beijing:Graduate School of Chinese Academy of Sciences (白伟华. GNSS-R海洋遥感技术研究[D]. 北京:中国科学院研究生院, 2008)
    [9]
    YANG Dongkai, ZHANG Qishan. Foundation and Practice of GNSS Reflected Signal Processing[M]. Beijing:Publishing House of Electronics Industry, 2012(杨东凯, 张其善. GNSS反射信号处理基础与实践[M]. 北京:电子工业出版社, 2012)
    [10]
    BREIMAN L. Bagging predictors[J]. Mach. Learning, 1996, 24:123-140
    [11]
    FREUND Y. Boosting a weak learning algorithm by majority[J]. Inf. Comp., 1995, 121(2):256-285
    [12]
    FREUND Y, SCHAPIRE R E. A decision-theoretic generalization of on-line learning and an application to boosting[J]. J. Comp. Sys. Sci., 1997, 55(1):119-139
    [13]
    FRIEDMAN J H. Greedy function approximation:a gradient boosting machine[J]. Ann. Stat., 2001, 29(5):1189-1232
    [14]
    CHEN Tianqi, CARLOs Guestrin. XGBoost:a scalable tree boosting system[C]//Proceeding KDD'16 Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York:ACM, 2016:785-794
    [15]
    KE G, MENG Q, FINELY T, et al. LightGBM:A Highly Efficient Gradient Boosting Decision Tree[R]. 31st Conference on Neural Information Processing Systems. California:Neural Information Processing Systems, 2017
    [16]
    SENI G, ELDER J F. Ensemble methods in data mining:improving accuracy through combining predictors[J]. Synt. Lect. Data Mining Know. Disc., 2010, 2(1):1-126
  • 加载中

Catalog

    通讯作者: 陈斌, bchen63@163.com
    • 1. 

      沈阳化工大学材料科学与工程学院 沈阳 110142

    1. 本站搜索
    2. 百度学术搜索
    3. 万方数据库搜索
    4. CNKI搜索

    Article Metrics

    Article Views(783) PDF Downloads(98) Cited by()
    Proportional views
    Related

    /

    DownLoad:  Full-Size Img  PowerPoint
    Return
    Return