由 张 良承 Deep learning for GNSS zenith tropospheric delay forecasting based on the informer model using 11-year ERA5 reanalysis data
基于11年ERA5再分析数据与Informer模型的GNSS天顶对流层延迟深度学习预测方法
引文格式 | Citation:
Hu F X, Sha Z M, Wei P Z, et al. Deep learning for GNSS zenith tropospheric delay forecasting based on the informer model using 11-year ERA5 reanalysis data[J]. GPS Solutions, 2024, 28(4): 182. DOI: 10.1007/s10291-024-01720-9.
GPS Solutions（中科院1区Top，IF：3.9）
Zenith tropospheric delay
Deep-learning
Informer
ERA5
Precise point positioning
Deep-learning
Informer
ERA5
Precise point positioning
Abstract | 摘要
Zenith Tropospheric Delay (ZTD) is one of the main atmospheric errors in the Global Navigation Satellite System (GNSS). In this study, we propose a novel ZTD forecasting model based on the deep-learning method named Informer-based ZTD (IBZTD) forecasting model using the European Centre for Medium-Range Weather Forecasts (ECMWF) fifth generation reanalysis data (ERA5) from 2011 to 2021. With 72-hour historical GNSS-derived ZTDs as prior information, the subsequent 24-hour ZTDs can be forecasted. The IBZTD forecasting model achieves the best regression fit with post GNSS-derived ZTDs compared with GPT3 (Global Pressure and Temperature 3) and HGPT2 (Hourly Global Pressure and Temperature 2) models, especially in winter with a Root Mean Square Error (RMSE) of 1.51 cm and a Mean Absolute Error (MAE) of 1.15 cm. With the post GNSS-derived ZTDs as reference, in terms of the overall 24-hour forecasting accuracy for 9 GNSS stations in 2022, IBZTD forecasting model achieves a MAE of 1.66 cm and a RMSE of 2.21 cm, significantly outperforming the GPT3 model (MAE: 2.60 cm, RMSE: 3.37 cm), HGPT2 model (MAE: 3.23 cm, RMSE: 4.03 cm) and Long Short-Term Memory (LSTM) model (MAE: 2.65 cm, RMSE: 3.65 cm). An average time improvement of 17.8% and comparable forecasting precisions are achieved in the IBZTD forecasting model compared with the Transformer-based ZTD (TBZTD) forecasting model. Using predicted ZTD as prior constraints in Precise Point Positioning (PPP), the vertical convergence speed exhibits a significant improvement of 14.20%, 20.24%, 18.48%, and 19.39% in four seasons.
天顶对流层延迟（ZTD）是全球导航卫星系统（GNSS）主要的大气误差源之一。本研究基于欧洲中期天气预报中心第五代再分析数据（ERA5）2011-2021年资料，提出了一种名为IBZTD的新型深度学习预报模型。该模型以72小时GNSS实测ZTD序列作为先验信息，可对未来24小时ZTD进行精准预报。相较于GPT3和HGPT2模型，IBZTD模型与事后GNSS ZTD数据具有最优的回归拟合度，其中冬季表现尤为突出，均方根误差（RMSE）和平均绝对误差（MAE）分别达1.51厘米和1.15厘米。以2022年9个GNSS测站的事后ZTD为参考，IBZTD模型在24小时预报中的整体MAE为1.66厘米，RMSE为2.21厘米，显著优于GPT3模型（MAE: 2.60厘米，RMSE: 3.37厘米）、HGPT2模型（MAE: 3.23厘米，RMSE: 4.03厘米）及长短期记忆网络模型（MAE: 2.65厘米，RMSE: 3.65厘米）。与基于Transformer的ZTD预报模型相比，IBZTD在保持相当精度的同时，平均计算效率提升17.8%。将预报ZTD作为先验约束应用于精密单点定位（PPP）解算，垂直方向收敛速度在四季分别提升14.20%、20.24%、18.48%和19.39%，展现出显著的性能改善。