A new three-dimensional computerized ionospheric tomography model based on a neural network

Zheng, Dunyong; Yao, Yibin; Nie, Wenfeng; Chu, Nan; Lin, Dong; Ao, Minsi

doi:10.1007/s10291-020-01047-1

Cited by 26 publications

(16 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Modern artificial neural networks (ANNs) are particularly good at performing multifactorial analyses and usually serve as nonlinear statistical data modeling tools; of these, the multi-layer feedforward neural networks (MFNNs) have been widely used to solve nonlinear optimization problems with multiple inputs [17,[37][38][39]. T m is associated with many factors and the accuracy and efficiency of a traditional linear regression model of T m -T s , e s is not always satisfactory, so a three-layer feedforward neural network (TFNN) was employed to develop regional T m models applicable to China and adjacent areas in this work, and the ensemble learning method was used to strengthen the generalization performance of new models.…”

Section: Development Of New Modelsmentioning

confidence: 99%

“…The ensemble learning method is a good approach to strengthen the generalization performance of neural network models [37,41]. A TFNN can be thought to be an individual learner, and the purpose of ensemble learning is to achieve better generalization performance than a single learner by combining multiple individual learners.…”

Section: A Brief Introduction To Ensemble Learningmentioning

confidence: 99%

See 1 more Smart Citation

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

Long

Dong

et al. 2021

Atmosphere

View full text Add to dashboard Cite

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.

show abstract

Section: Development Of New Modelsmentioning

confidence: 99%

Section: A Brief Introduction To Ensemble Learningmentioning

confidence: 99%

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

Long

Dong

et al. 2021

Atmosphere

View full text Add to dashboard Cite

show abstract

“…However, the initial weight values for a BPNN are usually randomly generated before training, so the results are usually different from each other after training even for the same training set. In the training process, there is a great risk of falling into the local minimum as a result of training with the gradient descent method, and the generalization ability of the BPNN model for regression may be very poor due to incorrect selection [15,29,40]. Ensemble learning is a theoretical framework of machine learning based on combination strategy which includes the boosting and bagging method.…”

Section: The Bpnn and Ensemble Learningmentioning

confidence: 99%

“…Ensemble learning is a theoretical framework of machine learning based on combination strategy which includes the boosting and bagging method. The boosting method usually contains a series of base learners which are trained in series, and there is strong correlation between the sequentially generated learners [40]. In contrast, the bagging method and its base learners are trained in parallel, and the training process could be seen as mutually independent.…”

Section: The Bpnn and Ensemble Learningmentioning

confidence: 99%

Enhanced Neural Network Model for Worldwide Estimation of Weighted Mean Temperature

et al. 2021

View full text Add to dashboard Cite

Precise modeling of weighted mean temperature (Tm) is critical for realizing real-time conversion from zenith wet delay (ZWD) to precipitation water vapor (PWV) in Global Navigation Satellite System (GNSS) meteorology applications. The empirical Tm models developed by neural network techniques have been proved to have better performances on the global scale; they also have fewer model parameters and are thus easy to operate. This paper aims to further deepen the research of Tm modeling with the neural network, and expand the application scope of Tm models and provide global users with more solutions for the real-time acquisition of Tm. An enhanced neural network Tm model (ENNTm) has been developed with the radiosonde data distributed globally. Compared with other empirical models, the ENNTm has some advanced features in both model design and model performance, Firstly, the data for modeling cover the whole troposphere rather than just near the Earth’s surface; secondly, the ensemble learning was employed to weaken the impact of sample disturbance on model performance and elaborate data preprocessing, including up-sampling and down-sampling, which was adopted to achieve better model performance on the global scale; furthermore, the ENNTm was designed to meet the requirements of three different application conditions by providing three sets of model parameters, i.e., Tm estimating without measured meteorological elements, Tm estimating with only measured temperature and Tm estimating with both measured temperature and water vapor pressure. The validation work is carried out by using the radiosonde data of global distribution, and results show that the ENNTm has better performance compared with other competing models from different perspectives under the same application conditions, the proposed model expanded the application scope of Tm estimation and provided the global users with more choices in the applications of real-time GNSS-PWV retrival.

show abstract

“…The ionospheric analysis centers of International GNSS Service (IGS) have been routinely generating single‐layer global ionospheric maps (GIMs) derived from GNSS observations with different approaches since 1998 (Hernández‐Pajares et al., 2009; Roma‐Dollase et al., 2018). The GNSS‐based ionospheric tomography for obtaining the three‐dimensional (3‐D) ionospheric electron density (IED) has also received great attention of many research groups (Arikan, 2016; Bolmgren et al., 2020; Jin & Jin, 2011; Kunitsyn et al., 2013; Ma et al., 2005; Wen et al., 2010; Yao et al., 2013; Zheng et al., 2020).…”

Section: Introductionmentioning

confidence: 99%

Electron Density Reconstruction by Ionospheric Tomography From the Combination of GNSS and Upcoming LEO Constellations

et al. 2021

View full text Add to dashboard Cite

show abstract

A new three-dimensional computerized ionospheric tomography model based on a neural network

Cited by 26 publications

References 24 publications

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

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

Enhanced Neural Network Model for Worldwide Estimation of Weighted Mean Temperature

Electron Density Reconstruction by Ionospheric Tomography From the Combination of GNSS and Upcoming LEO Constellations

Contact Info

Product

Resources

About