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.
In recent years, transformer has been widely used in natural language processing (NLP) and computer vision (CV). Comparatively, forecasting image time sequences using transformer has received less attention. In this paper, we propose the conv-attentional image time sequence transformer (CAiTST), a transformer-based image time sequences prediction model equipped with convolutional networks and an attentional mechanism. Specifically, we employ CAiTST to forecast the International GNSS Service (IGS) global total electron content (TEC) maps. The IGS TEC maps from 2005 to 2017 (except 2014) are divided into the training dataset (90% of total) and validation dataset (10% of total), and TEC maps in 2014 (high solar activity year) and 2018 (low solar activity year) are used to test the performance of CAiTST. The input of CAiTST is presented as one day’s 12 TEC maps (time resolution is 2 h), and the output is the next day’s 12 TEC maps. We compare the results of CAiTST with those of the 1-day Center for Orbit Determination in Europe (CODE) prediction model. The root mean square errors (RMSEs) from CAiTST with respect to the IGS TEC maps are 4.29 and 1.41 TECU in 2014 and 2018, respectively, while the RMSEs of the 1-day CODE prediction model are 4.71 and 1.57 TECU. The results illustrate CAiTST performs better than the 1-day CODE prediction model both in high and low solar activity years. The CAiTST model has less accuracy in the equatorial ionization anomaly (EIA) region but can roughly predict the features and locations of EIA. Additionally, due to the input only including past TEC maps, CAiTST performs poorly during magnetic storms. Our study shows that the transformer model and its unique attention mechanism are very suitable for images of a time sequence forecast, such as the prediction of ionospheric TEC map sequences.
[1] The basic configuration of the Wuhan MST (mesosphere-stratosphere-troposphere) radar, which was designed and constructed by the School of Electronic Information, Wuhan University, is preliminarily described in this paper. The Wuhan MST radar operates at very high frequency (VHF) band (53.8 MHz) by observing the real-time characteristics of turbulence and the wind field vector in the height range of 3.5-90 km (not including 25-60 km) with high temporal and height resolutions. This all-solid-state, all-coherent pulse Doppler radar is China's first independent development of an MST radar focusing on atmospheric observation. The subsystems of the Wuhan MST radar include an antenna system, a feeder line system, all-solid-state radar transmitters, digital receivers, a beam control system, a signal processing system, a data processing system, a product generation system, and a user terminal. Advanced radar technologies are used, including highly reliable all-solid-state transmitters, low-noise large dynamic range digital receivers, an active phased array, high-speed digital signal processing, and real-time graphic terminals. This paper describes the design and implementation of the radar. Preliminary online wind measurements and results of the comparison to simultaneous observations by a GPS rawinsonde are presented as well.
This paper briefly reviews ionospheric irregularities that occur in the E and F regions at mid‐latitudes. Sporadic E (ES) is a common ionospheric irregularity phenomenon that is first noticed in the E layer. ES mainly appears during daytime in summer hemispheres, and is formed primarily from neutral wind shear in the mesosphere and lower thermosphere (MLT) region. Field‐aligned irregularity (FAI) in the E region is also observed by Very High Frequency (VHF) radar in mid‐latitude regions. FAI frequently occurs after sunset in summer hemispheres, and spectrum features of E region FAI echoes suggest that type‐2 irregularity is dominant in the nighttime ionosphere. A close relationship between ES and E region FAI implies that ES may be a possible source of E region FAI in the nighttime ionosphere. Strong neutral wind shear, steep ES plasma density gradient, and a polarized electric field are the significant factors affecting the formation of E region FAI. At mid‐latitudes, joint observational experiments including ionosonde, VHF radar, Global Positioning System (GPS) stations, and all‐sky optical images have revealed strong connections across different scales of ionospheric irregularities in the nighttime F region, such as spread F (SF), medium‐scale traveling ionospheric disturbances (MSTID), and F region FAI. Observations suggest that different scales of ionospheric irregularities are generally attributed to the Perkins instability and subsequently excited gradient drift instability. Nighttime MSTID can further evolve into small‐scale structures through a nonlinear cascade process when a steep plasma density gradient exists at the bottom of the F region. In addition, the effect of ionospheric electrodynamic coupling processes, including ionospheric E‐F coupling and inter‐hemispheric coupling on the generation of ionospheric irregularities, becomes more prominent due to the significant dip angle and equipotentiality of magnetic field lines in the mid‐latitude ionosphere. Polarized electric fields can map to different ionospheric regions and excite plasma instabilities which form ionospheric irregularities. Nevertheless, the mapping efficiency of a polarized electric field depends on the ionospheric background and spatial scale of the field.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.