Multi-Channel Auto-Calibration for the Atmospheric Imaging Assembly instrument with Deep Learning
Abstract
Solar activity plays a quintessential role in influencing the interplanetary medium and space-weather around the Earth. Remote sensing instruments on-board heliophysics space missions provide a pool of information about the Sun's activity, via the measurement of its magnetic field and the emission of light from the multi-layered, multi-thermal and dynamic solar atmosphere. Ultraviolet (UV) and Extreme UV (EUV) wavelength observations from space help in understanding the subtleties of the outer layers of the Sun, namely the chromosphere and the corona. Unfortunately, such instruments, like the Atmospheric Imaging Assembly (AIA) onboard NASA's Solar Dynamics Observatory (SDO), suffer time-dependent degradation, that reduces their sensitivity. Current state-of-the-art calibration techniques rely on periodic sounding rockets which can be infrequent and rather unfeasible for deep-space missions. As a part of the Frontier Development Lab (FDL), we devised a convolutional neural network (CNN) based approach to calibrate or compensate for the concerned degradation, as an alternate to the sounding rocket missions. We use SDO-AIA data for our analysis that aims to perform the auto-calibration by exploiting spatial patterns on the solar surface across multi-wavelength observations. Our results show that CNN based models could comprehensively reproduce the outcomes of the sounding rocket experiments within a reasonable degree of accuracy, indicating that it performs equally well when compared with the current techniques. Furthermore, comparison with a standard "astronomer's technique" (baseline model) reveal that the CNN approach outperforms it quite significantly. This approach establishes the framework for a novel technique to calibrate (E)UV instruments and advance our understanding of the cross-channel relation between different (E)UV channels thereby paving the way to improved forecasting activities. FDL is a NASA co-operative agreement with SETI institute.
- Publication:
-
AGU Fall Meeting Abstracts
- Pub Date:
- December 2020
- Bibcode:
- 2020AGUFMNG0040032G
- Keywords:
-
- 1914 Data mining;
- INFORMATICS;
- 7833 Mathematical and numerical techniques;
- SPACE PLASMA PHYSICS;
- 7924 Forecasting;
- SPACE WEATHER;
- 7959 Models;
- SPACE WEATHER