Reanalysis products have been applied to calculate the tropospheric delay for Global Navigation Satellite System (GNSS) positioning purposes widely. It is necessary to obtain high-precision tropospheric delay information from GNSS users with a high-precision tropospheric vertical stratification model because the height of the grids of the atmospheric reanalysis data is inconsistent with that of GNSS users, especially in regions with high terrains. In addition, the variation of the tropospheric delay in the vertical direction is much higher than that in the horizontal direction. The zenith total delay (ZTD) vertical stratification model is also key to the development of real-time and high-precision ZTD models. A new approach, the sliding window algorithm, is proposed to develop a ZTD vertical stratification model. In this work, a ZTD vertical stratification model considering spatiotemporal factors is developed based on the second Modern-Era Retrospective analysis for Research and Applications (MERRA-2) data, which is named the GZTD-H model. Radiosonde and International GNSS Service (IGS) data are treated as reference values to evaluate the performance of the GZTD-H model, which is compared to the model GPT2w. The results show that the GZTD-H model realizes the highest performance in ZTD layered vertical interpolation against ZTD layered profiles obtained at radiosonde sites, which achieves an improvement of 10% over the model GPT2w. Compared to model GPT2w, the GZTD-H model attains a spatial interpolation improvement of 8% for the Global Geodetic Observing System (GGOS) Atmosphere gridded ZTD over the surface ZTD calculated from radiosonde profiles. Furthermore, compared to model GPT2w, the model GZTD-H also attains improvements of 11% over the precise ZTD products acquired at IGS sites. In terms of model parameters, the GZTD-H model is greatly reduced and optimized over model GPT2w. Hence, the applicability of this model is enhanced in terms of GNSS atmospheric sounding and precise GNSS positioning.

再分析产品已被广泛用于全球导航卫星系统（GNSS）定位目的的对流层延迟计算。必须使用高精度对流层垂直分层模型从GNSS用户获取高精度对流层延迟信息，因为大气再分析数据的网格高度与GNSS用户的高度不一致，尤其是在地形高的地区。另外，对流层延迟在垂直方向上的变化远大于在水平方向上的变化。天顶总延迟（ZTD）垂直分层模型也是开发实时和高精度ZTD模型的关键。提出了一种新的方法，即滑动窗口算法，以开发ZTD垂直分层模型。在这项工作中，一个基于时空因素的ZTD垂直分层模型是基于第二次现代研究和应用回顾性分析（MERRA-2）数据开发的，该模型称为GZTD-H模型。将无线电探空仪和国际GNSS服务（IGS）数据视为参考值，以评估GZTD-H模型的性能，并将其与GPT2w模型进行比较。结果表明，相对于在探空仪站点获得的ZTD分层剖面，GZTD-H模型在ZTD分层垂直插值中实现了最高性能，比GPT2w模型提高了10％。与模型GPT2w相比，GZTD-H模型对全球大地观测系统（GGOS）大气网格化ZTD的空间插值改进了8％（根据探空仪剖面计算得出）。此外，与GPT2w型号相比，GZTD-H型号还比在IGS站点上购买的精确ZTD产品提高了11％。在模型参数方面，与模型GPT2w相比，大大减少了GZTD-H模型并对其进行了优化。因此，就GNSS大气探测和精确的GNSS定位而言，该模型的适用性得到了增强。