Search

This paper focuses on sea surface wind speed estimation using L1B level v3.1 data of reflected GNSS signals from the Cyclone GNSS (CYGNSS) mission and European Centre for Medium-range Weather Forecast Reanalysis (ECMWF) wind speed data. Seven machine learning methods are applied for wind speed retrieval, i.e., Regression trees (Binary Tree (BT), Ensembles of Trees (ET), XGBoost (XGB), LightGBM (LGBM)), ANN (Artificial neural network), Stepwise Linear Regression (SLR), and Gaussian Support Vector Machine (GSVM), and a comparison of their performance is made. The wind speed is divided into two different ranges to study the suitability of the different algorithms. A total of 10 observation variables are considered as input parameters to study the importance of individual variables or combinations thereof. The results show that the LGBM model performs the best with an RMSE of 1.419 and a correlation coefficient of 0.849 in the low wind speed interval (0–15 m/s), while the ET model performs the best with an RMSE of 1.100 and a correlation coefficient of 0.767 in the high wind speed interval (15–30 m/s). The effects of the variables used in wind speed retrieval models are investigated using the XGBoost importance metric, showing that a number of variables play a very significant role in wind speed retrieval. It is expected that these results will provide a useful reference for the development of advanced wind speed retrieval algorithms in the future. [ABSTRACT FROM AUTHOR]

The ionospheric total electron content (TEC) is an important ionospheric parameter, and it is widely utilized in research such as space weather prediction and precise positioning. However, it is still challenging to develop an ionospheric TEC prediction model with high accuracy. In this study, a new ionospheric TEC model over China was developed using the bidirectional long short‐term memory (bi‐LSTM) method and observations from 257 ground‐based global navigation satellite system (GNSS) stations in the Crustal Movement Observation Network of China from January 2018 to December 2021. The root mean square errors of the bi‐LSTM‐based model's 1 and 2 hr ahead predictions on the test data set (from June 2021 to December 2021) are 1.12 and 1.68 TECU, respectively, which are 75/50/32% and 72/48/22% smaller than those of the IRI‐2016, artificial neural network and LSTM‐based models, correspondingly. The bi‐LSTM‐based model shows the best performance, which is most likely due to the fact that the sequence information in both forward and backward directions is taken into consideration in the new model. In addition, the diurnal variation, seasonal variation of the ionospheric TEC, and variations under geomagnetic storm conditions are successfully captured by the bi‐LSTM‐based model. Moreover, the TEC maps resulting from the bi‐LSTM model agree well with those obtained from the final ionospheric product from the Chinese Academy of Sciences. Hence, the new model can be a good choice for the investigation of the spatiotemporal variation trend in the ionosphere and GNSS navigation. Plain Language Summary: The ionospheric total electron content (TEC) is the total number of free electrons along a signal propagation path in a cross section of one square meter, and the ionospheric delay error of the signal from the global navigation satellite system (GNSS) is proportional to the value of TEC. The variation of the ionospheric TEC can also be used to study the variations in space weather. In this study, a new ionospheric TEC model over China based on the bidirectional long short‐term memory (bi‐LSTM) method and long‐term ground‐based observations at 257 GNSS stations from the Crustal Movement Observation Network of China was developed and subsequently validated. The main reason for the selection of the bi‐LSTM model is for its consideration of the sequence information in both forward and backward directions. The prediction results of the new model show that in comparison with that of three other models, including the artificial neural network, LSTM, and traditional IRI‐2016 models, the new model is the best performer. Furthermore, the bi‐LSTM model also successfully captures the diurnal and seasonal variations of the ionospheric TEC and the TEC variations under geomagnetic storm conditions. Key Points: The bidirectional long short‐term memory (bi‐LSTM) method is adopted to predict the ionospheric total electron content maps over China using long‐term ground‐based global positioning system observations from the Crustal Movement Observation Network of ChinaThe bi‐LSTM‐based model outperforms the IRI‐2016, artificial neural network and long short‐term memory‐based modelsThe bi‐LSTM‐based model can predict the ionospheric response during geomagnetic storm periods, such as the 4–7 November 2021 G3 storm period [ABSTRACT FROM AUTHOR]

