Neural Network Forecast of the Sunspot Butterfly Diagram

Abstract

Using neural networks as a prediction method, we attempt to demonstrate that forecasting of the Sun's sunspot time series can be extended to the spatial-temporal case. We employ this machine learning methodology to forecast not only in time but also in space (in this case the latitude) on a spatial-temporal dataset representing the solar sunspot diagram extending to a total of 142 years. The analysis shows that this approach seems to be able to reconstruct the overall qualitative aspects of the spatial-temporal series, namely the overall shape and amplitude of the latitude and time pattern of sunspots. This is, as far as we are aware, the first time neural networks have been used to forecast the Sun's sunspot butterfly diagram, and although the results are limited in the quantitative prediction aspects, it points the way to use the full spatial-temporal series as opposed to just the time series for machine learning approaches to forecasting. Further to that, we use the method to predict that the upcoming Cycle 25 maximum sunspot number will be around $R_{25}=57\pm 17$. This implies a very weak cycle and that it will be the weakest cycle on record.

References in corpus (17)

• Hidden Physics Models: Machine Learning of Nonlinear Partial Differential Equations
• Physics Informed Deep Learning (Part I): Data-driven Solutions of Nonlinear Partial Differential Equations
• Using Machine Learning to Replicate Chaotic Attractors and Calculate Lyapunov Exponents from Data
• Deep Hidden Physics Models: Deep Learning of Nonlinear Partial Differential Equations
• Physics Informed Deep Learning (Part II): Data-driven Discovery of Nonlinear Partial Differential Equations
• Hybrid Forecasting of Chaotic Processes: Using Machine Learning in Conjunction with a Knowledge-Based Model
• Calibrating 100 Years of Polar Faculae Measurements: Implications for the Evolution of the Heliospheric Magnetic Field
• An Updated Solar Cycle 25 Prediction with AFT: The Modern Minimum
• Deciphering Solar Magnetic Activity I: On The Relationship Between The Sunspot Cycle And The Evolution Of Small Magnetic Features
• A solar cycle lost in 1793--1800: Early sunspot observations resolve the old mystery
• The butterfly diagram in the 18th century
• Predicting the Amplitude and Hemispheric Asymmetry of Solar Cycle 25 with Surface Flux Transport
• A Comparison Between Global Proxies of the Sun's Magnetic Activity Cycle: Inferences from Helioseismology
• Identifying Potential Markers of the Sun's Giant Convective Scale
• Solar activity in the past and the chaotic behaviour of the dynamo
• Width of Sunspot Generating Zone and Reconstruction of Butterfly Diagram
• Spatial-temporal forecasting the sunspot diagram

Cited by in corpus (15)

• Solar cycle prediction
• Progress in Solar Cycle Predictions: Sunspot Cycles 24-25 in Perspective
• Forecasting Solar Cycle 25 using Deep Neural Networks
• Application of Synoptic Magnetograms to Global Solar Activity Forecast
• On Polar Magnetic Field Reversal in Solar Cycles 21, 22, 23, and 24
• North-South Asymmetry in Solar Activity and Solar Cycle Prediction, V: Prediction for the North-South Asymmetry in the Amplitude of Solar Cycle 25
• Spotless days and geomagnetic index as the predictors of solar cycle 25
• Optimal Neural Network Feature Selection for Spatial-Temporal Forecasting
• Zonal harmonics of solar magnetic field for solar cycle forecast
• Predicting the Evolution of Photospheric Magnetic Field in Solar Active Regions Using Deep Learning
• Effects of Observational Data Shortage on Accuracy of Global Solar Activity Forecast
• A comparative study of non-deep learning, deep learning, and ensemble learning methods for sunspot number prediction
• Solar Cycles: Can They Be Predicted?
• Solar Cycle Prediction: Challenges, Progress, and Future Perspectives
• Global Evolution of Solar Magnetic Fields and Prediction of Activity Cycles