Applying artificial neural network to the short‐term prediction of electron density structure using GPS occultation data

Zeng, Zhen; Hu, Xiong; Zhang, Xunjie

doi:10.1029/2001gl013656

Cited by 9 publications

(7 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…At the same time, Cander and Lamming (1997) use the multi-layer perceptron to model different ionospheric parameters. Then, in 2002, Zeng et al (2002) used GPS occultation data to build an artificial neural network for short-term prediction of electron density structure. Habarulema et al (2007) developed a NN prediction model for the TEC of the global positioning system over South Africa in 2007.…”

mentioning

confidence: 99%

ED‐ConvLSTM: A Novel Global Ionospheric Total Electron Content Medium‐Term Forecast Model

et al. 2022

View full text Add to dashboard Cite

In this paper, we proposed an innovative encoder‐decoder structure with a convolution long short‐term memory (ED‐ConvLSTM) network to forecast global total electron content (TEC) based on the International GNSS Service (IGS) TEC maps from 2005 to 2018 with 1‐hr time cadence. The ED‐ConvLSTM model is used to forecast TEC maps 1–7 days in advance through iterations. To investigate the model's performance, we compared the model with International Reference Ionosphere (IRI2016) model in 2014 and 2018, and compared the model with 1‐day Beijing University of Aeronautics and Astronautics (BUAA) model in 2018. The results show that our 7‐day ED‐ConvLSTM model (ED‐ConvLSTM model that forecasts 7 days in advance) outperforms IRI2016 in 2014 and 2018, and our 5‐day ED‐ConvLSTM model (ED‐ConvLSTM model that forecasts 5 days in advance) outperforms 1‐day BUAA model. Furthermore, the root mean square error (RMSE) from the 1‐day ED‐ConvLSTM model with respect to the IGS TEC maps decreases by 51.5% and 43%, respectively, in 2014 and 2018 compared with that from IRI2016 model. The RMSE from the 1‐day ED‐ConvLSTM model is 20.3% lower than that from the 1‐day BUAA model in 2018. In addition, our model has the highest RMSE in the Equatorial Ionospheric Anomaly (EIA) region, but can roughly predict the features and locations of EIA. However, the model fails to forecast localized TEC enhancement and the sudden ionospheric response to the geomagnetic storms. Overall, the model shows competitive performance in medium‐term global TEC maps prediction during geomagnetic quiet periods.

show abstract

mentioning

confidence: 99%

ED‐ConvLSTM: A Novel Global Ionospheric Total Electron Content Medium‐Term Forecast Model

et al. 2022

View full text Add to dashboard Cite

show abstract

“…In addition, many research has also achieved good results with few samples. [55][56][57][58] Therefore, we think that 1700 samples are not too many, they can also reflect a certain law of wind field change.…”

Section: B Training Processmentioning

confidence: 99%

A Machine Learning-Based Method for Wind Fields Forecasting Utilizing GNSS Radio Occultation Data

et al. 2022

View full text Add to dashboard Cite

With the development of computer technology and expanding environmental issues, machine learning has received more and more attention in the field of weather forecasting. Global Navigation Satellite System-Radio Occultation(GNSS-RO) technology is a kind of remote sensing technology. This investigation proposes an alternative to numerical weather forecasting model. The new method is based on machine learning utilizing GNSS-RO data to forecast the wind field in the Beijing-Tianjin-Hebei region of China. The dataset including temperature, humidity， pressure， wind speed and direction was obtained by numerical calculation in terms of historical monitoring data in Beijing-Tianjin-Hebei region. Then the models of wind fields forecasting based on machine learning were established with different neural network including Long Short-Term Memory (LSTM), Convolutional Neural Network (CNN) and Deep Neural Networks (DNN). The prediction performance of different models was analyzed. The results demonstrate that LSTM and CNN have better performance on predicting the wind field than Deep Neural Networks. The wind speed error is about 1.4m/s, and the wind direction error is about 30°. Moreover, the time required for neural network to predict a new sample is about 1 second, which is only 0.2% of the prediction time compared with numerical model. Finally, the machine learning model can be used to predict the wind field effectively, with GNSS-RO data as the input in application. This paper pro-vides a new method in sight to use machine learning to forecast the regional wind field utilizing GNSS-RO data. INDEX TERMSWind fields forecasting; machine learning; GNSS-RO; Long Short-Term Memory (LSTM); Convolutional Neural Networks (CNN)

show abstract

“…Zeng et al. (2002) used Global Positioning System (GPS) occultation data to predict the ionospheric electron density. The results showed that the ANN was an effective method for establishing an ionospheric prediction model.…”

Section: Introductionmentioning

confidence: 99%

“…The prediction results proved the promising prospect of artificial neural networks in ionospheric prediction. Zeng et al (2002) used Global Positioning System (GPS) occultation data to predict the ionospheric electron density. The results showed that the ANN was an effective…”

mentioning

confidence: 99%

Global Ionospheric TEC Forecasting for Geomagnetic Storm Time Using a Deep Learning‐Based Multi‐Model Ensemble Method

et al. 2023

View full text Add to dashboard Cite

High-reliable ionospheric prediction information is of great significance for precise positioning and navigation, space weather monitoring, as well as wireless communication (Schunk & Sojka, 1996;Zhang et al., 2022). Many models have been proposed to model the ionosphere and predict its changes. However, the prediction accuracy is limited due to the irregular characteristics and the complicated mechanism of ionospheric variations (Liu et al., 2022;Mcgranaghan et al., 2018). In recent years, the rapidly developed deep learning technique has been steadily applied to ionospheric prediction with an increase in long-term ionospheric observation data (Camporeale, 2019;Ren et al., 2022).Since the mid-1990s, artificial neural networks (ANN), the forerunner of deep learning, provide a new efficient solution for ionospheric modeling and prediction (Joselyn et al., 1993;Oyeyemi et al., 2005). Cander (1998) used different artificial neural networks to simulate and predict the temporal-spatial variations of ionospheric key parameters, such as f0F2 and total electron content (TEC). The prediction results proved the promising prospect of artificial neural networks in ionospheric prediction. Zeng et al. (2002) used Global Positioning System (GPS) occultation data to predict the ionospheric electron density. The results showed that the ANN was an effective

show abstract

Applying artificial neural network to the short‐term prediction of electron density structure using GPS occultation data

Cited by 9 publications

References 8 publications

ED‐ConvLSTM: A Novel Global Ionospheric Total Electron Content Medium‐Term Forecast Model

ED‐ConvLSTM: A Novel Global Ionospheric Total Electron Content Medium‐Term Forecast Model

A Machine Learning-Based Method for Wind Fields Forecasting Utilizing GNSS Radio Occultation Data

Global Ionospheric TEC Forecasting for Geomagnetic Storm Time Using a Deep Learning‐Based Multi‐Model Ensemble Method

Contact Info

Product

Resources

About