E-Print Archive

There are 4291 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.

Solar Flares Forecasting Using Time Series and Extreme Gradient Boosting Ensembles  

Tiago Cinto   Submitted: 2020-04-28 20:14

Space weather events may cause damage to several fields, including aviation, satellites, oil and gas industries, and electrical systems, leading to economic and commercial losses. Solar flares are one of the most significant events, and refer to sudden radiation releases that can affect the Earth's atmosphere within a few hours or minutes. Therefore, it is worth designing high-performance systems for forecasting such events. Although in the literature there are many approaches for flare forecasting, there is still a lack of consensus concerning the techniques used for designing these systems. Seeking to establish some standardization while designing flare predictors, in this study we propose a novel methodology for designing such predictors, further validated with extreme gradient boosting tree classifiers and time series. This methodology relies on the following well-defined machine learning based pipeline: (i) univariate feature selection provided with the F-score; (ii) randomized hyper-parameter search and optimization; (iii) imbalanced data treatment through cost function analysis of classifiers; (iv) adjustment of cut-off point of classifiers seeking to find the optimal relationship between hit rate and precision; and (v) evaluation under operational settings. To verify our methodology effectiveness, we designed and evaluated three proof-of-concept models for forecasting >= C class flares up to 72 hours ahead. Compared to baseline models, those models were able to significantly increase their scores of true skill statistics (TSS) under operational forecasting scenarios by 0.37 (predicting flares in the next 24 hours), 0.13 (predicting flares within 24-48 hours), and 0.36 (predicting flares within 48-72 hours). Besides increasing TSS, the methodology also led to significant increases in the area under the ROC curve, corroborating that we improved the positive and negative recalls of classifiers while decreasing the number of false alarms.

Authors: Cinto, T., Gradvohl, A. L. S., Coelho, G. P. , da Silva, A. E. A.
Projects: None

Publication Status: Solar Phys. (preprint)
Last Modified: 2020-04-29 15:35
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
Solar Flares Forecasting Using Time Series and Extreme Gradient Boosting Ensembles

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