Deep Learning Forecasting of IRI-2020 Total Electron Content Residuals over China and Adjacent Regions During the Solar Cycle 25 Maximum: Roles of Anchored Output and the Background Field

Deep learning has rarely been used to forecast corrections of the International Reference Ionosphere (IRI) total electron content (TEC). We forecast the difference between the Center for Orbit Determination in Europe (CODE) global ionospheric maps and IRI-2020 TEC (the residual) over China and adjacent regions at 1–24 h lead times with four deep neural networks, trained on 2008–2019, validated on 2020–2022 and tested during the Solar Cycle 25 maximum (2023–2025). Reusing the residual observed one day earlier lowers the root mean square error (RMSE) of IRI by 37.3%. At 24 h, direct-output networks do not significantly beat this naive forecast, whereas all four networks anchored to it, predicting only the day-to-day change, beat it significantly—the patch time series Transformer (PatchTST) by 12.4%. IRI then contributes only its day-to-day increment, which helps only if the regression coefficient β of the observed TEC change onto this increment exceeds 1/2. With IRI driven by indices observed at the target time, β is 0.23 in quiet periods but 0.90 for disturbance storm time (Dst) index ≤ −50 nT. Without IRI, anchored PatchTST beats the CODE 1-day predicted maps (C1PG) by 11.1%, a comparison favored by its final-map inputs. Naive observational forecasts should be routine benchmarks; β indicates when a background field adds predictive value.

Authors

Institutions

Publication Details

Journal
Atmosphere
Published
2026-11-20
DOI
https://doi.org/10.3390/atmos17111151
Primary Topic
Ionosphere and magnetosphere dynamics
Type
article
Field-Weighted Citation Impact
0.00

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Deep Learning Forecasting of IRI-2020 Total Electron Content Residuals over China and Adjacent Regions During the Solar Cycle 25 Maximum: Roles of Anchored Output and the Background Field

Xiangyu Tian, Ren Wang, Xiaoming Li, Tingchen JIANG et al.
2 links
Atmosphere
Ionosphere and magnetosphere dynamics
article

Deep Learning Forecasting of IRI-2020 Total Electron Content Residuals over China and Adjacent Regions During the Solar Cycle 25 Maximum: Roles of Anchored Output and the Background Field

Xiangyu Tian, Ren Wang, Xiaoming Li, Tingchen JIANG, Qiyong Zhang, Ying Li
article en

Abstract

Deep learning has rarely been used to forecast corrections of the International Reference Ionosphere (IRI) total electron content (TEC). We forecast the difference between the Center for Orbit Determination in Europe (CODE) global ionospheric maps and IRI-2020 TEC (the residual) over China and adjacent regions at 1–24 h lead times with four deep neural networks, trained on 2008–2019, validated on 2020–2022 and tested during the Solar Cycle 25 maximum (2023–2025). Reusing the residual observed one day earlier lowers the root mean square error (RMSE) of IRI by 37.3%. At 24 h, direct-output networks do not significantly beat this naive forecast, whereas all four networks anchored to it, predicting only the day-to-day change, beat it significantly—the patch time series Transformer (PatchTST) by 12.4%. IRI then contributes only its day-to-day increment, which helps only if the regression coefficient β of the observed TEC change onto this increment exceeds 1/2. With IRI driven by indices observed at the target time, β is 0.23 in quiet periods but 0.90 for disturbance storm time (Dst) index ≤ −50 nT. Without IRI, anchored PatchTST beats the CODE 1-day predicted maps (C1PG) by 11.1%, a comparison favored by its final-map inputs. Naive observational forecasts should be routine benchmarks; β indicates when a background field adds predictive value.

AtmosphereVol. 17(11)
Jiangsu Ocean University (CN), Chuzhou University (CN)
National Natural Science Foundation of China
Ionosphere and magnetosphere dynamics
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon
Deep Learning Forecasting of IRI-2020 Total Electron Content Residuals over China and Adjacent Regions During the Solar Cycle 25 Maximum: Roles of Anchored Output and the Background Field — Xiangyu Tian, Ren Wang, et al. · Atmosphere (2026) | TGRS Research Map | TGRS