Generation of MLSO K-Coronagraph white light images from SDO/AIA EUV (171, 193 & 211 passbands) using deep learning
Abstract
In this study, we apply a deep learning method for the image-to-image translation from SDO/AIA (171,193 & 211) to MLSO K-coronagraph white light images. We train (from 1.11 to 1.25 Rs considering the FOV) the model using pairs of SDO/AIA images and their corresponding MLSO K-coronagraph images from 2014 to 2019 (January to September). We evaluate the model by comparing the pairs of MLSO K-coronagraph white light images and the corresponding ones generated from October and November of 2013 to 2019. Our main results from this study are as follows. First, the model successfully generates MLSO K-coronagraph-like white light images from SDO/AIA images. Second, in view of metrics, the generated images show a good correlation of ~ 0.87 which confirms that the generated images are consistent with the target ones. Third, we note that dominant coronal features such as helmet streamers and polar coronal holes are successfully generated. Utilizing these generated K-coronagraph-like white light images, we are looking for a possibility to detect early signatures of CMEs, to check streamer deflections by CME flanks, and to examine the association between coronal structures and high-frequency metric type IIs. Our method is expected to partially overcome the current limited observation time of MLSO observatory, and useful to study coronal features continuously.
NOTE: This work was supported by Institute for Information & communications Technology Promotion (IITP) grant funded by the Korea government (MSIP)(2018-0-01488, study on analysis and prediction technique of solar flares).- Publication:
-
AGU Fall Meeting Abstracts
- Pub Date:
- December 2020
- Bibcode:
- 2020AGUFMSH0370010L
- Keywords:
-
- 7599 General or miscellaneous;
- SOLAR PHYSICS;
- ASTROPHYSICS;
- AND ASTRONOMY;
- 7899 General or miscellaneous;
- SPACE PLASMA PHYSICS;
- 7999 General or miscellaneous;
- SPACE WEATHER