D-day 0 C O N T A C T S
REGISTRATION
PERSONAL INFORMATION
Submission Time: 2017-07-19 02:43:26 UTC


Email: espark@khu.ac.kr
First Name: Eunsu
Middle Name:
Last Name: Park
Name as it appears on badge : Eunsu Park
Affiliation: School of Space Research, Kyung Hee University
Nationality: Republic of Korea
Degree: Graduate Student


Preferred Working Group 1st Choice: WG 1 (Data)
Preferred Working Group 2nd Choice: WG 4 (Event Campaign)


PRESENTATION
Title : Application of Convolution Neural Network to the forecasts of flare classification and occurrence using SOHO MDI data
Abstract
A Convolutional Neural Network(CNN) is one of the well-known deep-learning methods in image processing and computer vision area. In this study, we apply CNN to two kinds of flare forecasting models: flare classification and occurrence. For this, we consider several pre-trained models (e.g., AlexNet, GoogLeNet, and ResNet) and customize them by changing several options such as the number of layers, activation function, and optimizer. Our inputs are the same number of SOHO)/MDI images for each flare class (None, C, M and X) at 00:00 UT from Jan 1996 to Dec 2010 (total 1600 images). Outputs are the results of daily flare forecasting for flare class and occurrence. We build, train, and test the models on TensorFlow, which is well-known machine learning software library developed by Google. Our major results from this study are as follows. First, most of the models have accuracies more than 0.7. Second, ResNet developed by Microsoft has the best accuracies : 0.86 for flare classification and 0.84 for flare occurrence. Third, the accuracies of these models vary greatly with changing parameters. We discuss several possibilities to improve the models.


LUNCH
Sep. 18

List





(c) 2017 KOREA ASTRONOMY AND SPACE SCIENCE INSTITUTE
All right reserved
776 Daedeokdae-ro, Yuseong-Ku, Daejeon, Rep. of Korea
Korea Business Registration Number : 314-82-06495
Name of Representative : Myung Gyoon Lee
Tel. 042-865-2052 Fax. 042-865-3358 Email. isest2017 (at) kasi.re.kr