Forecasting the <i>Dst</i> index using a swarm‐optimized neural network
importance 5/10
ai assisted
Ionosphere and magnetosphere dynamics space weather stage: research
Problem
Forecasting the disturbance storm time (Dst) index, a measure of geomagnetic disturbance, 1 to 6 hours ahead.
Why it matters
Short-term Dst forecasting is a space weather prediction task addressed with 26 years of hourly data.
What the AI did
A hybrid ANN+PSO technique used particle swarm optimization to update neural-network weights, forecasting Dst from past values 1-6 hours ahead.
Results
Trained/tested on 233,760 hourly data points; described as powerful for t+1 to t+3 forecasting; RMSE values truncated in abstract.
Impact
Demonstrated a hybrid swarm-optimized neural network for short-term Dst forecasting.
Record
| Venue | Space Weather |
|---|---|
| Published | 2017 |
| Work type | article |
| Authors | Juan A. Lazzús, Pedro Vega, P. Rojas, Ignacio Salfate |
| Citations | 62 (OpenAlex, at import time) |
| References | 115 |
| Model or method | Artificial neural network optimized by particle swarm optimization (ANN+PSO) |
| Organization | not stated in source |
| Primary source | https://doi.org/10.1002/2017sw001608 |
| Open access | closed |
| Keywords | Dst index, space weather, neural network, particle swarm optimization, forecasting |
Importance rating
5
real but narrower advance
Dst forecasting is a space weather prediction task; abstract gives dataset size and accuracy but no statement of who or what benefits or at what 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
|