中国空间科学技术 ›› 2022, Vol. 42 ›› Issue (2): 56-63.doi: 10.16708/j.cnki.1000-758X.2022.0022

• 论文 • 上一篇    下一篇

基于N-BEATS的单站对流层天顶总延迟预报

苏行,杨韬,孙保琪,杨旭海   

  1. 1中国科学院 国家授时中心,西安710600
    2中国科学院 精密导航定位与定时技术重点实验室,西安710600
    3中国科学院大学,北京100049
    4西北工业大学 无人系统技术研究院,西安710072
  • 出版日期:2022-04-25 发布日期:2022-03-30

Site-specific tropospheric zenith total delay forecast based on N-BEATS

  1. 1National Time Service Center, Chinese Academy of Sciences,Xi’an 710600, China
    2Key Laboratory of Precise Positioning and Timing Technology, Chinese Academy of Sciences, Xi’an 710600, China
    3University of Chinese Academy of Sciences, Beijing 100049, China
    4Unmanned System Research Institute, Northwestern Polytechnical University,Xi’an 710072,China
  • Online:2022-04-25 Published:2022-03-30

摘要: 高精度对流层延迟先验值有助于加速精密单点定位的快速收敛。基于高精度高分辨率气象数据库,采用深度学习NBEATS算法,进行了单站对流层天顶总延迟的预报试验。试验选取了9个IGS跟踪站,试验弧段从2002年1月至2019年6月共185a。首先基于NBEATS算法,设计了3种预报策略,然后基于前175a针对不同预报策略进行模型训练,并对最后365d的对流层天顶总延迟进行预报。试验结果表明,以该气象数据库为基准,12h以内预报弧段的预报残差均值量级大多可达亚毫米,2h、4h、6h的预报残差的标准差分别约为5mm、9mm、13mm。

关键词: N-BEATS, 深度学习, 时序预报, 对流层天顶总延迟, 对流层湿延迟, 对流层干延迟

Abstract: High-precision priori tropospheric delay can reduce the convergence time of precise point positioning. Based on a highprecision and high-resolution numerical meteorological database, the deep learning method N-BEATS algorithm was used to predict the site-specific tropospheric zenith total delay. Nine IGS tracking stations were selected. It covered 18.5 years from January 2002 to June 2019. Based on the N-BEATS algorithm, three forecast strategies were designed with different input arcs. The first 17.5 years of the entire period were used for model training. The last year’s data was used for validation. The results show that the average forecast residuals of different forecast arcs shorter than 12hours are mostly in the sub-millimeter range. As the forecast arc increases, the average forecast residual increases. The strategy with a longer input arc shows better performance than the other two strategies with shorter arcs. The standard deviations of the forecast residuals of 2hours, 4hours, and 6hours are approximately 5mm, 9mm, and 13mm, respectively.

Key words: N-BEATS, deep learning, time series forecast, tropospheric zenith total delay, tropospheric wet delay, tropospheric hydrostatic delay