Solar Flare Forecast Using 3D Convolutional Neural Networks
importance 6/10
ai assisted
Solar and Space Plasma Dynamics space weather forecasting stage: research
Problem
Forecasting whether an active region on the Sun will erupt a C- or M-class solar flare within the next 24 hours.
Why it matters
Solar flares severely influence space weather, endangering satellites, astronauts and power grids.
What the AI did
Two 3D convolutional neural networks were trained on magnetogram sequences of active-region magnetic fields to forecast flare eruptions.
Results
TSS scores of 0.756 (≥C-class) and 0.826 (≥M-class) for 24-hour forecasts.
Impact
The models achieved superior forecast performance on stated TSS metrics, per the abstract.
Record
| Venue | The Astrophysical Journal |
|---|---|
| Published | 2022 |
| Work type | article |
| Authors | Pengchao Sun, Wei Dai, Weiqi Ding, Song Feng, Yanmei Cui, Bo Liang, Ze-yin Dong, Yunfei Yang |
| Citations | 25 (OpenAlex, at import time) |
| References | 50 |
| Model or method | 3D CNN |
| Organization | not stated in source |
| Primary source | https://doi.org/10.3847/1538-4357/ac9e53 |
| Open access | gold |
| Keywords | solar flare, forecasting, 3D CNN, space weather, magnetogram, active region |
Importance rating
6
significant — thousands to millions affected
Solar flares severely influence space weather, endangering satellites, astronauts and power grids; 24-hour forecasts support protection of these systems.
More in Physics & Astronomy
| # | Paper | Year | Citations | Importance |
|---|---|---|---|---|
| 1 | Magnetic control of tokamak plasmas through deep reinforcement learning | 2022 | 739 |
7
|
| 2 | Solving the quantum many-body problem with artificial neural networks | 2017 | 2,205 |
7
|
| 3 | Learning high-accuracy error decoding for quantum processors | 2024 | 90 |
7
|
| 4 | Optimizing Quantum Error Correction Codes with Reinforcement Learning | 2019 | 158 |
7
|
| 5 | Machine-learning-assisted correction of correlated qubit errors in a topological code | 2018 | 141 |
7
|