Estimation of 3D Ionospheric Electron-Density Distribution Specialized for the Korean Peninsula Using a U-Net Super-Resolution CNN
Bibliographic record
Abstract
Accurate knowledge of the three-dimensional ionospheric electron-density distribution is essential for reliable radio-wave propagation modeling, yet global empirical models (e.g., IRI-2020, NeQuick2) fail to capture local and short-term variability. In this work, we propose a U-Net–based super-resolution CNN (SRCNN) that reconstructs a regionally specialized 3D electron-density distribution over the Korean Peninsula from sparse, high-fidelity input profiles. These input profiles are generated for two sites (Icheon and Jeju) by combining direct ionosonde measurements for the bottomside with an ionosonde-corrected IRI-2020 model for the topside. The AI model was trained on electron-density distributions produced by the IRI-2020 model. The proposed model demonstrates significant improvements over the standard IRI model, showcasing its stability across all solar activity levels. Most notably, under solar-maximum conditions, the root mean square relative error (RMSRE) was drastically reduced at Icheon (from 367.23% to 16.04%) and Jeju (from 538.12% to 9.68%). The model also consistently improved other key metrics, such as the F2-peak altitude error and the Pearson correlation coefficient (r> 0.99), proving its robust performance. The proposed approach can contribute to improving ionospheric error correction and signal quality in precise GNSS positioning, space surveillance radar, and satellite communication systems.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".