The quality of the zenith hydrostatic delay (ZHD) could significantly affect the accuracy of the zenith wet delay (ZWD) of the Global Navigation Satellite System (GNSS) signal, and from the ZWD precipitable water vapor (PWV) can be obtained. The ZHD is usually obtained from a standard model – a function of surface pressure at the GNSS station. When PWV is retrieved from the GNSS stations that are not equipped with dedicated meteorological sensors for surface pressure measurements, blind models, e.g., the global pressure and temperature (GPT) models, are commonly used to determine the pressures for these GNSS stations. Due to the limited accuracies of the GPT models, the ZHD obtained from the model-derived pressure value is also of low accuracy, especially in mid- and high-latitude regions. To address this issue, a new ZHD model, named GZHD, was investigated for real-time retrieval of GNSS-PWV in this study. The ratio of the ZHD to the zenith total delay (ZTD) was first calculated using sounding data from 505 globally distributed radiosonde stations selected from the stations that had over 5000 samples. It was found that the temporal variation in the ratio was dominated by the annual and semiannual components, and the amplitude of the annual variation was dependent upon the geographical location of the station. Based on the relationship between the ZHD and ZTD, the new model, GZHD, was developed using the back propagation artificial neural network (BP-ANN) method which took the ZTD as an input variable. The 20-year (2000–2019) radiosonde data at 558 global stations and the 9-year (2006–2014) COSMIC-1 (Constellation Observing System for Meteorology, Ionosphere, and Climate) data, which were also globally distributed, were used as the training samples of the new model. The GZHD model was evaluated using two sets of references: the integrated ZHD obtained from sounding data and ERA5 reanalysis data. The performance of the new model was also compared with GPT3, the latest version. Results showed the new model outperformed GPT3, especially in mid- and high-latitude regions. When radiosonde-derived ZHD was used as the reference, the accuracy, which was measured by the root mean square error (RMSE) of the samples, of the GZHD-derived ZHD was about 21 % better than the GTP3-derived ones. When ERA5-derived ZHD was used as the reference, the accuracy of the GZHD-derived ZHD was about 30 % better than GPT3-derived ZHD. In addition, the real-time PWV derived from 41 GNSS stations resulting from GZHD-derived ZHD was also evaluated, and the result indicated that the accuracy of the PWV was improved by 21 %. [ABSTRACT FROM AUTHOR]

An artificial neural network (ANN) method for the modeling of global topside ionospheric vertical scale height (VSH) using electron density profiles retrieved from Global Navigation Satellite Systems radio occultation (RO) data is proposed in this study. The data for this study are 80,124 VSHs derived from the events randomly selected from 9 years of Constellation Observing System for Meteorology, Ionosphere, and Climate RO measurements and 144,530 VSHs derived from the events randomly selected from 16 years of topside sounder measurements of both Aluoette‐1/2 and ISIS‐1/2 satellites during 1962–1978 are used for comparison. VSHs from the International Reference Ionosphere are also used for the comparison. Results showed that: (1) the median of the relative residuals of the new ANN regression approach/model (which was based on RO measurements) was 8.5% less than that of the traditional approach/model (which was based on the topside sounder data); (2) the median of the relative residuals of the ANN model when longitude was used as a variable was 1.1% less than the one without longitude; and substantial error in the polar region was shown to be mitigated by taking the variable longitude into consideration; (3) compared to International Reference Ionosphere, the accuracy of the new ANN model was improved by around 14%; (4) the new ANN model outperforms the traditional base vector‐based least squares model by around 10% when incoherent scatter radar measurements are used as a reference; and (5) the characteristics of global VSHs generated from the new model during geomagnetic storms better agree with measurements than that of the base vector‐based least squares. Key Points: A new approach for vertical scale height modeling from ionospheric radio occultation data using artificial neural network is proposedThe new approach significantly outperforms the traditional model in accuracyThe new approach agrees with the characteristic of VSH in equatorial region better than traditional approach during geomagnetic storm times [ABSTRACT FROM AUTHOR]

Inertial navigation is a crucial part of vehicle navigation systems in complex and covert surroundings. To address the low accuracy of vehicle inertial navigation in multifaced and covert surroundings, in this study, we proposed an inertial navigation error estimation based on an adaptive neuro fuzzy inference system (ANFIS) which can quickly and accurately output the position error of a vehicle end-to-end. The new system was tested using both single-sequence and multi-sequence data collected from a vehicle by the KITTI dataset. The results were compared with an inertial navigation system (INS) position solution method, artificial neural networks (ANNs) method, and a long short-term memory (LSTM) method. Test results indicated that the accumulative position errors in single sequence and multi-sequences experiments decreased from 9.83% and 4.14% to 0.45% and 0.61% by using ANFIS, respectively, which were significantly less than those of the other three approaches. This result suggests that the ANFIS can considerably improve the positioning accuracy of inertial navigation, which has significance for vehicle inertial navigation in complex and covert surroundings. [ABSTRACT FROM AUTHOR]

Mapping the ionosphere over low-latitude regions with a high accuracy is a challenging task due to the complex nature of the ionospheric structure. In this study, the artificial neural network (ANN) technique was used to investigate the determination of the total electron content (TEC) in low latitude regions using measurements from 187 ground-based International global navigation satellite system (GNSS) Service (IGS) stations and the Constellation Observing System for Meteorology, Ionosphere, and Climate (COSMIC-2) mission in the period from 1 October 2019 to 30 September 2021. To reduce the systematic discrepancies between the space-borne and ground-based observational systems, the ANN technique was also utilized to calibrate the COSMIC-2 derived TECs to the ground level. The RMSE of the calibrated COSMIC-2 TECs was 1.78 TECU. This, in comparison with the RMSE value of 4.10 TECU for the uncalibrated COSMIC-2 TECs, demonstrated 57% improvement. It is found that the performance of the new model was strongly associated with the value of TEC and low-latitude ionospheric structure, such as the equatorial ionization anomaly (EIA). Compared with the IRI-2016 model, the Technical University of Catalonia (UPC) rapid global ionospheric maps (GIMs) (UQRG), the Center for Orbit Determination in Europe (CODE) final GIMs (CODG), and the Chinese Academy of Sciences (CAS) final GIMs (CASG), the new model outperformed the IRI-2016 model and was competitive with the GIMs. All results suggest that the new model developed using both ground-based and space-borne measurements together with the ANN technique can model the ionospheric structure, such as the EIA. Therefore, the new model developed may become a good reference for the studies of the structure and variation of the ionosphere over low latitudes. [ABSTRACT FROM AUTHOR]

