Page 149 - 《武汉大学学报(信息科学版)》2025年第9期
P. 149

第 50 卷第 9 期           武帅莹等:一种基于 GNSS 和机器学习的 InSAR 大气改正方法                             1877


               [52]  YU C, PENNA N T, LI Z H.  Generation of Real-   CHI  H,  et  al.   Improving  Tropospheric  Corrections
                    Time  Mode  High-Resolution  Water  Vapor  Fields   on  Large-Scale  Sentinel-1  Interferograms  Using  a
                    from GPS Observations[J].  Journal of Geophysical   Machine  Learning  Approach  for  Integration  with
                    Research: Atmospheres, 2017, 122(3): 2008-2025.  GNSS-Derived Zenith Total Delay (ZTD)[J].  Re⁃
               [53]  WALTERS  R  J,  ELLIOTT  J  R ,  LI  Z ,  et  al.    mote Sensing of Environment, 2020, 239: 111608.
                    Rapid  Strain  Accumulation  on  the  Ashkabad  Fault   [60]  TANG  W,  LIAO  M  S,  ZHANG  L,  et  al.   Study
                    (Turkmenistan)  from  Atmosphere-Corrected  In⁃  on InSAR Tropospheric Correction Using Global At⁃
                    SAR[J].   Journal  of  Geophysical  Research:  Solid   mospheric  Reanalysis  Products[J].   2017,  60(2):
                    Earth, 2013, 118(7): 3674-3690.                  527-540.
               [54]  WILGAN  K,  HURTER  F,  GEIGER  A,  et  al.    [61]  PRATS-IRAOLA P, SCHEIBER R, MAROTTI
                    Tropospheric  Refractivity  and  Zenith  Path  Delays   L,  et  al.   TOPS  Interferometry  with  TerraSAR-X
                    from  Least-Squares  Collocation  of  Meteorological   [J].   IEEE  Transactions  on  Geoscience  and  Remote
                    and GNSS Data[J].  Journal of Geodesy, 2017, 91  Sensing, 2012, 50(8): 3179-3188.
                    (2): 117-134.                               [62]  COSTANTINI  M.   A  Novel  Phase  Unwrapping
               [55]  SPOORTHI  G  E,  GORTHI  S,  GORTHI  R  K  S    Method Based on Network Programming[J].  IEEE
                    S.   PhaseNet:  A  Deep  Convolutional  Neural  Net⁃  Transactions  on  Geoscience  and  Remote  Sensing,
                    work  for  Two-Dimensional  Phase  Unwrapping[J].    1998, 36(3): 813-821.
                    IEEE Signal Processing Letters, 2019, 26(1): 54-58.  [63]  BÉLISLE E, HUANG Z, LE DIGABEL S, et al.
               [56]  MA L, LIU Y, ZHANG X L, et al.  Deep Learning   Evaluation  of  Machine  Learning  Interpolation  Tech⁃
                    in  Remote  Sensing  Applications:  A  Meta-Analysis   niques for Prediction of Physical Properties[J].  Com⁃
                    and Review[J].  ISPRS Journal of Photogrammetry   putational Materials Science, 2015, 98: 170-177.
                    and Remote Sensing, 2019, 152: 166-177.     [64]  李永生, 张景发, 姜文亮, 等 .  基于网络法时序 In⁃
               [57]  JIN J C, CHEN G, MENG X M, et al.  Prediction   SAR 大气误差校正方法研究[J].  大地测量与地球
                    of  River  Damming  Susceptibility  by  Landslides   动力学, 2015, 35(1): 145-149.
                    Based  on  a  Logistic  Regression  Model  and  InSAR   LI Yongsheng, ZHANG Jingfa, JIANG Wenliang,
                    Techniques: A Case Study of the Bailong River Ba⁃  et al.  Atmospheric Artifacts Correction in Time Se⁃
                    sin,  China[J].   Engineering  Geology,  2022,  299:   ries  InSAR  Using  Network  Methodology[J].   Jour⁃
                    106562.                                          nal  of  Geodesy  and  Geodynamics,  2015,  35(1):
               [58]  XUE  X  M.   Time-Dependent  Modeling  of  Volcano   145-149.
                    Deformation in Alaska and Transient Detection Using   [65]  BEKAERT D P S, WALTERS R J, WRIGHT T
                    Machine Learning Methods[D].  East Lansing, MI,   J,  et  al.   Statistical  Comparison  of  InSAR  Tropo⁃
                    USA: Michigan State University, 2021.            spheric  Correction  Techniques[J].   Remote  Sensing
               [59]  SHAMSHIRI  R,  MOTAGH  M,  NAHAVAND⁃            of Environment, 2015, 170: 40-47.
   144   145   146   147   148   149   150   151   152   153   154