Comparison of neural network and support vector machine methods for Kp forecasting
Problem
Near-real-time forecasting of the Kp geomagnetic activity index was addressed by comparing four forecast models based on neural networks and support vector machines using solar wind data and preliminary Kp values.
Why it matters
Kp indexes geomagnetic activity and accurate forecasts are needed for space-weather monitoring; broader stakes are not stated in source.
What the AI did
Neural network and support vector machine models were built and compared for Kp forecasting; the neural network using solar wind data plus preliminary Kp values performed best.
Results
Best model (NN with solar wind and preliminary Kp): correlation coefficient 0.93, RMS error 0.48, mean absolute error 0.61.
Impact
Peer-reviewed comparison showing the neural network model outperformed the other three tested models.
Record
| Venue | Journal of Geophysical Research Space Physics |
|---|---|
| Published | 2013 |
| Work type | article |
| Authors | Eun‐Young Ji, Yong‐Jae Moon, Jongyeob Park, Jin‐Yi Lee, Dong‐Hun Lee |
| Citations | 45 (OpenAlex, at import time) |
| References | 35 |
| Model or method | neural network and support vector machine |
| Organization | not stated in source |
| Primary source | https://doi.org/10.1002/jgra.50500 |
| Open access | bronze |
| Keywords | Kp index, geomagnetic activity, neural network, support vector machine, space weather, forecasting |
Importance rating
real but narrower advance
Kp forecasting supports space-weather monitoring; abstract presents a model comparison without stating affected populations, infrastructure, or economic scale.
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
|