Validation of Ionospheric Modeled TEC in the Equatorial Ionosphere During the 2013 March and 2021 November Geomagnetic Storms

Self Cite

New, open access tools have been developed to validate ionospheric models in terms of technologically relevant metrics. These are ionospheric errors on GPS 3D position, HF ham radio communications, and peak F‐region density. To demonstrate these tools, we have used output from Sami is Another Model of the Ionosphere (SAMI3) driven by high‐latitude electric potentials derived from Active Magnetosphere and Planetary Electrodynamics Response Experiment, covering the first available month of operation using Iridium‐NEXT data (March 2019). Output of this model is now available for visualization and download via https://sami3.jhuapl.edu. The GPS test indicates SAMI3 reduces ionospheric errors on 3D position solutions from 1.9 m with no model to 1.6 m on average (maximum error: 14.2 m without correction, 13.9 m with correction). SAMI3 predicts 55.5% of reported amateur radio links between 2–30 MHz and 500–2,000 km. Autoscaled and then machine learning “cleaned” Digisonde NmF2 data indicate a 1.0 × 1011 el. m3 median positive bias in SAMI3 (equivalent to a 27% overestimation). The positive NmF2 bias is largest during the daytime, which may explain the relatively good performance in predicting HF links then. The underlying data sources and software used here are publicly available, so that interested groups may apply these tests to other models and time intervals.

Section: Discussionmentioning

confidence: 63%

Validating Ionospheric Models Against Technologically Relevant Metrics

Chartier,

Steele,

Sugar

et al. 2023

Self Cite

“…The objective of this section is to investigate the impact of the E × B velocity term on the inversion of density, velocity, and temperature during the geomagnetic storm. Different from quite solar period on 23 Dec 2019 in previous section, we select a geomagnetic storm event driven by coronal mass ejections, focusing on the SAMI3 simulation data on 4 Nov 2021 (Chou et al, 2023). Therefore, the SAMI3 simulation parameters at time 00 : 00: 00 ∼00 : 15: 00 on 4 Nov 2021 have been chosen as follows: F10.7 A = 87.8024, F10.7 = 90.8000 (every 24 hr), Ap = 94 (every 3 hr), Kp = 6 (every 3 hr).…”

Section: Pinn-sami3 Framework Test During a Geomagnetic Stormmentioning

confidence: 99%

A Novel Ionospheric Inversion Model: PINN‐SAMI3 (Physics Informed Neural Network Based on SAMI3)

Ma,

Fu,

Huba

et al. 2024

Self Cite

Purely data‐driven ionospheric modeling fails to adequately obey fundamental physical laws. To overcome this shortcoming, we propose a novel ionospheric inversion model, Physics‐Informed Neural Network based on fully physical models SAMI3 (PINN‐SAMI3). The model incorporates the governing equations of the ionospheric physical model SAMI3 into the neural network to reconstruct the temporal‐spatial distribution of ionospheric plasma parameters. The objective of this study is to investigate the feasibility of integrating physical models with machine learning for ionospheric modeling. The PINN‐SAMI3 framework enforces physical laws through the multiple ion species of continuity, momentum, temperature equations in the magnetic dipole coordinate system. The simulation results show that if sparse ion densities are used as training data, it is possible to retrieve ionospheric electron densities, ion velocities and ion temperatures, respectively. The optimal physical constraints have been also investigated for different inversion quantities. Furthermore, the impact of incorporating E × B velocity terms on inversion results during the periods of ionospheric calm and geomagnetic storm is analyzed. The PINN‐SAMI3 achieves good inversion results even using sparse data in comparison to the traditional artificial neural networks (ANN). The framework will contribute to advance the future space weather prediction capability with artificial intelligence (AI).

“…An example of a physics‐based data assimilation model is the Whole Atmosphere Model‐Ionosphere Plasmasphere Electrodynamics (WAM‐IPE), which is operated at the National Oceanic and Atmospheric Administration Space Weather Prediction Center. This model utilizes a wealth of ground‐based and space‐based observations, solar activity indices, geomagnetic data, and lower atmospheric forcing (Chou et al., 2023; Fang et al., 2022), making it valuable for characterizing and predicting the behavior of the ionosphere during space weather events. Nonetheless, the complexity and computation time required for the operation of data assimilation models still pose challenges.…”

Section: Introductionmentioning

confidence: 99%

Deep Learning‐Based Regional Ionospheric Total Electron Content Prediction—Long Short‐Term Memory (LSTM) and Convolutional LSTM Approach

Jeong,

Lee,

Kil

et al. 2024

This study evaluates the performance of deep learning approach in the prediction of the ionospheric total electron content (TEC) during magnetically quiet periods. Two deep learning techniques, long short‐term memory (LSTM) and convolutional LSTM (ConvLSTM), are employed to predict TEC values 24 hr ahead in the vicinity of the Korean Peninsula (26.5°–40°N, 121°–134.5°E). The LSTM method predicts TEC at a single point based on time series of data at that point, whereas the ConvLSTM method simultaneously predicts TEC values at multiple points using spatiotemporal distribution of TEC. Both the LSTM and ConvLSTM models are trained using the complete regional TEC maps reconstructed by applying the Deep Convolutional Generative Adversarial Network–Poisson Blending (DCGAN‐PB) method to observed TEC data. The training period spans from 2002 to 2018, and the model performance is evaluated using 2019 data. Our results show that the ConvLSTM method outperforms the LSTM method, generating more reliable TEC maps with smaller root mean square errors when compared to the ground truth (DCGAN‐PB TEC maps). This outcome indicates that deep learning models can improve the prediction accuracy of TEC at a specific point by taking into account spatial information of TEC. We conclude that ConvLSTM is a reliable and efficient approach for the prompt ionospheric prediction.