Date of Award

2023

Document Type

Thesis

Degree Name

Master of Science (MS)

Department

Computer Science

Committee Chair

Timothy Newman

Committee Member

Jacob Hauenstein

Committee Member

Nikolai Pogorelov

Subject(s)

Solar flares--Forecasting, Data mining

Abstract

Data mining techniques that can support the forecasting of solar flares are explored. The main focus is to investigate the effects of flare coincidence on the evaluation of forecasts. Coincident flares are solar flares in a region of the Sun in which another flare has occurred recently, whereas other flares are denoted as non-coincident flares. Dimensionality reduction and classification are two of the types of techniques examined, where binary classification is used to issue yes/no forecasts of major solar flares. Five algorithms are considered as binary classifiers: k-nearest neighbors (k-NN), logistic regression (LR), support vector machines (SVM), random forest classifiers (RFC), and linear discriminant analysis (LDA). The methodologies, experimental results, and analyses of utilizing each algorithm are presented. The LR and RFC offered the highest True Skill Statistic (TSS) results.

Share

COinS
 
 

To view the content in your browser, please download Adobe Reader or, alternately,
you may Download the file to your hard drive.

NOTE: The latest versions of Adobe Reader do not support viewing PDF files within Firefox on Mac OS and if you are using a modern (Intel) Mac, there is no official plugin for viewing PDF files within the browser window.