Abstract
As a crucial parameter in estimating precipitable water vapor from tropospheric delay, the weighted mean temperature (Tm) plays an important role in Global Navigation Satellite System (GNSS)-based water vapor monitoring techniques. However, the rigorous calculation of Tm requires vertical profiles of temperature and water vapor pressure that are difficult to acquire in practice. As a result, empirical models are widely used but have limited accuracy. In this study, we use three machine learning methods, i.e., random forest (RF), backpropagation neural network (BPNN), and generalized regression neural network (GRNN), to improve the estimation of empirical Tm in China. The basic idea is to use the high-quality radiosonde observations estimated Tm to calibrate and optimize the empirical Tm through machine learning methods. Validating results show that the three machine learning methods improve the Tm accuracy by 37.2%, 32.6%, and 34.9% compared with the global pressure and temperature model 3 (GPT3). In addition to the overall accuracy improvement, the proposed methods also mitigate the accuracy variations in space and time, guaranteeing evenly high accuracy. This study provides a new idea to estimate Tm, which could potentially contribute to the GNSS meteorology.
Highlights
When Global Navigation Satellite System (GNSS) signals travel through the neutral atmosphere, they will experience a delay and bending effect due to atmospheric refraction.If the satellite elevation is larger than 5◦, the bending effect can be neglected [1]
We determined the optimal hyperparameters for different machine learning methods, i.e., the number of trees for random forest (RF), the neuron number in the hidden layer for backpropagation neural network (BPNN), and the spread value for generalized regression neural network (GRNN)
When comparing the three machine learning models, we found that the RF performs better than the BPNN and GRNN models by showing smaller cross-validation root mean square error (RMSE)
Summary
When Global Navigation Satellite System (GNSS) signals travel through the neutral atmosphere, they will experience a delay and bending effect due to atmospheric refraction.If the satellite elevation is larger than 5◦ , the bending effect can be neglected [1]. When Global Navigation Satellite System (GNSS) signals travel through the neutral atmosphere, they will experience a delay and bending effect due to atmospheric refraction. The delay effect always introduces apparent errors in positioning results. The GNSS community calls such error as tropospheric delay and usually models it with a multiplication between a zenith delay and a mapping function. The tropospheric delay is an error source in GNSS positioning and should be mitigated or eliminated. The tropospheric delay can be used to monitor the atmosphere since it contains important information about the troposphere, especially that the ZWD contains information about water vapor in the atmosphere. The water vapor in the atmosphere can be remotely sensed by taking advantage of ZWD
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
