Prediction of the Sunspot Number with a New Model Based on the Revised Data

Liu, Jinhuo; Zhao, Juan; Lin, Haibo

doi:10.1007/s11207-019-1536-1

Cited by 11 publications

(4 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The autoregressive integrated moving average Model (ARIMA) method is employed by Abdel-Rahman and Marzouk [2] to predict the solar cycle 24. While Liu et al [10] employed a Gaussian function to estimate the solar cycle 24 activity. Du [11] used the value 39 months before the solar minimum to predict the peak of Solar Cycle 25.…”

Section: Related Workmentioning

confidence: 99%

Novel residual hybrid machine learning for solar activity prediction in smart cities

Abdulkadir,

Hasan,

Islam

et al. 2023

Earth Sci Inform

View full text Add to dashboard Cite

Predicting global solar activity is crucial for smart cities, especially space activities, communication industries, and climate change monitoring. The recently developed models to predict solar activity based on stand-alone arti cial intelligence, based on machine and deep learning models, and hybrid models are promising. Yet they may not be effective at capturing simpler linear patterns in the data and often fail to provide reliable predictions due to the computationally expensive and complex. This article proposed a novel residual hybrid machine learning method integrating linear regression machine learning, and deep learning neural networks for solving predictive accuracy in individual machine learning models that reduces complexity. The residual hybrid model leverages the capacities of the support vector machine (SVM) and long short-term memory neural network (LSTM) for hybrid SVM-LSTM model. The performance of the model is evaluated using the correlation coe cient, determination coe cient, rootmean-squared error (RMSE) and mean-absolute error. The simulation results indicated that compared to the SVM-LSTM, the training and testing RMSE of the LSTM is reduced by 76.62% and 71.18%, respectively. It also decreases the training and testing RMSE of the SVM by 77.06% and 71.81%, respectively. The proposed model can be implemented as reliable solution for accurately predicting solar activities in smart cities.

show abstract

Section: Related Workmentioning

confidence: 99%

Novel residual hybrid machine learning for solar activity prediction in smart cities

Abdulkadir,

Hasan,

Islam

et al. 2023

Earth Sci Inform

View full text Add to dashboard Cite

show abstract

“…Sunspot can affect the geomagnetic field and accurately predicting sunspot number can provide important information for navigation and wireless communication, which is of great significance. smoothed monthly mean sunspot number has strong chaotic properties, and it is more predictable than the monthly mean sunspot number, so we choose the monthly mean sunspot number as our dataset [37]. The Solar Influences Data Analysis Center (SIDC) records smoothed monthly mean sunspot number from 1749 to the present [38], we selected data from 1763 to 2018 as our experimental dataset.…”

Section: )Sunspot Time Seriesmentioning

confidence: 99%

Hetero-Dimensional Multitask Neuroevolution for Chaotic Time Series Prediction

Zhang

Jiang

2020

IEEE Access

View full text Add to dashboard Cite

Chaotic time series prediction has important research and application value, and neural network-based prediction methods have problems such as low accuracy and difficulty in determining the number of nodes in the hidden layer. In recent years, as a representative of evolutionary multitask optimization algorithms(EMTO), multifactorial evolutionary algorithms (MFEA) have achieved excellent results in Multitask Optimization (MTO) problems, but it does not work well in solving hetero-dimensional multitask problem. We analyzed this phenomenon and proposed the concept of harmful transfer. Then to solve these problems, in this paper, we propose the hetero-dimensional multitask neuroevolution algorithms (HD-MFEA neuroevolution) for chaotic time series prediction. First, we propose hetero-dimensional assortative mating algorithm and self-adaption elite replacement algorithm, so that the hetero-dimensional multitask evolutionary algorithm (HD-MFEA) can overcome the problems caused by harmful transfer on hetero-dimensional multitask problem. Second, in order to adapt to the hierarchical characteristics of neural networks, we propose the neural level segmental coding strategy. Third, we consider the optimization of neural networks with different hidden layer nodes as hetero-dimensional multitask problem and use the HD-MFEA neuroevolution to solve this problem. We verify the effectiveness of the HD-MFEA on six heterodimensional multitask benchmark problems. The Mackey-Glass, Lorenz and Sunspot time series are used to demonstrate the performance of the HD-MFEA neuroevolution. Experimental results have showed that the HD-MFEA neuroevolution performs well in predicting the chaotic time series problems.

show abstract

“…To get better knowledge on the solar cycle and its effects of the whole heliosphere, the recovery, digitization and analysis of the historical observations have begun in recent years. Lin et al (2019) digitized and constructed the parameters based on the Chinese historical sunspots drawings from 1925 to 2015. However, statistical work has to be followed in order to obtain the hidden scientific information.…”

Section: Introductionmentioning

confidence: 99%

Chinese sunspot drawings and their digitization – (III) quasi-biennial oscillation of the hand-drawn sunspot records

Wan

Zeng

Zheng

et al. 2020

Res. Astron. Astrophys.

View full text Add to dashboard Cite

Quasi-biennial Oscillations (QBOs) of the Sun have a significant meaning as a benchmark of solar cycle, not only for understanding the dynamo action but also in terms of space weather prediction. In this paper, the hand-drawn sunspot images recorded from the Purple Mountain Observatory are used to investigate the solar QBOs and the Gnevyshev gap of the sunspot relative numbers (Rs) and group sunspot numbers (Rg) during the period 1954–2011. The main results are as follows: (1) both the Rs and Rg exhibit similar periods including the 22-year magnetic cycle, the 11-year Schwabe cycle, and the QBOs modes; (2) the reconstructed QBOs of both data sets exhibit coherent behavior and tend to have a high amplitude during the maximum phase of each solar cycle; (3) the Gnevyshev gap is produced by the superposition of the QBOs and the 11-year Schwabe cycle, and the Rs is better to study the variation of the Gnevyshev gap rather than the Rg.

show abstract

Prediction of the Sunspot Number with a New Model Based on the Revised Data

Cited by 11 publications

References 18 publications

Novel residual hybrid machine learning for solar activity prediction in smart cities

Novel residual hybrid machine learning for solar activity prediction in smart cities

Hetero-Dimensional Multitask Neuroevolution for Chaotic Time Series Prediction

Chinese sunspot drawings and their digitization – (III) quasi-biennial oscillation of the hand-drawn sunspot records

Contact Info

Product

Resources

About