Prediction of Solar Cycles 26 and 27 Based on LSTM-FCN
NEW ASTRONOMY(2025)
China Three Gorges Univ
Abstract
Predicting solar activity changes is crucial for Earth’s climate, communication systems, and aerospace technology. This study employs the Long Short-Term Memory Fully Convolutional Network (LSTM-FCN) deep learning method to predict the amplitudes and peak times of Solar Cycles (SCs) 26 and 27 for both the entire solar disk and the northern and southern hemispheres. The experimental data comprises the monthly mean total Sunspot Number (SSN) data and the monthly mean northern and southern Hemispheric Sunspot Number (HSN) data, provided by the World Data Center - Sunspot Index and Long-term Solar Observations (WDC-SILSO). The experimental process tested the Input-Output Window Ratio (IOWR) from 4:1 to 14:1, and the results indicate that when the IOWR is 10:1, the normalized Relative RMSE (RRMSE) is minimized at 0.078. According to the prediction, SC 26 is expected to peak in June 2034 with an amplitude of 194.4, and SC 27 is expected to peak in July 2045 with an amplitude of 244.2. It was also found that SC 26 and SC 27 have northern and southern hemisphere asymmetry. This study demonstrates the potential application of the LSTM-FCN deep learning method in forecasting SCs, providing a new tool and approach for solar physics research.
MoreTranslated text
Key words
Solar activity,Solar cycle predict,LSTM-FCN,Sunspot number
求助PDF
上传PDF
View via Publisher
AI Read Science
AI Summary
AI Summary is the key point extracted automatically understanding the full text of the paper, including the background, methods, results, conclusions, icons and other key content, so that you can get the outline of the paper at a glance.
Example
Background
Key content
Introduction
Methods
Results
Related work
Fund
Key content
- Pretraining has recently greatly promoted the development of natural language processing (NLP)
- We show that M6 outperforms the baselines in multimodal downstream tasks, and the large M6 with 10 parameters can reach a better performance
- We propose a method called M6 that is able to process information of multiple modalities and perform both single-modal and cross-modal understanding and generation
- The model is scaled to large model with 10 billion parameters with sophisticated deployment, and the 10 -parameter M6-large is the largest pretrained model in Chinese
- Experimental results show that our proposed M6 outperforms the baseline in a number of downstream tasks concerning both single modality and multiple modalities We will continue the pretraining of extremely large models by increasing data to explore the limit of its performance
Upload PDF to Generate Summary
Must-Reading Tree
Example

Generate MRT to find the research sequence of this paper
Data Disclaimer
The page data are from open Internet sources, cooperative publishers and automatic analysis results through AI technology. We do not make any commitments and guarantees for the validity, accuracy, correctness, reliability, completeness and timeliness of the page data. If you have any questions, please contact us by email: report@aminer.cn
Chat Paper
Summary is being generated by the instructions you defined