Neural network based model for global Total Electron Content forecasting

Claudio Cesaroni, Luca Spogli, Àngela Aragón‐Ángel, Michele Fiocca, Varuliantor Dear, Giorgiana De Franceschi, Vincenzo Romano

Journal of Space Weather and Space Climate 2020 article cited by 92

Source Open-access PDF More in Physics & Astronomy

importance 5/10 ai assisted Ionosphere and magnetosphere dynamics space weather forecasting stage: research

Problem

Forecasting the global Total Electron Content (TEC) of the ionosphere 24 hours in advance, including during disturbed geomagnetic conditions.

Why it matters

Ionospheric conditions affect systems that rely on satellite signals, so accurate forecasts during disturbed periods are needed.

What the AI did

A nonlinear autoregressive neural network with external input (NARX) forecast TEC at selected map grid points using current and forecast geomagnetic conditions, extended globally via the NeQuick2 model with an optimized effective sunspot number.

Results

not stated in source

Impact

The approach was extensively tested against other TEC map products, but no quantitative performance figures appear in the abstract.

Record

Venue	Journal of Space Weather and Space Climate
Published	2020
Work type	article
Authors	Claudio Cesaroni, Luca Spogli, Àngela Aragón‐Ángel, Michele Fiocca, Varuliantor Dear, Giorgiana De Franceschi, Vincenzo Romano
Citations	92 (OpenAlex, at import time)
References	51
Model or method	NARX neural network with external input, fed into NeQuick2
Organization	not stated in source
Primary source	https://doi.org/10.1051/swsc/2020013
Open access	gold
Keywords	TEC forecasting, NARX, neural network, ionosphere, space weather, GNSS

Importance rating

5 / 10

real but narrower advance

Ionospheric forecasts matter for satellite-signal users, but abstract gives no scale or impact figures; benefit is significant yet specialized.

Basis: inferred. Judged from the source text, which gives no explicit scale. Stated scale: not stated in source. Method and limits.

More in Physics & Astronomy

#	Paper	Year	Citations	Importance
1	Magnetic control of tokamak plasmas through deep reinforcement learning Jonas Degrave, Federico Felici, Jonas Buchli, Michael Neunert, Brendan...	2022	739	7
2	Solving the quantum many-body problem with artificial neural networks Giuseppe Carleo, Matthias Troyer	2017	2,205	7
3	Learning high-accuracy error decoding for quantum processors Johannes Bausch, Andrew Senior, Francisco J. H. Heras, Thomas Edlich,...	2024	90	7
4	Optimizing Quantum Error Correction Codes with Reinforcement Learning Hendrik Poulsen Nautrup, Nicolas Delfosse, Vedran Dunjko, Hans J. Brie...	2019	158	7
5	Machine-learning-assisted correction of correlated qubit errors in a topological code Paul Baireuther, Thomas E. O’Brien, Brian Tarasinski, C. W. J. Beenakk...	2018	141	7