A Low‐Latitude Three‐Dimensional Ionospheric Electron Density Model Based on Radio Occultation Data Using Artificial Neural Networks With Prior Knowledge. Issue 1 (17th January 2023)

• Record Type: Journal Article
• Authors: Yang, Ding; Fang, Hanxian
• Is Part Of: Space weather. Volume 21:Issue 1(2023)
• Page Start: n/a
• Page End: n/a
• Publication Date: 2023-01-17
• Subjects: Space environment -- Periodicals; 551.509992
• DOI: 10.1029/2022SW003299
• Languages: English
• ISSNs: 1542-7390

Abstract

Abstract: The accurate estimation of electron density in the ionosphere is crucial for various applications including remote sensing systems, communication, satellite positioning, and navigation. Previous ionospheric models using artificial neural networks (ANN) are only data‐driven, whose effects are entirely affected by observational data. In this paper, we utilize the results of International Reference Ionosphere (IRI)‐2016 as prior knowledge to develop a low‐latitude (30°N–30°S) three‐dimensional ionospheric electron density model using ANN, namely ANN‐IRI, based on COSMIC radio occultation ionospheric profiles during 2006–2020. The prior knowledge helps ANN‐IRI get a better prediction effect and obtain convergence more quickly. The COSMIC data sets above the altitude 150 km are divided into three sets, a training set (2006–2014 and 2018–2020), a validation set (2016), and a test set (2015 and 2017). For the test set, ANN‐IRI shows a good performance for predicting the electron density, better than ANN (without prior knowledge) and IRI‐2016. And ANN‐IRI behaves better during quiet than disturbed times as well as during low solar activity than high solar activity years. In addition, we corrected effectively the error of ANN‐IRI in the lower ionosphere source from COSMIC data based on IRI‐2016 and spline interpolation. Compared with completely independent data sets from incoherent scatter radars (ISRs) and ROCSAT‐1 in situ observations, the electron density predicted by corrected ANN‐IRI exhibits good similarity. Generally, ANN‐IRI behaves better than ANN and IRI‐2016 for predicting electron density. Our work demonstrates a new possibility of applying deep learning methods with prior knowledge to a broader field of geosciences, particularly for problems of prediction. Plain Language Summary: Previous ionospheric models using artificial neural networks (ANN) are only data‐driven, whose effects are entirely affected by observational data. We utilize the results of International Reference Ionosphere (IRI)‐2016 as prior knowledge to develop a low‐latitude (30°N–30°S) three‐dimensional ionospheric electron density model using ANN, namely ANN‐IRI, based on COSMIC radio occultation ionospheric profiles from 2006 to 2020. The prior knowledge helps ANN‐IRI learn from IRI‐2016 and get a better prediction effect. In addition, ANN‐IRI effectively corrects the lower ionosphere source error from COSMIC data. Both quantitative and qualitative results demonstrate that ANN‐IRI performs well in predicting electron density. ANN‐IRI behaves better during quiet than disturbed times as well as during low solar activity than high solar activity years for the test set. Compared with the completely independent data sets from incoherent scatter radars and ROCSAT‐1 in situ observations, ANN‐IRI generally behaves better than ANN and IRI for predicting electron density. Key Points: Artificial neural networks (ANN) with prior knowledge from International Reference Ionosphere (IRI)‐2016 is applied to construct a low‐latitude three‐dimensional ionospheric model based on COSMIC data ANN‐IRI corrects the error in the lower ionosphere source from COSMIC data effectively, based on IRI and spline interpolation Compared with the data sets from IRIs and ROCSAT‐1 in situ observations, the results of ANN‐IRI exhibit good consistency