Probabilistic Solar Proxy Forecasting With Neural Network Ensembles
importance 5/10
ai assisted
Ionosphere and magnetosphere dynamics space weather stage: research
Problem
Forecasting the F10.7cm solar radio flux proxy, which drives thermosphere density forecasts affecting low-Earth-orbit objects through atmospheric drag.
Why it matters
Thermosphere density forecast errors affect drag predictions and LEO satellite operations.
What the AI did
Neural network ensembles of MLPs and LSTMs forecast F10.7cm from historical values only, testing backwards averaging, lookback, multi-step and dynamic forecasting.
Results
Ensemble methods improved on persistence and the operational SET model; numeric values not stated in source
Impact
Ensemble neural networks outperformed the operational linear SET forecasts of F10.7cm.
Record
| Venue | Space Weather |
|---|---|
| Published | 2023 |
| Work type | article |
| Authors | Joshua D. Daniell, Piyush M. Mehta |
| Citations | 12 (OpenAlex, at import time) |
| References | 32 |
| Model or method | Neural network ensembles (MLPs and LSTMs) |
| Organization | not stated in source |
| Primary source | https://doi.org/10.1029/2023sw003675 |
| Open access | gold |
| Keywords | space weather, F10.7cm, neural network ensembles, LSTM, MLP, forecasting |
Importance rating
5
real but narrower advance
Thermosphere density errors affect LEO objects via drag; operationally relevant forecasting improvement, but no scale stated.
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
|