A neural network model for predicting weighted mean temperature

Abstract. The tropospheric weighted mean temperature (Tm) is one of the key characteristic parameters in the troposphere, which plays an important role in the conversion of Zenith Wet Delay (ZWD) to atmospheric Precipitable Water Vapor (PWV). The precision of Global Navigation Satellite System (GNSS) inversion of PWV can be significantly improved with the accurate calculation of Tm. Due to the strong nonlinear mapping ability of Back Propagation (BP) neural network, the algorithm can be used to excavate the law with massive data. In term of the nonlinear and non-stationary characteristics of GNSS precipitable water vapor, in this paper, we proposes a forecast method of GNSS precipitable water vapor based on BP neural network, which can modelling the weighted mean temperature of troposphere. The traditional BP neural network has some shortcomings, such as large amount of calculation, long training time and easy to appear “over-fitting” phenomenon and so on. In order to optimize the deficiency and numerical simulation, the three characteristic values include water vapor pressure, surface pressure and surface temperature provided are selected as input parameters, named as BP_Tm. The optimal initialization parameters of the model were obtained from the 2016 radiosonde data of 89 radiosonde stations in China, and the modeling and accuracy verification were conducted with the 2017 radiosonde data，and the accuracy of the new model was compared with the common regional Tm model. The results show the BP_Tm model has good simulation accuracy, the average deviation is −0.186K, and the root mean square error is 3.144K. When simulating the weighted mean temperature of a single station, the accuracy of the four models to simulate Tm is compared and analyzed, which the BP_Tm model can obtain good accuracy and reflect better stability and reliability.

Download Full-text

A Novel Modeling Strategy of Weighted Mean Temperature in China Using RNN and LSTM

Remote Sensing ◽

10.3390/rs13153004 ◽

2021 ◽

Vol 13 (15) ◽

pp. 3004

Author(s):

Wenliang Gao ◽

Jingxiang Gao ◽

Liu Yang ◽

Mingjun Wang ◽

Wenhao Yao

Keyword(s):

Neural Network ◽

Water Vapor ◽

Short Term Memory ◽

Precipitable Water ◽

Satellite System ◽

Site Location ◽

Weighted Mean ◽

Mean Temperature ◽

Weighted Mean Temperature ◽

Modeling Strategy

In the meteorology of Global Navigation Satellite System, the weighted mean temperature (Tm) is a key parameter in the process of converting the zenith wetness delay into precipitable water vapor, and it plays an important role in water vapor monitoring. In this research, two deep learning algorithms, namely, recurrent neural network (RNN) and long short-term memory neural network (LSTM), were used to build a high-precision weighted mean temperature model for China using their excellent time series memory capability. The model needs site location information and measured surface temperature to predict the weighted mean temperature. We used data from 118 stations in and around China provided by the Integrated Global Radiosonde Archive from 2010 to 2015 to train the model and data from 2016 for model testing. The root mean square error (RMSE) of the RNN_Tm and LSTM_Tm models were 3.01K and 2.89K, respectively. Compared with the values calculated by the empirical GPT3 model, the accuracy was improved by 31.1% (RNN_Tm) and 33.9% (LSTM_Tm). In addition, we selected another 10 evenly distributed stations in China and used the constructed model to test the prediction capability of the weighted mean temperature from 2010 to 2016. The RMSE values were 2.95K and 2.86K, which proved that the model also exhibits high generalization in non-modeling sites in China. In general, the RNN_Tm and LSTM_Tm models have a good performance in weighted mean temperature prediction.

Download Full-text

Neural Network-Based Models for Estimating Weighted Mean Temperature in China and Adjacent Areas

Atmosphere ◽

10.3390/atmos12020169 ◽

2021 ◽

Vol 12 (2) ◽

pp. 169

Author(s):

Fengyang Long ◽

Wusheng Hu ◽

Yanfeng Dong ◽

Jinling Wang

Keyword(s):

Neural Network ◽

Water Vapor ◽

Meteorological Factor ◽

Profile Data ◽

Weighted Mean ◽

Mean Temperature ◽

Weighted Mean Temperature ◽

New Models ◽

Atmospheric Profile ◽

Tm Model

The weighted mean temperature (Tm) is a key parameter when converting the zenith wet delay (ZWD) to precipitation water vapor (PWV) in ground-based Global Navigation Satellite System (GNSS) meteorology. Tm can be calculated via numerical integration with the atmospheric profile data measured along the zenith direction, but this method is not practical in most cases because it is not easy for general users to get real-time atmospheric profile data. An alternative method to obtain an accurate Tm value is to establish regional or global models on the basis of its relations with surface meteorological elements as well as the spatiotemporal variation characteristics of Tm. In this study, the complex relations between Tm and some of its essentially associated factors including the geographic position and terrain, surface temperature and surface water vapor pressure were considered to develop Tm models, and then a non-meteorological-factor Tm model (NMFTm), a single-meteorological-factor Tm model (SMFTm) and a multi-meteorological-factor Tm model (MMFTm) applicable to China and adjacent areas were established by adopting the artificial neural network technique. The generalization performance of new models was strengthened with the help of an ensemble learning method, and the model accuracies were compared with several representative published Tm models from different perspectives. The results show that the new models all exhibit consistently better performance than the competing models under the same application conditions tested by the data within the study area. The NMFTm model is superior to the latest non-meteorological model and has the advantages of simplicity and utility. Both the SMFTm model and MMFTm model show higher accuracy than all the published Tm models listed in this study; in particular, the MMFTm model is about 14.5% superior to the first-generation neural network-based Tm (NN-I) model, with the best accuracy so far in terms of the root-mean-square error.

Download Full-text

Advanced grid model of weighted mean temperature based on feedforward neural network over China

Earth and Space Science ◽

10.1029/2020ea001458 ◽

2021 ◽

Author(s):

Mingchen Zhu ◽

Wusheng Hu ◽

Wei Sun

Keyword(s):

Neural Network ◽

Feedforward Neural Network ◽

Weighted Mean ◽

Grid Model ◽

Mean Temperature ◽

Weighted Mean Temperature

Download Full-text

Improving the Estimation of Weighted Mean Temperature in China Using Machine Learning Methods

Remote Sensing ◽

10.3390/rs13051016 ◽

2021 ◽

Vol 13 (5) ◽

pp. 1016

Author(s):

Zhangyu Sun ◽

Bao Zhang ◽

Yibin Yao

Keyword(s):

Neural Network ◽

Machine Learning ◽

Water Vapor ◽

Water Vapor Pressure ◽

Tropospheric Delay ◽

Weighted Mean ◽

Learning Methods ◽

Machine Learning Methods ◽

Mean Temperature ◽

Weighted Mean Temperature

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.

Download Full-text