E-Print Archive

There are 4282 abstracts currently viewable.


Search:

Advanced Search
Options
Main Page Add New E-Print Submitter
Information
Feedback
News Help/FAQ About Preferences
Manage Key Phrase
Notification
* News 04/04/20 * The archive is using a new backend database. This has thrown up a few SQL errors in the last few days. If you have any issues please email adavey@nso.edu with either the number of eprint you are trying to edit or a link to your preprint.

Forecasting Solar Cycle 25 Using Deep Neural Networks  

Bernard Benson   Submitted: 2020-05-19 16:21

With recent advances in the field of machine learning, the use of deep neural networks for time series forecasting has become more prevalent. The quasi-periodic nature of the solar cycle makes it a good candidate for applying time series forecasting methods. We employ a combination of WaveNet and Long Short-Term Memory neural networks to forecast the sunspot number using the years 1749 to 2019 and total sunspot area using the years 1874 to 2019 time series data for the upcoming Solar Cycle 25. Three other models involving the use of LSTMs and 1D ConvNets are also compared with our best model. Our analysis shows that the WaveNet and LSTM model is able to better capture the overall trend and learn the inherent long and short term dependencies in time series data. Using this method we forecast 11 years of monthly averaged data for Solar Cycle 25. Our forecasts show that the upcoming Solar Cycle 25 will have a maximum sunspot number around 106 19.75 and maximum total sunspot area around 1771 381.17. This indicates that the cycle would be slightly weaker than Solar Cycle 24.

Authors: B. Benson, W.D. Pan, A. Prasad, G.A. Gary, Q. Hu
Projects: None

Publication Status: Published, Solar Physics.
Last Modified: 2020-05-20 12:08
Go to main E-Print page  Edit Entry  Download Preprint  Delete Entry 

Determination of Linear Force-Free Magnetic Field Constant Alpha Using Deep Learning  

Bernard Benson   Submitted: 2017-12-04 17:12

Modeling the coronal magnetic field of the Sun is an important objective in heliophysics. In this study, we illustrate how to use deep learning to estimate the parameter for a magnetic field model. A linear force-free magnetic field configuration is employed to model, as an initial illustration, an active region by using two magnetic dipoles and to determine the associated linear force-free field (LFFF) α parameter from a set of pseudocoronal loop images which serve as training and validation sets to existing deep learning algorithms. Our results show very high accuracy of determining the LFFF parameter α from pseudocoronal loop images. Keywords?Sun; solar corona; solar activity; magnetic field models; deep learning;

Authors: Bernard Benson, Zhuocheng Jiang, W. David Pan, G. Allen Gary and Qiang Hu
Projects: SDO-AIA

Publication Status: Accepted to CSCI-ISAI 2017, Las Vegas Conference
Last Modified: 2017-12-05 11:51
Go to main E-Print page  Edit Entry  Download Preprint  Delete Entry 


Key
Go to main E-Print pageGo to main E-Print page.
Download PreprintDownload Preprint.
Submitter's HomepageSubmitters Homepage.
Edit EntryEdit Entry.
Delete AbstractDelete abstract.

Abstracts by Author
Forecasting Solar Cycle 25 Using Deep Neural Networks
Determination of Linear Force-Free Magnetic Field Constant Alpha Using Deep Learning

Related Pages
MSU Solar Physics.
Max Millennium Science Mail Archive.
Max Millennium Message of the Day Mail Archive.
Max Millennium Flare Catalog

Archive Maintainer
Alisdair Davey



© 2000-2020 Solar Physics Group - Montana State University