Long-Term Evolution of Solar Activity and Prediction of the Following Solar Cycles
First published: 2024
Brief summary
Surveys cross-disciplinary methods -- including machine learning and neural networks borrowed from computer science -- now used to predict future solar activity cycles, fitting a long-term 'century cycle' function against which individual 11-year cycles are compared.
Article
Long-Term Evolution of Solar Activity and Prediction of the Following Solar Cycles is a preprint published by arXiv in 2024. It surveys cross-disciplinary methods -- including machine learning and neural networks borrowed from computer science -- now used to predict future solar activity cycles, fitting a long-term 'century cycle' function against which individual 11-year cycles are compared.
The analysis focuses on 11-year solar cycle nested within a longer 'century cycle'. It also considers explicitly interdisciplinary methodology (machine learning, similarity theory) applied to solar cycle 25/26 prediction. This gives the cycle claim a specific numerical and evidential setting rather than presenting periodicity only as a visual impression.
Cross-disciplinary approaches such as machine learning and neural networks for solar cycle prediction are also very popular research directions; the authors confirm the existence and long-term evolution trend of the solar century cycle, and predict current and upcoming solar cycles using it. The interpretation is strongest when the same cycle definition and statistical standard can be applied consistently across the different fields being compared.
For cycles researchers, the article brings together solar cycle prediction, machine learning, century cycle, sunspot forecasting. It is relevant to comparative cycles research because it links periodic behaviour across disciplines and encourages common methods for testing recurrence, phase and causation.
Because it is a preprint, the work should be read alongside later peer-reviewed publications and independent replications. It remains useful because the proposed cycle, dataset and analytical approach are stated clearly enough to be scrutinised.
Source details and credits
- Source / publisher: arXiv
- Source type: Preprint
- URL type: WWW
- Credits: arXiv
- URL: https://arxiv.org/html/2402.13173v1