Modeling and Forecasting the GPS Zenith Troposphere Delay in West Antarctica Based on Different Blind Source Separation Methods and Deep Learning

Zhang, Qingchuan; Li, Fēi; Zhang, Shengkai; Li, Wenhao

doi:10.3390/s20082343

Cited by 26 publications

(4 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…PWV. Furthermore, the prediction models of tropospheric correction based on machine learning algorithms were discussed by Zhang et al (2020) and Selbesoglu (2020). In their studies, the prediction models can forecast tropospheric corrections six hours in advance.…”

Section: Pwv Periodical Variations Due To Spiral Rainbandsmentioning

confidence: 99%

Tropical cyclone-induced periodical positioning disturbances during the 2017 Hato in the Hong Kong region

Liu

2021

GPS Solut

View full text Add to dashboard Cite

The tropospheric delay is an important error source in the Global Positioning System (GPS) positioning and navigation applications. Although most of the tropospheric delays can be removed in the double-differencing (DD) positioning mode, their remaining residuals can still contaminate the positioning accuracy and become unpredictable when tropospheric condition encounters severe variations such as during a tropical cyclone (TC) event. We investigated the positioning performance of five baselines with lengths ranging from 7.8 km to 49.9 km during the 2017 TC Hato. The results showed that the TC Hato brought a significant disturbance to the GPS baseline positioning results, particularly in the vertical (up) component. The TC Hato started to affect Hong Kong and the root mean squares (RMS) of GPS positioning errors increased dramatically from about 30 mm to 140 mm.when it was at a distance of 400-600 km from Hong Kong on August 22, 2017. We found that the vertical positioning errors on that day have the major periods: 2.7 h, 3.0 h, 3.4 h, 4.0 h, and 4.8 h.Examining the wet and hydrostatic parts of the tropospheric delays via the continuous wavelet spectral analysis, we found that the periodical variation of the positioning results on August 22 was caused by the periodical variation of the precipitable water vapor (PWV). The variation of differenced PWV between two baseline stations had consistent periods of 2-5 h. Besides, the periods of differenced PWV time series are in good agreement with the spiral rainband in the TC. This finding suggests that the TC Hato induce periodical PWV variations at two GPS stations of baseline, which resulted in GPS positioning errors of the same periods.

show abstract

Section: Pwv Periodical Variations Due To Spiral Rainbandsmentioning

confidence: 99%

Tropical cyclone-induced periodical positioning disturbances during the 2017 Hato in the Hong Kong region

Liu

2021

GPS Solut

View full text Add to dashboard Cite

show abstract

“…To make a more accurate and reliable prediction of PWV in Japan, we introduced the radial basis function neural network (RBFNN) to construct the ZTD prediction model to compensate for the error of ZTD estimated by the GPT3 model. Compared with the existing ZTD prediction models based on machine learning algorithms (Xiao et al, 2018;Q. Zhang et al, 2020), our models use shortterm historical data to forecast the following data in the next few days and with the background model to constrain the stability.…”

Section: Introductionmentioning

confidence: 99%

A precipitation forecast model applied with the RBF based on the improved GPT3 model in Japan