The global ionosphere map (GIM) is not capable of serving precise positioning and navigation for single frequency receivers in Australia due to sparse International GNSS Service (IGS) stations located in the vast land. This study proposes an approach to represent Australian total electron content (TEC) using the spherical cap harmonic analysis (SCHA) and artificial neural network (ANN). The new Australian TEC maps are released with an interval of 15 min for longitude and latitude in 0.5° × 0.5°. The validation results show that the Australian Ionospheric Maps (AIMs) well represent the hourly and seasonally ionospheric electrodynamic features over the Australian continent; the accuracy of the AIMs improves remarkably compared to the GIM and the model built only by the SCHA. The residual of the AIM is inversely proportional to the level of solar radiation. During the equinoxes and solstices in a solar minimum year, the residuals are 2.16, 1.57, 1.68, and 1.98 total electron content units (TECUs, 1 TECU = 1016 electron/m2), respectively. Furthermore, the AIM has a strong capability in capturing the adequate electrodynamic evolutions of the traveling ionospheric disturbances under severe geomagnetic storms. The results demonstrate that the ANN-aided SCHA method is an effective approach for mapping and investigating the TEC maps over Australia. [ABSTRACT FROM AUTHOR]

The ionospheric delay is of paramount importance to radio communication, satellite navigation and positioning. It is necessary to predict high-accuracy ionospheric peak parameters for single frequency receivers. In this study, the state-of-the-art artificial neural network (ANN) technique optimized by the genetic algorithm is used to develop global ionospheric models for predicting foF2 and hmF2. The models are based on long-term multiple measurements including ionospheric peak frequency model (GIPFM) and global ionospheric peak height model (GIPHM). Predictions of the GIPFM and GIPHM are compared with the International Reference Ionosphere (IRI) model in 2009 and 2013 respectively. This comparison shows that the root-mean-square errors (RMSEs) of GIPFM are 0.82 MHz and 0.71 MHz in 2013 and 2009, respectively. This result is about 20%–35% lower than that of IRI. Additionally, the corresponding hmF2 median errors of GIPHM are 20% to 30% smaller than that of IRI. Furthermore, the ANN models present a good capability to capture the global or regional ionospheric spatial-temporal characteristics, e.g., the equatorial ionization anomaly and Weddell Sea anomaly. The study shows that the ANN-based model has a better agreement to reference value than the IRI model, not only along the Greenwich meridian, but also on a global scale. The approach proposed in this study has the potential to be a new three-dimensional electron density model combined with the inclusion of the upcoming Constellation Observing System for Meteorology, Ionosphere and Climate (COSMIC-2) data. [ABSTRACT FROM AUTHOR]

• There were remarkable discrepancies between COSMIC and ionosonde with a maximum amplitude of 25%. • The remarkable discrepancies are dependent on universal time, geographic latitude, and season. • Ionospheric model applied by the method improves significantly in accuracy and physical features. There are remarkable ionospheric discrepancies between space-borne (COSMIC) measurements and ground-based (ionosonde) observations, the discrepancies could decrease the accuracies of the ionospheric model developed by multi-source data seriously. To reduce the discrepancies between two observational systems, the peak frequency (foF2) and peak height (hmF2) derived from the COSMIC and ionosonde data are used to develop the ionospheric models by an artificial neural network (ANN) method, respectively. The averaged root-mean-square errors (RMSEs) of COSPF (COSMIC peak frequency model), COSPH (COSMIC peak height model), IONOPF (Ionosonde peak frequency model) and IONOPH (Ionosonde peak height model) are 0.58 MHz, 19.59 km, 0.92 MHz and 23.40 km, respectively. The results indicate that the discrepancies between these models are dependent on universal time, geographic latitude and seasons. The peak frequencies measured by COSMIC are generally larger than ionosonde's observations in the nighttime or middle-latitudes with the amplitude of lower than 25%, while the averaged peak height derived from COSMIC is smaller than ionosonde's data in the polar regions. The differences between ANN-based maps and references show that the discrepancies between two ionospheric detecting techniques are proportional to the intensity of solar radiation. Besides, a new method based on the ANN technique is proposed to reduce the discrepancies for improving ionospheric models developed by multiple measurements, the results indicate that the RMSEs of ANN models optimized by the method are 14–25% lower than the models without the application of the method. Furthermore, the ionospheric model built by the multiple measurements with the application of the method is more powerful in capturing the ionospheric dynamic physics features, such as equatorial ionization, Weddell Sea, mid-latitude summer nighttime and winter anomalies. In conclusion, the new method is significant in improving the accuracy and physical characteristics of an ionospheric model based on multi-source observations. [ABSTRACT FROM AUTHOR]