Song

Jiang

et al. 2023

Preprint

View full text Add to dashboard Cite

Accurate monitoring of atmospheric water vapor content is essential for the early warning of extreme weather events. As known, GNSS zenith troposphere delay (GNSS_ZTD) is an indispensable data source for retrieving precipitable water vapor (PWV). However, the newest GPT3 empirical model is not accurate enough to perform the ZTD (GPT3_ZTD) and PWV (GPT3_PWV) estimation in some regions, such as Japan. Thus, here we introduce a radial basis function (RBF) neural network to establish ZTD forecast models based on the GPT3 model and use the predicted ZTD to retrieve PWV and adopt the retrieved PWV in forecasting precipitation. To thoroughly verify the accuracy of forecast results in 2021, we selected three external validation data, which are GNSS, radiosonde, and meteorological data. The GNSS_ZTD validation results show that the error compensation model of GPT3 based on RBF is superior to the GPT3 model and the model using a single RBF and back propagation (BP) neural network. The average RMSE of all GNSS stations is 50.7mm, 53.7mm, and 37.8mm for GPT3_ZTD, RBF_BP_ZTD, and RBF_GPT3_ZTD, respectively. The GNSS_PWV and RO_PWV validation results show that the retrieved PWV with compensation of RBF_GPT3_ZTD is better than the uncompensated GPT3_ZTD, the average accuracy of RBF_GPT3_PWV of GNSS stations and radiosonde stations is improved by 40.4% and 25.8% against that of GPT3_PWV. For the precipitation forecast model results, the average forecast accuracy of all GNSS stations and radiosonde stations is 63.12% and 61.36%, according to the ERA5 precipitation. The average forecast accuracy is 66.26%, validated by meteorological precipitation records. The proposed model not only improves the GPT3 model but also forecasts the PWV value, which can improve the precipitation forecast in Japan, and is expected to expand to other regions.

show abstract

“…Zhang et al established an hourly ZTD model using GPS-derived ZTD products by independent component analysis (ICA) and principal component analysis (PCA), and conducted short-time-span regional ZTD forecasting model using a long short-term memory (LSTM) neural network. Their results showed that ICA was superior to PCA, and the 24-h ZTD forecasting root mean square error (RMSE) was 13.3 cm [28]. These sequence-aligned models are natural choices for modeling time-series data.…”

Section: Introductionmentioning

confidence: 99%

Transformer-Based Global Zenith Tropospheric Delay Forecasting Model

Zhang

Yao

et al. 2022

Remote Sensing

View full text Add to dashboard Cite

Zenith tropospheric delay (ZTD) plays an important role in high-precision global navigation satellite system (GNSS) positioning and meteorology. At present, commonly used ZTD forecasting models comprise empirical, meteorological parameter, and neural network models. The empirical model can only fit approximate periodic variations, and its accuracy is relatively low. The accuracy of the meteorological parameter model depends heavily on the accuracy of the meteorological parameters. The recurrent neural network (RNN) is suitable for short-term series data prediction, but for long-term series, the ZTD prediction accuracy is clearly reduced. Long short-term memory (LSTM) has superior forecasting accuracy for long-term ZTD series; however, the LSTM model is complex, cannot be parallelized, and is time-consuming. In this study, we propose a novel ZTD time-series forecasting utilizing transformer-based machine-learning methods that are popular in natural language processing (NLP) and forecasting global ZTD, the training parameters provided by the global geodetic observing system (GGOS). The proposed transformer model leverages self-attention mechanisms by encoder and decoder modules to learn complex patterns and dynamics from long ZTD time series. The numeric results showed that the root mean square error (RMSE) of the forecasting ZTD results were 1.8 cm and mean bias, STD, MAE, and R 0.0, 1.7, 1.3, and 0.95, respectively, which is superior to that of the LSTM, RNN, convolutional neural network (CNN), and GPT3 series models. We investigated the global distribution of these accuracy indicators, and the results demonstrated that the accuracy in continents was superior to maritime space transformer ZTD forecasting model accuracy at high latitudes superior to that at low latitude. In addition to the overall accuracy improvement, the proposed transformer ZTD forecast model also mitigates the accuracy variations in space and time, thereby guaranteeing high accuracy globally. This study provides a novel method to estimate the ZTD, which could potentially contribute to precise GNSS positioning and meteorology.

show abstract

Modeling and Forecasting the GPS Zenith Troposphere Delay in West Antarctica Based on Different Blind Source Separation Methods and Deep Learning

Cited by 26 publications

References 37 publications

Tropical cyclone-induced periodical positioning disturbances during the 2017 Hato in the Hong Kong region

Tropical cyclone-induced periodical positioning disturbances during the 2017 Hato in the Hong Kong region

A precipitation forecast model applied with the RBF based on the improved GPT3 model in Japan

Transformer-Based Global Zenith Tropospheric Delay Forecasting Model

Contact Info

Product

Resources

About